FIELD OF THE INVENTION
The present invention is related to the sensor systems and the computer science-based
machine learning and artificial intelligence algorithms to track and assess the rail
transportation system.
BACKGROUND OF THE INVENTION
The present invention is based on the various input sensors and the machines like Rail track
sensors and input devices, Geo tracking system to monitor, Radar system to coordinate with
the driver, Radar system to the coordinator with lineman, Satellite connectivity and relative
items for signal transfer. The main area of the work is to ease the key metrics for maintenance
managers involving uptime, Property longevity, cost control, and safety across a diverse set
of Properties and technologies. This novel rail Property management system needs to
integrate with other systems including condition monitoring and corporate finance. Rail
Property management integrates hardware, software, and consulting parameters within
Property management. The improved economy has unleashed a backlog of projects for new
rail Property management systems. This guide will support the growing demand for help with
supplier selection. The present invention works on artificial intelligence and machine learning
algorithm to track and recall things.
SUMMARY OF THE INVENTION
The invention is about railway assessment management which covers key aspects of rail
Property management systems including Property performance management like operations
and maintenance, condition and reliability monitoring, and Property management business
processes. It also includes general product functions, Property types, deployment strategies,
work order management, materials management, labour management, service contract
management, financial management, reporting and analytics, and technology architecture.
The guide has attributes tailored for rail operators and transit agencies and allows those
involved in a rail Property management selection process to make improved decisions more
quickly.

BRIEF DESCRIPTION OF THE INVENTION
This includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art. Property management means a complete system which is a group of coordinated activities related to railways that optimize and Property the railway system performance. It comprises all the railway systems, procedures and tools to maximise Property availability for a minimum whole-life cost and risk. This often involves using intelligent software to collect and analyse data about users so that predictive and preventative maintenance can take place rather than reactive repairs. Based on the surveya railroad track inspection system has a common support structure to which is attached a plurality of track scanning sensors, a data store for storing track scan data recorded by the track scanning sensors, and a scan data processor for automatic analysis of said track scan data upon receipt thereof to detect one or more track components within the scan data.
The issue is not the tracking, but also the remedial plan. The system for railway track geometry defect modelling was discussed. In the system, the rail track geometry defect is predicted based on the deterioration. This helps in preventing derailment and helps in optimal repair. A system is discussed which is computer software code for operating a railroad train to minimize wheel and track wear. The mentioned system controls a railroad train over a segment of track. The system comprised the location tracking of the train on the segment of the track; the track characterization information related to physical conditions of the segment of the track; and a processor for controlling applied attractive forces and braking forces of the train responsive to the location of the train and the track characterization information to reduce at least one of wheel wear and/or track wear during operation of the train over the segment of track. a method of giving warnings and alerts according to the railway environment and the information acquisition, and assessment. The has the defined processes for the ambient parameter information collected and video image information and analysis and sends Environmental security appreciation information and early warning information by the communication module.
A method is discussed which don’t need human intervention in the analysis of the railway tracks. The system is the unmanned aerial vehicle system checking railway Properties. This was the aviation-based system to track the systems. This discussed the railroad track inspection system. The system has multiple track scanning sensors, a data store, and a scan data processor. Each part has its independent task like the scan data processor provides automatic analysis of the track scan data to detect track components within the scan data from a predetermined list of component types according to features identified in said scan data; the track scanning sensors, data store and scan data processor are attached to a common support structure for mounting the system to a railway vehicle in use. The key metrics for maintenance of the rail systems are to involve uptime, Property longevity, cost control, and safety across a diverse set of Properties and technologies. To meet these critical objectives, executive management recognizes the requirement for a modern and reliable rail Property management system. In addition, the rail Property management system needs to integrate with other systems including condition monitoring and corporate finance. Rail Property management integrates hardware, software, and consulting parameters within Property management. The improved economy has unleashed a backlog of projects for new rail Property management systems. This guide will support the growing demand for help with supplier selection. Rail Property management system selection is mission-critical, particularly in the Property-intensive rail industry. The total solution has become complex and functionality involves the combination of an expanded range of capabilities and specific technology requirements. While product plays a major role, suppliers have specific domain expertise, geographical presence, and knowledge of certain industry dynamics. These must all be evaluated in a supplier selection process. In some embodiments, the numbers expressing quantities of ingredients, properties such as concentration, reaction conditions, and so forth, used to describe and claim certain embodiments of the invention are to be understood as being modified in some instances by the term “about.”Accordingly, in some embodiments, the numerical parameters outlined in the written description and attached claims are approximations that can vary depending upon the desired properties sought to be obtained by a particular embodiment.
In some embodiments, the numerical parameters should be construed in light of the number of reported significant digits and by applying ordinary rounding techniques. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of some embodiments of the invention are approximations, the numerical values outlined in the specific examples are reported as precisely as practicable. The numerical values presented in some embodiments of the invention may contain certain errors necessarily resulting from the standard deviation found in their respective testing measurements. As used in the description herein and throughout the claims that follow, the meaning of “a,” “an,” and “the” includes plural reference unless the context dictates otherwise. Also, as used in the description herein, the meaning of “in” includes “in” and “on” unless the context dictates otherwise. The recitation of ranges of values herein is merely intended to serve as a shorthand method of referring individually to each separate value falling within the range. Unless otherwise indicated herein, each value is incorporated into the specification as if it were individually recited herein. All methods described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The use of any examples, or exemplary language (e.g. “such as”) provided concerning certain embodiments herein is intended merely to better illuminate the invention and does not pose a limitation on the scope of the invention otherwise claimed. No language in the specification should be construed as indicating any non-claimed element essential to the practice of the invention. Groupings of alternative elements or embodiments of the invention disclosed herein are not to be construed as limitations. Each group member can be referred to and claimed individually or in any combination with other members of the group or other elements found herein. One or more members of a group can be included in, or deleted from, a group for reasons of convenience and/or patentability.
Figure 1 represents the complete workflow and the modules available in the present invention. The detailed description of the figure abstract of the present invention is discussed in detail in the section. System has various modules and connected components. The system has the proper internet connectivity to coordinate among all modules and components of the present invention. As mentioned in the system and claim, satellite and GPS tracking of the railway system are required for all information and data fetching. The designing component of the system has the railway tracks among the moving trains and the service trolley. System not only manages things; but also provides the necessary solutions and suggestions. The artificial intelligence and machine learning algorithm work well as the computing system, where the inputs and outputs are reflected. Monitoring information and spatial coordinated information, to monitor the environmental information of device present position and the extraction of spatial coordinated information, and Video image information acquisition module, is monitored to the Infrared Image Information of the environment residing for the device, and is stored in the storage module by monitoring information. Memory module, to store aforesaid environmental parameter information and video image information, and can pass through communication module transmitting video image information and ambient parameter information under the control of control module; are recorded in storage module by ambient parameter information acquisition module. Assessment warning module 108, is to the aforementioned ambient parameter information that collects with video image information is assessed and early warning, namely the Environmental security grade of the current line is judged according to assessment result, corresponding railway line environmental emergency Action Message is obtained according to line security grade, and under the control of control module, Environmental security level evaluation information and railway line environmental emergency Action Message can be sent by communication module, thus the Environmental security assessment realized railway line and prewarming process. The communication module, is as the correspondence with the foreign country module of the device, wireless transmission is passed through outwardly with wireless signal under the control of control module, or by an interface of the mobile base station with the transmission of the form of note and broadcast image information, coded message, short message, implement device communicates with station upper computer terminal, train driving room terminal and passenger's mobile phone terminal. An inertia sensