Description:TECHNICAL FIELD
The present disclosure relates generally to a field of vehicle operation management, and more specifically, to a system and a method for predictive maintenance and fault detection in a fleet of delivery vehicles.
BACKGROUND
In today’s interconnected world, the importance logistics industries and associated technologies has significantly increased due to an efficient and fast transfer of goods and services between suppliers, warehouses, and end-users. Such a transfer is achieved generally through delivery vehicles. Currently, certain attempts have been made to detect the fault in the vehicle proactively while minimizing vehicle downtime and ensuring the safety of delivery vehicle riders. However, such attempts are limited to routine checks, predetermined schedules, and the like that are time-consuming as well as cost-intensive. Currently, there is no holistic approach or system that can be relied upon resulting in inefficiency, higher maintenance costs, compromised rider safety, and unexpected breakdowns, which is not desirable. Moreover, the risk of unplanned disruptions and delays increases, which is again not desirable. As a result, the current systems and methods are marred with issues of prolonged vehicle downtime, reduced delivery efficiency, heightened operational costs and risk of potential safety hazards for riders of delivery vehicles. Thus, there exists a technical problem of how to manage delivery vehicles effectively by anticipating potential issues or faults proactively without causing any actual (or real-time) damage to the vehicle as well as the rider with enhanced overall operational efficiency.
Therefore, in light of the foregoing discussion, there exists a need to overcome the aforementioned drawbacks associated with the conventional systems and methods for predictive maintenance and fault detection in a fleet of delivery vehicles.
SUMMARY
The present disclosure provides a system and a method for predictive maintenance and fault detection in a fleet of delivery vehicles. The present disclosure provides a solution to the existing problem of how to manage delivery vehicles effectively by anticipating potential issues or faults proactively without causing any actual (or real-time) damage to the vehicle as well as the rider with enhanced overall operational efficiency. An objective of the present disclosure is to provide a solution that overcomes at least partially the problems encountered in the prior art and provides an improved system and an improved method for predictive maintenance and fault detection in a fleet of delivery vehicles. In the present invention, the plurality of delivery vehicles are intelligently and automatically classified into a plurality of vehicle risk groups based on obtained vehicle dataset from each telematics component of the plurality of delivery vehicles and other datasets related to rider and vehicle. This innovative finding and classification that delivery vehicle belongs to which risk group in the domain of two-wheeler predictive maintenance is observed to significantly improve the accuracy and reliability of the disclosed system while preventing or reducing false positives (i.e., false fault prediction) drastically as compared to conventional fault detection systems.
One or more objectives of the present disclosure are achieved by the solutions provided in the enclosed independent claims. Advantageous implementations of the present disclosure are further defined in the dependent claims.
In one aspect, the present disclosure provides a system for predictive maintenance and fault detection in a fleet of delivery vehicles. The system includes a fault detection server that further includes a hardware processor. The hardware processor is configured to obtain a historical vehicle dataset of each delivery vehicle of a plurality of delivery vehicles from a first database, and a behavioural dataset of each rider of the plurality of riders from a second database. Furthermore, the hardware processor of the fault detection server is configured to obtain the vehicle dataset from a telematics component installed in each delivery vehicle of the plurality of delivery vehicles assigned to a plurality of riders. Thereafter, the hardware processor is configured to classify the plurality of delivery vehicles into a plurality of vehicle risk groups based on the obtained historical dataset and the obtained vehicle dataset from each telematics component of the plurality of delivery vehicles. Furthermore, the hardware processor is configured to dynamically detect and designate one or more potential faulty parts in the plurality of delivery vehicles that are to be proactively replaced or repaired in one or more upcoming time periods, based on the obtained historical vehicle dataset, the obtained vehicle dataset, and the classification of the plurality of delivery vehicles into the plurality of vehicle risk groups.
The system of the present disclosure provides an efficient, reliable, and accurate predictive maintenance and fault detection in the fleet of the delivery vehicles. For example, the hardware processor integrates the historical delivery dataset, the behavioural dataset, and the vehicle dataset to predict the maintenance that is required in each the delivery vehicle and also to detect faults in the fleet of the delivery vehicle in advance. This integration allows for a holistic view of each of the plurality of delivery vehicles while considering past performance, behavioural characteristics, and vehicle handling skills of the riders. Therefore, by employing these datasets (i.e., the plurality of the delivery vehicle’s datasets and the rider’s dataset), the system is configured to anticipate potential faults accurately and maintenance that is required to be done even before the escalation of these potential faults into critical issues along with the identification of the rider’s accountability. For example, the system can differentiate between a rider who rides his assigned delivery vehicle responsibly and carefully and another rider who rides rashly and carelessly. In both cases, the system is configured to penalize both riders in a different manner (e.g., by imposing fines or penalties or rash use, and the like) that increases the rider’s accountability towards the assigned delivery vehicle.
Furthermore, the system also ensures judicious penalty imposition analyses to prevent any false penalty imposition, for example, if any rider shifts from aggressive driving to a more cautious style, the system accounts for this change and adjusts the maintenance predictions of the corresponding delivery vehicle along with the penalty that can be imposed on the rider according to such change. Moreover, the dynamic classification of the plurality of delivery vehicles into the plurality of risk groups and designation of the one or more potential faulty parts provides a significant technical effect over conventional systems of significantly reducing or even preventing mostly unexpected breakdowns, minimizing vehicle downtime, and ensuring that the maintenance efforts and resources are optimized by more than 30 to 75% over conventional systems. Additionally, the system also provides personalized maintenance strategies to the classified plurality of vehicle risk groups based on different risk groups, technicalities, historical dataset, and the vehicle dataset for each of the plurality of delivery vehicles. Consequently, the delivery vehicles that are prone to higher risks receive more attention, while those with lower risks are subjected to fewer interventions, saving time and resources. Hence, the system is configured to manage delivery vehicles effectively by anticipating potential issues or faults proactively without causing any actual (or real-time) damage to the vehicle as well as the rider with enhanced overall operational efficiency.
In another aspect, the present disclosure provides a method for predictive maintenance and fault detection in a fleet of delivery vehicles. Moreover, the method includes obtaining a historical vehicle dataset of each delivery vehicle of a plurality of delivery vehicles from a first database, and a behavioural dataset of each rider of the plurality of riders from a second database. Furthermore, obtaining a vehicle dataset from a telematics component installed in each delivery vehicle of the plurality of delivery vehicles assigned to a plurality of riders, classify the plurality of delivery vehicles into a plurality of vehicle risk groups based on the obtained historical dataset and the obtained vehicle dataset from each telematics component of the plurality of delivery vehicles and dynamically detecting and designating one or more at potential faulty parts in the plurality of delivery vehicles that are to be proactively replaced or repaired in one or more upcoming time periods, based on the obtained historical vehicle dataset, the obtained vehicle dataset, and the classification of the plurality of delivery vehicles plurality into the plurality of vehicle risk groups.
The method achieves all the advantages and technical effects of the system of the present disclosure.
It will be appreciated that features of the present disclosure are susceptible to being combined in various combinations without departing from the scope of the present disclosure as defined by the appended claims.
Additional aspects, advantages, features, and objects of the present disclosure would be made apparent from the drawings and the detailed description of the illustrative implementations construed in conjunction with the appended claims that follow.
BRIEF DESCRIPTION OF THE DRAWINGS
The summary above, as well as the following detailed description of illustrative embodiments, is better understood when read in conjunction with the appended drawings. For the purpose of illustrating the present disclosure, exemplary constructions of the disclosure are shown in the drawings. However, the present disclosure is not limited to specific methods and instrumentalities disclosed herein. Moreover, those in the art will understand that the drawings are not to scale. Wherever possible, like elements have been indicated by identical numbers.
Embodiments of the present disclosure will now be described, by way of example only, with reference to the following diagrams wherein:
FIG. 1 is a block diagram of a system for predictive maintenance and fault detection in a fleet of delivery vehicles, in accordance with an embodiment of the present disclosure;
FIG. 2 is a block diagram of a plurality of delivery vehicles, in accordance with an embodiment of the present disclosure;
FIG. 3A is a scenario-based diagram that depicts an exemplary scenario illustrating predictive maintenance and fault detection in a fleet of delivery vehicles, in accordance with an embodiment of the present disclosure;
FIG. 3B is a scenario-based diagram that depicts an exemplary scenario that depicts an exemplary predictive maintenance alert generated by a system illustrating predictive maintenance and fault detection, in accordance with an embodiment of the present disclosure; and
FIG. 4 is a flowchart that depicts a method for predictive maintenance and fault detection in a fleet of delivery vehicles, in accordance with an embodiment of the present disclosure.
In the accompanying drawings, an underlined number is employed to represent an item over which the underlined number is positioned or an item to which the underlined number is adjacent. A non-underlined number relates to an item identified by a line linking the non-underlined number to the item. When a number is non-underlined and accompanied by an associated arrow, the non-underlined number is used to identify a general item at which the arrow is pointing.
DETAILED DESCRIPTION OF EMBODIMENTS
The following detailed description illustrates embodiments of the present disclosure and ways in which they may be implemented. Although some modes of carrying out the present disclosure have been disclosed, those skilled in the art would recognize that other embodiments for carrying out or practicing the present disclosure are also possible.
FIG. 1 is a block diagram of a system for predictive maintenance and fault detection in a fleet of delivery vehicles, in accordance with an embodiment of the present disclosure. With reference to FIG. 1, there is shown a block diagram of a system 100. The system 100 includes a fault detection server 102 that further includes a hardware processor 104, a historical dataset 108A, a behavioural dataset 108B, a vehicle dataset 108C, a first database 106A, a second database 106B, and a predictive maintenance module 112. There is further shown a plurality of delivery vehicles 116, a communication network 114, and a plurality of riders 118.
The fault detection server 102 is configured to be used in the system 100 for the predictive maintenance and fault detection in the fleet of delivery vehicles. In an implementation, the fault detection server 102 may be a master server or a master machine that is a part of a data centre that controls an array of other cloud servers communicatively coupled to it for load balancing, running customized applications, and efficient data management. Examples of implementation of the fault detection server 102 may include but are not limited to, a dedicated server, a storage server, a cloud-based server, a web server, an application server, or a combination thereof.
The hardware processor 104 is configured to obtain various datasets (e.g., the historical dataset 108A, the behavioural dataset 108B, and the vehicle dataset 108C) and further dynamically detect and designate one or more potential faulty parts in the plurality of delivery vehicles 116 that are to be proactively replaced or repaired in one or more upcoming time periods. Examples of implementation of the hardware processor 104 may include but are not limited to a central data processing device, a microprocessor, a microcontroller, a complex instruction set computing (CISC) processor, an application-specific integrated circuit (ASIC) processor, a reduced instruction set (RISC) processor, a very long instruction word (VLIW) processor, a central processing unit (CPU), a state machine, a data processing unit, and other processors or circuitry. Moreover, the first database 106A and the second database 106B refers to a database that is accessible via the internet, typically through a web browser. Moreover, the first database 106A is configured to store the historical dataset 108A and the second database 106B is configured to store the behavioural dataset 108B.
The communication network 114 includes a medium (e.g., a communication channel) through which the fault detection server 102, potentially communicates with the plurality of delivery vehicles 116. Examples of the communication network 114 may include but are not limited to, the Internet, a Local Area Network (LAN), a wireless personal area network (WPAN), a Wireless Local Area Network (WLAN), a wireless wide area network (WWAN), a cloud network, a Long-Term Evolution (LTE) network, a plain old telephone service (POTS), a Metropolitan Area Network (MAN), and/or the Internet.
Each rider in the plurality of riders 118 refers to a delivery personnel who operates a delivery vehicle from the plurality of delivery vehicles 116. Each rider in the plurality of riders 118 possesses specific preferences, requirements, and characteristics, such as vehicle handling skills, responsive and careful vehicle driving, and the like. The plurality of riders 118 includes a first rider 118A, a second rider 118B, and up to Nth rider 118N, and each of the riders from the plurality of riders 118 is assigned a specific delivery vehicle from the plurality of delivery vehicles 116.
There is provided the system 100 for predictive maintenance and fault detection in a fleet of delivery vehicles. The fleet of delivery vehicles refers to the plurality of delivery vehicles 116 that are specifically designated or employed to transport goods or provide delivery services within the delivery network. The plurality of delivery vehicles 116 plays a crucial role in facilitating the movement of items from one location to another, ensuring timely and efficient deliveries. In some implementations, the plurality of delivery vehicles 116 includes various types of transportation means, such as trucks, vans, cars, motorcycles, bicycles, or any other suitable mode of transport. The plurality of delivery vehicles 116 includes a first delivery vehicle 116A, a second delivery vehicle 116B, and up to Nth delivery vehicle 116N and each of the plurality of delivery vehicle 116 includes a telematic component 110. For example, the first delivery vehicle 116A includes a first telematic component 110A, and the second delivery vehicle 116B includes a second telematics component 110B. Similarly, the nth delivery vehicle 116N includes a nth telematic component 110N. The system 100 is configured to provide comprehensive and intelligent analysis of different datasets that can be further used to provide accurate and reliable predictive vehicle maintenance and fault detection that can be further used to optimize vehicle performance, minimize downtime due to faults, enhance rider accountability, and ultimately ensures efficient and reliable fleet operations.
The hardware processor 104 of the fault detection server 102 is configured to obtain the historical dataset 108A of each delivery vehicle of the plurality of delivery vehicles 116 from the first database 106A, and the behavioural dataset 108B of each rider of the plurality of riders 118 from the second database 106B. In an example, the hardware processor 104 is configured to obtain the historical dataset 108A of the first delivery vehicle 116A from the first database 106A. In another example, the hardware processor 104 is configured to obtain the historical dataset 108A of the second delivery vehicle 116B from the first database 106A. In yet another example, the hardware processor 104 is configured to obtain the historical dataset 108A of the nth delivery vehicle 116N from the first database 106A. Similarly, the hardware processor 104 is configured to obtain the behavioural dataset 108B of the first rider 118A of a plurality of rider 118 and the behavioural dataset 108B of the second rider 118B of the plurality of rider 118 from the second database 106B. As a result, the hardware processor 104 is configured to obtain the historical dataset 108A and the behavioural dataset 108B, which can be further used for analyzing the datasets (i.e., the historical dataset 108A, and the behavioural dataset 108B) to obtain accurate and reliable decision-making and fleet management with precise fault detection, and enhanced rider performance accountability.
In an implementation, the historical dataset 108A includes a unique vehicle identifier of each delivery vehicle, a manufacturing year of each delivery vehicle, a vehicle mileage, a last service date, and a last repaired part or replaced part of each delivery vehicle, a unique vehicle identifier of each rider assigned to each delivery vehicle. For example, the historical dataset 108A includes a unique vehicle identifier, the manufacturing year of the first delivery vehicle 116A, a vehicle mileage, the last service date, and the last repaired part or replaced part of the first delivery vehicle 116A, a unique vehicle identifier of the first rider 118A assigned to the first delivery vehicle 116A. Similarly, the historical dataset 108A may include a unique vehicle identifier of the second delivery vehicle 116B, the manufacturing year of the second delivery vehicle 116B, a vehicle mileage, the last service date, and the last repaired part or replaced part of the second delivery vehicle 116B, a unique vehicle identifier of the first rider 118A assigned to the second delivery vehicle 116B. Moreover, the historical dataset 108A is collected from various sources, such as a plurality of sensors, rider feedback, mechanics feedback, service providers, and the like in order to analyse the current trend associated with each of the plurality of delivery vehicles 116. As a result, by virtue of using the historical dataset 108A, the system 100 is configured to determine the type of maintenance and the time interval at which the maintenance is required for each of the plurality of delivery vehicles 116 efficiently and accurately based on the analyses of the past trends of each of the plurality of delivery vehicles 116.
In an implementation, the behavioural dataset 108B includes vehicle handling information associated with each rider, a set of active time periods in a day for each rider, and a set of dormant time periods in the day of each rider from the plurality of riders 118. The behavioural dataset 108B refers to information on how each rider, such as the first rider 118A, the second rider 118B, and the like handles the corresponding delivery vehicle, time intervals during a day when the rider is actively using the delivery vehicle, as well as a dormant time interval within the same day when the rider is not using the delivery vehicle. In an implementation, the behavioural dataset 108B, such as a mobile device or a computing device, rider’s feedback, user’s feedback on the rider’s deliveries, and the like can be collected through the rider’s device as well as the user’s device. As a result, the behavioural dataset 108B is used to provide insights into rider habits, vehicle usage patterns, and activity levels, contributing to a better understanding of rider behaviour and aiding in the formulation of strategies for enhanced fleet management and maintenance as well as for determining rider’s accountability towards the assigned delivery vehicle from the plurality of delivery vehicles 116.
Furthermore, the hardware processor 104 is configured to obtain the vehicle dataset 108C from a telematics component 110 installed in each delivery vehicle of the plurality of delivery vehicles 116 assigned to the plurality of riders 118. In an implementation, the telematics component 110 refers to a device that is installed in each of the plurality of delivery vehicles and is configured to collect and further transmit various types of data, such as location information, vehicle diagnostics, driving behaviour, and the like, to the fault detection server 102 which can be further used for monitoring, analysis, and remote management purposes. In an example, the hardware processor 104 is configured to obtain the vehicle dataset 108C from the first telematics component 110A installed in the first delivery vehicle 116A of the plurality of delivery vehicle 116, which is assigned to the first rider 118A. In another example, the hardware processor 104 is configured to obtain the vehicle dataset 108C from the second telematics component 110B installed in the second delivery vehicle 116B of the plurality of delivery vehicle 116, which is assigned to the second rider 118B. In yet another example, the hardware processor 104 is configured to obtain the vehicle dataset 108C from Nth telematics component 110N installed in the Nth delivery vehicle 116N of the plurality of delivery vehicle 116, which is assigned to the Nth rider 118N. Moreover, an example of the telematics component 110 installed in each of the plurality of delivery vehicles 116 to obtain the vehicle dataset 108C is further described in detail in FIG. 2. By analysing the vehicle dataset 108C from each of the telematics components 110 installed in each of the plurality of delivery vehicles 116 enables the hardware processor 104 of the system 100 to identify various vehicle-related insights that can be further used for analysis and maintenance predictions.
In an implementation, in order to obtain the vehicle dataset 108C from the telematics component 110, the telematics component 110 is configured to acquire sensor data from the plurality of sensors placed in each delivery vehicle of the plurality of delivery vehicles 116 and transmit the acquired sensor data to the fault detection server 102 for remote analysis and monitoring. In other words, the plurality of sensors, such as a gyro sensor, a location sensor, and an accelerometer is placed in each of the plurality of delivery vehicles 116, such as the first delivery vehicle 116A, the second delivery vehicle 116B up to the nth delivery vehicle 116N. After that, the plurality of sensors are configured to capture valuable information, such as acceleration, location, motion capturing, the number of times the parts of the delivery vehicles are replaced/repaired, and the like. For example, the gyro sensor is configured to capture vehicle orientation-related data of each of the delivery vehicles 116, and the accelerometer is configured to capture the vibrations of the vehicle to determine the acceleration and deacceleration pattern of each of the plurality of delivery vehicles 116. Similarly, the location sensor is configured to measure the location-related data of each of the plurality of delivery vehicles 116. Furthermore, each of the telematics components 110, which is installed in each of the plurality of delivery vehicles 116 is configured to transmit the collected data to the fault detection server 102. As a result, the collected data can be used by the fault detection server 102 to provide real-time insights into the operational status of each of the plurality of delivery vehicles 116, enabling timely identification of potential issues and optimized maintenance strategies to enhance fleet management efficiency, reduces downtime, and ensures cost-effective maintenance practices.
Furthermore, the hardware processor 104 is configured to classify the plurality of delivery vehicles 116 into the plurality of vehicle risk groups based on the obtained historical dataset 108A and the obtained vehicle dataset 108C from each telematics component of the plurality of delivery vehicles 116. An example of the classification of the plurality of delivery vehicles 116 into the plurality of vehicle risk groups based on the obtained historical dataset 108A and the vehicle dataset 108C obtained from each telematics component of the plurality of delivery vehicles 116 is further described in detail in FIG. 3A. For example, the plurality of delivery vehicles 116 are classified as a “first vehicle risk group”, a “second vehicle risk group”, and a “third vehicle risk group”. Moreover, each of the vehicle risk groups from the plurality of the vehicle risk groups depicts a different risk level associated with the corresponding vehicle risk groups, for example, the “first vehicle risk group” includes the delivery vehicles with more age and the delivery that are in the worst situation. Similarly, the “second vehicle risk group” includes the delivery vehicles in better condition, and the “third vehicle risk group” includes the delivery vehicles that are new and are in a good situation. As a result, the system 100 is configured to predict and manage potential issues accurately and reliably, contributing to the effective fleet maintenance, targeted intervention, and optimized operational strategies.
In order to classify the plurality of delivery vehicles 116 into the plurality of vehicle risk group, the hardware processor (104) analyze both the historical dataset and the telematics vehicle dataset to identify risk factors that could contribute to potential incidents, accidents, and faulty parts. These risk factors include a) frequency of incidents which indicate how often the vehicle has been involved in incidents or accidents; b) severity of accidents which indicate an extent of damage caused by past accidents; c) terrain conditions from GPS data which indicate whether the vehicle is frequently driven in challenging terrains; d) abrupt acceleration and deceleration patterns that indicate aggressive driving behaviour that might increase the risk of accidents or wear and tear of vehicle; e) tilting events from gyro sensor data which identifies instances where the vehicle tilts or experiences abnormal movement. After risk factors are identified, the system 100 assigns numerical values or scores to each identified risk factor based on many factors. For example, higher scores are assigned to vehicles with higher incident frequency or severity; scores assignment further takes into account the type of terrain the vehicle operates in, considers the intensity and frequency of abrupt acceleration and deceleration and quantifies the extent of tilting events. Based on such technical operations, the system 100 automatically and intelligently clusters the vehicles into different risk groups based on the quantified risk scores. For instance: First vehicle risk group: Vehicles with low-risk scores across all factors; Second vehicle risk group: Vehicles with moderate risk scores indicating some potential issues; and third vehicle risk group: Vehicles with high-risk scores suggesting a higher likelihood of incidents or mechanical problems. This grouping might be initially determined based on predefined thresholds. However, the system may employ machine learning techniques to validate and refine the grouping over time. As more data is collected and incidents occur, the system can adjust the risk thresholds and factors accordingly. Once the vehicles are grouped into risk categories, this classification can be used for various purposes, a) prioritizing maintenance, i.e., vehicles in higher risk groups receive more attention and regular maintenance checks; b) allocating resources, i.e., higher-risk vehicles might be assigned to less experienced drivers, or specific routes could be adjusted based on risk levels, and the like. This approach allows for proactive risk management and tailored maintenance strategies for each vehicle from thousands to millions of vehicles with increased accuracy.
In accordance with an embodiment, the hardware processor 104 is configured to analyse the historical dataset 108A and the vehicle dataset 108C to identify relevant risk factors including a frequency of incidents, a severity of accidents, terrain conditions from GPS data, abrupt acceleration and deceleration patterns from accelerometer data, and tilting events from gyro sensor data for the classification of the plurality of delivery vehicles 116 into the plurality of vehicle risk groups 302 indicative of differing levels of potential risk for future incidents and for causing potential faulty parts at different upcoming time periods. In an implementation, the gyro sensor is used to obtain the gyro sensor data corresponding to various tilt events, the frequency of incidents, the severity of accidents, and the terrain conditions can be analysed by the GPS data obtained from the location sensor. In another implementation, the abrupt acceleration and deceleration patterns can be analysed by analyzing the accelerometer data, which is obtained by the accelerometer. In an implementation, the plurality of sensors, such as the gyro sensors, the accelerometer, and the location sensors are used to obtain the historical dataset 108A and the vehicle dataset 108C. Furthermore, the hardware processor 104 is configured to identify the relevant risk factors associated with each of the plurality of delivery vehicles 116. which is obtained from the accelerometer. For example, the exact condition of the brake pads and the risk associated with the brake pads of the first delivery vehicle 116A can be analysed by the gyro sensor data obtained from the gyro sensor. Similarly, the terrain and other delivery vehicle-related risks can be analysed by the data obtained by the plurality of sensors placed on each of the plurality of sensors, such as through each of the telematics components installed in each of the plurality of delivery vehicles 116. As a result, the obtained historical dataset 108A and the vehicle dataset 108C are used to facilitate the classification of the entire fleet of delivery vehicles into the plurality of vehicle risk groups. Moreover, the plurality of delivery vehicle risk groups varies in degrees of potential risk for future incidents and the possibility of causing potential faulty parts within different forthcoming time periods. As a result, the obtained historical dataset 108A and the vehicle dataset 108C can be used to provide valuable insights into which vehicles are more likely to encounter incidents or develop faulty parts, and it does so by considering a range of factors like accident history, driving behaviour, terrain conditions, and mechanical stresses that are used to optimize maintenance efforts, reduce downtime, and enhance overall fleet safety and reliability.
Furthermore, the hardware processor 104 is configured to dynamically detect and designate one or more potential faulty parts in the plurality of delivery vehicles 116 that are to be proactively replaced or repaired in one or more upcoming time periods, based on the obtained historical dataset 108A, the obtained vehicle dataset 108C, and the classification of the plurality of delivery vehicles 116 into the plurality of vehicle risk groups. In other words, the hardware processor 104 is configured to obtain the historical dataset 108A and the vehicle dataset 108C from the telematics component 110 installed in each of the plurality of delivery vehicles 116. After that, the hardware processor 104 is configured to classify the plurality of delivery vehicles 116 into the plurality of vehicle risk groups, such as the first group, the second group, and the third group. Finally, the hardware processor 104 is configured to detect and designate the one or more potential faulty parts (e.g., brake pads, engine components, battery, tire tread, fluid leakage, damaged shocks, steering components, throttle wire, and the like) in each of the plurality of delivery vehicles 116. In an example, the hardware processor 104 detects that the brake pads of the first delivery vehicle 116A are worn-out, in that case, the hardware processor 104 is configured to designate the corresponding brake pads as worn-out. In another example, the battery of the second delivery vehicle 116B is detected as weak along with the engine component of the second delivery vehicle 116B, which is detected as faulty. In such a case, the hardware processor 104 is configured to designate the corresponding parts as faulty. As a result, the identification of the one or more faulty parts in the plurality of delivery vehicles 116 enables the system 100 to proactively address emerging problems before their impact operations to ensure that the maintenance efforts are aligned with actual needs, leading to streamlined operational efficiency.
In accordance with an embodiment, the hardware processor 104 is configured to determine a penalty to be imposed on one or more riders of the plurality of riders 118, based on the obtained historical dataset 108A, the obtained vehicle dataset 108C, the obtained behavioural dataset 108B, the classification of the plurality of delivery vehicles 116 plurality into the plurality of vehicle risk groups 302, and dynamically detected one or more potential faulty parts in the plurality of delivery vehicles 116. In an example, the first rider 118A consistently follows safe driving practices, adheres to speed limits, and maintains the delivery vehicle assigned to the rider properly. The historical dataset 108A along with the vehicle dataset 108C, which is collected by the telematics component installed in each of the plurality of delivery vehicle 116 indicates that the assigned delivery vehicle (e.g., the first delivery vehicle 116A) has a low record of breakdowns or faults. In such an example, the system 100 might not recommend any penalties for the first rider, given their responsible behaviour and the good condition of their vehicle. In another example, the second rider 118B has a history of aggressive driving and frequent hard braking, which has led to increased wear and tear of the vehicle components of the delivery vehicle assigned to the corresponding delivery vehicle. The historical dataset 108A, the behavioural dataset 108B, and the vehicle dataset 108C reflect a higher number of maintenance incidents related to this rider's vehicles and also highlight instances of rapid acceleration and abrupt braking. In such an example, the system 100 is configured to recommend imposing a penalty on the second rider due to their behaviour and the increased risk of vehicle faults. Therefore, by analyzing the collected data and the classification of vehicles into risk groups, the hardware processor 104 is configured to make an informed decision about penalties, such as by assessing the rider’s behaviour, vehicle condition, and risk factors. As a result, the system 100 is configured to determine whether penalties should be imposed and to what extent that ensures that penalties are fair, based on actual data, and encourages better practices among the riders in the fleet contributing to the effective management of the entire fleet, ensuring operational efficiency, rider safety, and the minimization of undue expenses.
In accordance with an embodiment, the system 100 includes the predictive maintenance module 112 configured to identify correlations between rotational and orientation data, location, terrain, acceleration patterns, and stoppage time of each delivery vehicle from the vehicle dataset 108C acquired from the telematics component of each vehicle, to generate predictive maintenance alerts. For example, the predictive maintenance module 112 is configured to identify the correlation between associate abrupt accelerations with increased wear on specific parts or link frequent stops in challenging terrains with potential strain on certain components, such as by obtaining the historical dataset 108A and the vehicle dataset 108C of the first delivery vehicle 116A. In other words, the predictive maintenance module 112 is configured to receive data from the gyro sensor and further process the received data to determine the rotational and orientation characteristics of each of the plurality of delivery vehicles 116. Moreover, the predictive maintenance module 112 is executed by the hardware processor 104 to analyse the historical rotational and orientation data and identify patterns or anomalies indicative of potential faults or wear in the delivery vehicle. Furthermore, the predictive maintenance module 112 is configured to generate predictive maintenance alerts based on the identified patterns or anomalies. In addition, the maintenance alerts include recommendations for maintenance or corrective actions that are required to be taken to ensure the delivery vehicle’s reliability and rider’s safety. Moreover, an example of the generation of the predictive maintenance alerts is further described in detail in FIG. 3B. As a result, the system 100 is configured to enhance vehicle reliability and extend the lifespan of each part of the plurality of delivery vehicles 116 by ensuring a smoother operation of the fleet and improved rider satisfaction, such as by anticipating the potential maintenance requirements of each of the plurality of delivery vehicles 116.
In accordance with an embodiment, the hardware processor 104 is configured to refine the predictive maintenance alerts by adapting to the evolving rider behaviour and usage patterns of each rider. In an implementation, a user interface module can be used to provide access to predictive maintenance alerts and real-time rotational and orientation data, enabling fleet managers to make timely maintenance decisions and optimize delivery vehicle performance. As a result, the system 100 leads to precise and relevant predictive maintenance alerts that improve the overall effectiveness of the predictive maintenance system, leading to more efficient maintenance practices, reduced unnecessary interventions, and optimized fleet management.
Advantageously, the system 100 of the present disclosure provides an efficient, reliable, and accurate predictive maintenance and fault detection in the fleet of the delivery vehicles. For example, the hardware processor 104 integrates the historical dataset 108A, the behavioural dataset 108B, and the vehicle dataset 108C to predict the maintenance that is required in each the delivery vehicle and also to detect faults in the fleet of the delivery vehicle. This integration allows for a holistic view of each of the plurality of delivery vehicles 116 while considering past performance, behavioural characteristics, and vehicle handling skills of the riders. Therefore, by employing these datasets (i.e., the historical dataset 108A, the behavioural dataset 108B, and the vehicle dataset 108C), the system 100 is configured to anticipate potential faults accurately and maintenance that is required to be done even before the escalation of these potential faults into critical issues along with the identification of the rider’s accountability. For example, the system 100 is able to differentiate between a rider who rides his assigned delivery vehicle responsibly and carefully and another rider who rides rashly and carelessly. In both cases, the system 100 is configured to penalize both riders in a different manner (e.g., by imposing fines or penalties or rash use, and the like) that increases the rider’s accountability towards the assigned delivery vehicle.
Furthermore, the system 100 also ensures judicious penalty imposition analyses to prevent any false penalty imposition, for example, if any rider shifts from aggressive driving to a more cautious style, the system 100 accounts for this change and adjusts the maintenance predictions of the corresponding delivery vehicle along with the penalty that can be imposed on the rider according to such change. Moreover, the dynamic classification of the plurality of delivery vehicles 116 into the plurality of risk groups and designation of the one or more potential faulty parts prevents unexpected breakdowns, minimizes vehicle downtime, and ensures that the maintenance efforts are strategic and aligned with actual requirements. Additionally, the system 100 also provides personalized maintenance strategies to the classified plurality of vehicle risk groups based on different risk groups, technicalities, historical dataset, and the vehicle dataset for each of the plurality of delivery vehicles 116. Consequently, the delivery vehicles that are prone to higher risks receive more attention, while those with lower risks are subjected to fewer interventions, saving time and resources. Hence, the system 100 is configured to manage delivery vehicles effectively by anticipating potential issues or faults proactively without causing any actual (or real-time) damage to the vehicle as well as the rider with enhanced overall operational efficiency.
FIG. 2 is a block diagram of a plurality of delivery vehicles, in accordance with an embodiment of the present disclosure. With reference to FIG. 2, there is shown a block diagram of a plurality of delivery vehicles (i.e., the plurality of delivery vehicles 116 of FIG. 1).
There is provided the plurality of delivery vehicle 116 that includes the first delivery vehicle 116A, the second delivery vehicle 116B, up to the nth delivery vehicle 116N. The system 100 is configured to obtain the vehicle dataset 108C from the telematics components 110 (e.g., the first telematics component 110A, the second telematics component 110B, up to the Nth telematics component 110N) installed in each delivery vehicle (i.e., the first delivery vehicle 116A, the second delivery vehicle 116B, up to the Nth delivery vehicle 116N) of the plurality of delivery vehicles 116 assigned to the plurality of riders 118 (i.e., the first rider 118A, the second rider 118B, up to the Nth rider 118N). Furthermore, each of the telematics components that are installed in each of the plurality of delivery vehicles 116 is configured to acquire sensor data from a plurality of sensors 202 placed in each delivery vehicle of the plurality of delivery vehicles116. For example, the first telematics component 110A is installed in the first delivery vehicle 116A to acquire the sensor data from a first plurality of sensors 202A of the first delivery vehicle 116A and the second telematics component 110B is installed in the second delivery vehicle 116B to acquire the sensor data from a second plurality of sensors 202B of the second delivery vehicle 116B. Similarly, the nth telematics component 110N is installed in the nth delivery vehicle 116N to acquire the sensor data from nth plurality of sensors 202N of the nth delivery vehicle 116N.
In accordance with an embodiment, the plurality of sensors includes any two or more of a gyro sensor, a location sensor, and an accelerometer. In other words, each of the plurality sensors, such as the first plurality of sensors 202A, the second plurality of sensors 202B, up to the nth plurality of sensors 202N includes a gyro sensor, a location sensor, and an accelerometer without affecting the scope of the present disclosure. For example, the first plurality of sensors 202A includes a first gyro sensor 204A, a first location sensor 206A, and a first accelerometer 208A. Similarly, the second plurality of sensors 202B includes a second gyro sensor 204B, a second location sensor 206B, and a second accelerometer 208B and the nth plurality of sensors 202N includes nth gyro sensor 204N, nth location sensor 206N, and nth accelerometer 208N. In an implementation, the first gyro sensor 204A, the second gyro sensor 204B, up to the nth gyro sensor 204N refer to a device that is used for measuring the rotation or orientation of each of the plurality of delivery vehicles 116. Moreover, the sensor data that is captured by the gyro sensors, such as the first gyro sensor 204A, the second gyro sensor 204B, up to the nth gyro sensor 204N is used to detect any deviation in the delivery vehicle’s orientation that can be further used to detect any accident or any unpredicted tilt that may harm the safety of the rider. In another implementation, the location sensor (e.g., the first location sensor 206A, the second location sensor 206B, and the like) refers to a type of sensor, which is used to detect the exact location of each of the plurality of delivery vehicles 116 that can be further used to know the terrain on which the delivery vehicle is running. In yet another implementation, the accelerometer sensor (e.g., the first accelerometer 208A, the second accelerometer 208B, and the like) refers to an accelerometer, which is used to calculate acceleration, deacceleration, the stoppage time intervals, and the like of each of the plurality of delivery vehicles 116. Moreover, each of the telematics component 110 transmits the acquired sensor data to the fault detection server (i.e., the fault detection server 102) for remote analysis and monitoring. For example, the first telematics component 110A of the first delivery vehicle 116A transmits the acquired sensor data which is acquired from the first gyro sensor 204A, the first location sensor 206A, and the first accelerometer 208A to the fault detection server 102. In addition, the acquired sensor data is stored in multiple databases, such as the first database 106A, and the second database 106B in the form of the historical dataset 108A and the vehicle dataset 108C. Moreover, the historical dataset 108A includes a unique vehicle identifier of each delivery vehicle, the manufacturing year of each delivery vehicle, a vehicle mileage, the last service date, and the last repaired part or replaced part of each delivery vehicle, a unique vehicle identifier of each rider (e.g., the first rider 118A, the second rider 118B, up to the nth rider 118N) assigned to each delivery vehicle (e.g., the first delivery vehicle 116A, the second delivery vehicle 116B, up to the nth delivery vehicle 116N).
The hardware processor 104 of the system 100 is configured to analyse the historical dataset 108A and the vehicle dataset 108C to identify relevant risk factors including the frequency of incidents, the severity of accidents, terrain conditions from GPS data, abrupt acceleration and deceleration patterns from accelerometer data, and tilting events from gyro sensor data for the classification of the plurality of delivery vehicles into the plurality of vehicle risk groups indicative of differing levels of potential risk for future incidents and for causing potential faulty parts at different upcoming time periods. As a result, the sensor data collected from the plurality of delivery vehicles 116 enables the system 100 to identify correlations between rotational and orientation data, location, terrain, acceleration patterns, and stoppage time of each delivery vehicle from the vehicle dataset acquired from the telematics component of each vehicle, to generate predictive maintenance alerts and further transmit the generated predictive maintenance alerts to the riders and operators for efficient, accurate and reliable fault detection and vehicle maintenance.
FIG. 3A is a scenario-based diagram that depicts an exemplary scenario illustrating predictive maintenance and fault detection in a fleet of delivery vehicles, in accordance with an embodiment of the present disclosure. FIG. 3A is described in conjunction with elements from FIGs. 1, and 2. With reference to FIG. 3A, there is shown an exemplary illustration 300A that depicts predictive maintenance and fault detection in a fleet of delivery vehicles.
There is shown the plurality of delivery vehicles 116 that are assigned to the plurality of riders 118. In an example, the first delivery vehicle 116A is assigned to the first rider 118A that is shown by a first rectangular dotted box 304A. In another example, the second delivery vehicle 116B is assigned to the second rider 118B, which is shown by a second rectangular dotted box 304B. In yet an example, the Nth delivery vehicle 116N is assigned to the nth rider 118N, which is shown by a nth rectangular dotted box 304N. The hardware processor 104 of the fault detection server 102 (i.e., the fault detection server 102 of FIG. 1) is configured to obtain the historical dataset 108A of each delivery vehicle of the plurality of delivery vehicles 116 from the first database 106A and the behavioural dataset 108B of each rider of the plurality of riders 118 from the second database 106B along with the vehicle dataset 108C from the telematics component 110 installed in each delivery vehicle of the plurality of delivery vehicles 116 assigned to the plurality of riders 118. In an example, the historical dataset 108A for each delivery vehicle from the plurality of delivery vehicles 116 may include but is not limited to a unique vehicle identifier of each delivery vehicle, a manufacturing year of each delivery vehicle, a vehicle mileage, a last service date, and a last repaired part or replaced part of each delivery vehicle, a unique vehicle identifier of each rider assigned to each delivery vehicle. Similarly, the vehicle dataset 108C includes the sensor data (i.e., the data captured by a gyro sensor, a location sensor, and an accelerometer) acquired by each of the telematics components installed in each of the plurality of delivery vehicles 116. Moreover, the acquired sensor data is transmitted to the fault detection server 102 for remote analysis and monitoring. The behavioural dataset 108B includes vehicle handling information associated with each rider, a set of active time periods in a day for each rider, and a set of dormant time periods in the day of each rider from the plurality of riders 118. After that, the hardware processor 104 is configured to classify the plurality of delivery vehicles 116 into the plurality of vehicle risk groups 302 based on the obtained historical dataset 108A and the obtained vehicle dataset 108C from each telematics component of the plurality of delivery vehicles 116.
Each of the vehicle risk groups from the plurality of vehicle risk group 302 indicates the risk associated with a first vehicle risk group 302A and a second vehicle risk group 302B. However, the risk associated with the first vehicle risk group 302A can be greater than the risk associated with the second vehicle risk group 302B without affecting the scope of the present disclosure based on the historical dataset 108A and the vehicle dataset 108C. For example, the plurality of vehicle risk group 302 includes the first vehicle risk group 302A with a worst situation, which indicates that such delivery vehicles require more frequent maintenance (i.e., repair or replacement of parts, such as brake pads, steering components, throttle wire, or services) and the second vehicle risk group 302B, which indicates that the delivery vehicle requires less maintenance.
Furthermore, the hardware processor 104 is configured to dynamically detect and designate one or more potential faulty parts in the plurality of delivery vehicles 116 that are to be proactively replaced or repaired in one or more upcoming time periods, based on the obtained historical dataset 108A, the obtained vehicle dataset 108C, and the classification of the plurality of delivery vehicles plurality into the plurality of vehicle risk groups 302. For example, a first faulty part 306A and a second faulty part 306B of the first delivery vehicle 116A that is assigned to the first rider 118A, as shown in the first rectangular dotted box 304A is detected and designated as faulty parts by the hardware processor 104 of the system 100 that are required to be replaced or repaired to ensure delivery vehicle’s maintenance. Moreover, the hardware processor 104 is further configured to dynamically determine penalties that can be imposed on the rider based on the obtained behavioural dataset 108B and the classification of the plurality of delivery vehicles 116 into the plurality of vehicle risk groups 302 to ensure judicious usage of the assigned delivery vehicle.
FIG. 3B is a scenario-based diagram that depicts an exemplary scenario that depicts an exemplary predictive maintenance alert generated by a system illustrating predictive maintenance and fault detection, in accordance with an embodiment of the present disclosure. FIG. 3A is described in conjunction with elements from FIGs. 1, 2, and 3A. With reference to FIG. 3B, there is shown an exemplary illustration 300B that depicts an interface module 308 for displaying and accessing the generated predictive maintenance alerts, such as a predictive maintenance alert 310.
The interface module 308 refers to a visual interface that is used to display any ongoing event related to each of the plurality of delivery vehicles 116 assigned to each of the plurality of riders 118. The interface module 308 is connected to the predictive maintenance module 112 of the system 100 that is configured to identify correlations between rotational and orientation data, location, terrain, acceleration patterns, and stoppage time of each delivery vehicle from the vehicle dataset acquired from the telematics component of each vehicle, to generate predictive maintenance alerts. Furthermore, the hardware processor 104 of the system 100 is configured to refine the predictive maintenance alerts by adapting to the evolving rider behaviour and usage patterns of each rider. In addition, the interface module 308 is configured to access real-time rotational and orientation data of each of the plurality of delivery vehicles 116. In an example, the interface module 308 is configured to access real-time rotational and orientation data of the first delivery vehicle 116A. In another example, the interface module 308 is configured to access real-time rotational and orientation data of the second delivery vehicle 116B. In yet another example, the interface module 308 is configured to access real-time rotational and orientation data of the nth delivery vehicle 116N. As a result, the predictive maintenance alerts (e.g., the predictive maintenance alert 310) enables fleet managers to make timely maintenance decisions and optimize delivery vehicle performance.
FIG. 4 is a flowchart of a method for predictive maintenance and fault detection in a fleet of delivery vehicles, in accordance with an embodiment of the present disclosure. FIG. 4 is described in conjunction with elements from FIGs. 1, 2, 3A, and 3B. With reference to FIG. 4, there is shown a method 400 for predictive maintenance and fault detection in a fleet of delivery vehicles. The method 400 includes steps 402 to 408. The method 400 is executed by the hardware processor 104 of the system 100 (of FIG.1).
There is provided the method 400 for predictive maintenance and fault detection in a fleet of delivery vehicles. The fleet of delivery vehicles refers to the plurality of delivery vehicles 116 that are specifically designated or employed for the purpose of transporting goods or providing delivery services within a delivery network. The plurality of delivery vehicles 116 plays a crucial role in facilitating the movement of items from one location to another, ensuring timely and efficient deliveries. In some implementations, the plurality of delivery vehicles 116 includes various types of transportation means, such as trucks, vans, cars, motorcycles, bicycles, or any other suitable mode of transport. The plurality of delivery vehicles 116 includes the first delivery vehicle 116A, the second delivery vehicle 116B, and up to the Nth delivery vehicle 116N and each of the plurality of delivery vehicle 116 includes the telematic component 110. For example, the first delivery vehicle 116A includes the first telematics component 110A, and the second delivery vehicle 116B includes the second telematics component 110B. Similarly, the nth delivery vehicle 116N includes the nth telematic component 110N. As a result, the method 400 is used to provide a comprehensive and intelligent analysis of different datasets that can be further used to provide accurate and reliable predictive vehicle maintenance and fault detection that can be further used to optimize vehicle performance, minimize downtime due to faults, enhance rider accountability, and ultimately ensures efficient and reliable fleet operations.
At step 402, the method 400 includes obtaining the historical dataset 108A of each delivery vehicle of the plurality of delivery vehicles 116 from the first database 106A, and the behavioural dataset 108B of each rider of the plurality of riders 118 from the second database 106B. In an example, the hardware processor 104 is configured to obtain the historical dataset 108A of the first delivery vehicle 116A from the first database 106A. In another example, the hardware processor 104 is configured to obtain the historical dataset 108A of the second delivery vehicle 116B from the first database 106A. In yet another example, the hardware processor 104 is configured to obtain the historical dataset 108A of the nth delivery vehicle 116N from the first database 106A. Similarly, the hardware processor 104 is configured to obtain the behavioural dataset 108B of the first rider 118A of the plurality of rider 118 and the behavioural dataset 108B of the second rider 118B of the plurality of rider 118 from the second database 106B. As a result, the hardware processor 104 is configured to obtain the historical dataset 108A and the behavioural dataset 108B, which can be further used for analyzing the datasets (i.e., the historical dataset 108A, and the behavioural dataset 108B) in order to obtain accurate and reliable decision-making and fleet management with precise fault detection, and enhanced rider performance accountability.
At step 404, the method 400 includes obtaining the vehicle dataset 108C from the telematics component 110 installed in each delivery vehicle of the plurality of delivery vehicles 116 assigned to the plurality of riders 118. By collecting the vehicle dataset 108C from each of the telematics components 110 installed in each of the plurality of delivery vehicles 116 enables the hardware processor 104 of the system 100 to identify various vehicle-related insights that can be further used for analysis and maintenance predictions.
At step 406, the method 400 includes classifying the plurality of delivery vehicles 116 into a plurality of vehicle risk groups based on the obtained historical dataset 108A and the obtained vehicle dataset 108C from each telematics component of the plurality of delivery vehicles 116. For example, the plurality of delivery vehicles 116 are classified as a “first vehicle risk group”, a “second vehicle risk group”, and a “third vehicle risk group”. Moreover, each of the vehicle risk groups from the plurality of the vehicle risk groups depicts a different risk level associated with the corresponding vehicle risk groups, for example, the “first vehicle risk group” includes the delivery vehicles with more age and the delivery that are in the worst situation. Similarly, the “second vehicle risk group” includes the delivery vehicles in better condition, and the “third vehicle risk group” includes the delivery vehicles that are new and are in a good situation. As a result, the method 400 is used to predict and manage potential issues accurately and reliably, contributing to the effective fleet maintenance, targeted intervention, and optimized operational strategies.
At step 408, the method 400 includes dynamically detecting and designating one or more at potential faulty parts in the plurality of delivery vehicles that are to be proactively replaced or repaired in one or more upcoming time periods, based on the obtained historical vehicle dataset, the obtained vehicle dataset, and the classification of the plurality of delivery vehicles plurality into the plurality of vehicle risk groups. As a result, the identification of the one or more faulty parts in the plurality of delivery vehicles 116 enables the system 100 to proactively address emerging problems before their impact operations to ensure that the maintenance efforts are aligned with actual needs, leading to streamlined operational efficiency.
Advantageously, the system 100 of the present disclosure provides an efficient, reliable, and accurate predictive maintenance and fault detection in the fleet of the delivery vehicles. For example, the hardware processor 104 integrates the historical dataset 108A, the behavioural dataset 108B, and the vehicle dataset 108C to predict the maintenance that is required in each the delivery vehicle and also to detect faults in the fleet of the delivery vehicle. This integration allows for a holistic view of each of the plurality of delivery vehicles 116 while considering past performance, behavioural characteristics, and vehicle handling skills of the riders. Therefore, by combining these datasets (i.e., the historical dataset 108A, the behavioural dataset 108B, and the vehicle dataset 108C), the system 100 is configured to anticipate potential faults accurately and maintenance that is required to be done even before the escalation of these potential faults into critical issues along with the identification of the rider’s accountability. For example, the system 100 is able to differentiate between a rider who rides his assigned delivery vehicle responsibly and carefully and another rider who rides rashly and carelessly. In both cases, the system 100 is configured to penalize both riders in a different manner (e.g., by imposing fines or penalties or rash use, and the like) that increases the rider’s accountability towards the assigned delivery vehicle.
Furthermore, the method 400 is used to ensure judicious penalty imposition analyses to prevent any false penalty imposition, for example, if any rider shifts from aggressive driving to a more cautious style, the method 400 is used for accounting for this change and adjusts the maintenance predictions of the corresponding delivery vehicle along with the penalty that can be imposed on the rider according to such change. Moreover, the dynamic classification of the plurality of delivery vehicles 116 into the plurality of risk groups and designation of the one or more potential faulty parts prevents unexpected breakdowns, minimizes vehicle downtime, and ensures that the maintenance efforts are strategic and aligned with actual requirements. Additionally, the method 400 is also used for providing personalized maintenance strategies to the classified plurality of vehicle risk groups based on different risk groups, technicalities, historical dataset, and the vehicle dataset for each of the plurality of delivery vehicles 116. Consequently, the delivery vehicles that are prone to higher risks receive more attention, while those with lower risks are subjected to fewer interventions, saving time and resources. Hence, the method 400 is used to manage delivery vehicles effectively by anticipating potential issues or faults proactively without causing any actual (or real-time) damage to the vehicle as well as the rider with enhanced overall operational efficiency.
Modifications to embodiments of the present disclosure described in the foregoing are possible without departing from the scope of the present disclosure as defined by the accompanying claims. Expressions such as "including", "comprising", "incorporating", "have", "is" used to describe, and claim the present disclosure are intended to be construed in a non-exclusive manner, namely allowing for items, components or elements not explicitly described also to be present. Reference to the singular is also to be construed to relate to the plural. The word "exemplary" is used herein to mean "serving as an example, instance or illustration". Any embodiment described as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments or to exclude the incorporation of features from other embodiments. The word "optionally" is used herein to mean "is provided in some embodiments and not provided in other embodiments". It is appreciated that certain features of the present disclosure, which are, for clarity, described in the context of separate embodiments, may also be provided in combination in a single embodiment. Conversely, various features of the invention, which are, for brevity, described in the context of a single embodiment, may also be provided separately or in any suitable combination or as suitable in any other described embodiment of the disclosure.
, Claims:CLAIMS
We Claim:
1. A system (100) for predictive maintenance and fault detection in a fleet of delivery vehicles, the system comprising:
a fault detection server (102) comprising a hardware processor (104), wherein the hardware processor (104) is configured to:
obtain a historical dataset (108A) of each delivery vehicle of a plurality of delivery vehicles from a first database (106A), and a behavioural dataset (108B) of each rider of the plurality of riders (118) from a second database (106B);
obtain a vehicle dataset (108C) from a telematics component (110) installed in each delivery vehicle of the plurality of delivery vehicles (116) assigned to a plurality of riders (118);
classify the plurality of delivery vehicles (116) into a plurality of vehicle risk groups based on the obtained historical dataset (108A) and the obtained vehicle dataset (108C) from each telematics component of the plurality of delivery vehicles (116); and
dynamically detecting and designating one or more potential faulty parts in the plurality of delivery vehicles (116) that are to be proactively replaced or repaired in one or more upcoming time periods, based on the obtained historical dataset (108A), the obtained vehicle dataset (108C), and the classification of the plurality of delivery vehicles (116) into the plurality of vehicle risk groups (302).
2. The system (100) as claimed in claim 1, wherein the hardware processor (104) is configured to determine a penalty to be imposed on one or more riders of the plurality of riders (118), based on the obtained historical vehicle dataset (108A), the obtained vehicle dataset (108C), the obtained behavioural dataset (108B), the classification of the plurality of delivery vehicles (116) plurality into the plurality of vehicle risk groups (302), and dynamically detected one or more potential faulty parts in the plurality of delivery vehicles (116).
3. The system (100) as claimed in claim 1, wherein in order to obtain the vehicle dataset (108C) from the telematics component (110), the telematics component (110) is configured to:
acquire sensor data (210) from a plurality of sensors placed in each delivery vehicle of the plurality of delivery vehicles (116); and
transmit the acquired sensor data (210) to the fault detection server (102) for remote analysis and monitoring.
4. The system (100) as claimed in claim 3, wherein the plurality of sensors comprises two or more of: a gyro sensor, a location sensor, and an accelerometer.
5. The system (100) as claimed in claim 1, wherein the historical dataset (108A) comprises a unique vehicle identifier of each delivery vehicle, a manufacturing year of each delivery vehicle, a vehicle mileage, a last service date, and a last repaired part or replaced part of each delivery vehicle, a unique vehicle identifier of each rider assigned to each delivery vehicle.
6. The system (100) as claimed in claim 1, wherein the behavioural dataset (108B) comprises vehicle handling information associated with each rider, a set of active time periods in a day for each rider, and a set of dormant time periods in the day of each rider from the plurality of riders (118).
7. The system (100) as claimed in claim 1, wherein the system (100) comprises a predictive maintenance module (120) configured to identify correlations between rotational and orientation data, location, terrain, acceleration patterns, and stoppage time of each delivery vehicle from the vehicle dataset (108C) acquired from the telematics component of each vehicle, to generate predictive maintenance alerts.
8. The system (100) as claimed in claim 1, wherein the hardware processor (104) is configured to refine the predictive maintenance alerts by adapting to evolving rider behaviour and usage patterns of each rider.
9. The system (100) as claimed in claim 1, wherein the hardware processor (104) is configured to analyse the historical dataset (108A) and the vehicle dataset (108C) to identify relevant risk factors comprising a frequency of incidents, a severity of accidents, terrain conditions from GPS data, abrupt acceleration, and deceleration patterns from accelerometer data, and tilting events from gyro sensor data for the classification of the plurality of delivery vehicles (116) into the plurality of vehicle risk groups (302) indicative of differing levels of potential risk for future incidents and for causing potential faulty parts at different upcoming time periods.
10. A method (400) for predictive maintenance and fault detection in a fleet of delivery vehicles, wherein the method (400) comprising:
obtaining a historical dataset (108A) of each delivery vehicle of a plurality of delivery vehicles (116) from a first database (106A), and a behavioural dataset (108B) of each rider of the plurality of riders (118) from a second database (106B);
obtaining a vehicle dataset (108C) from a telematics component (110) installed in each delivery vehicle of the plurality of delivery vehicles (116) assigned to a plurality of riders (118);
classify the plurality of delivery vehicles (116) into a plurality of vehicle risk groups based on the obtained historical dataset (108A) and the obtained vehicle dataset (108C) from each telematics component of the plurality of delivery vehicles (116); and
dynamically detecting and designating one or more at potential faulty parts in the plurality of delivery vehicles (116) that are to be proactively replaced or repaired in one or more upcoming time periods, based on the obtained historical dataset (108A), the obtained vehicle dataset (108C), and the classification of the plurality of delivery vehicles (116) into the plurality of vehicle risk groups.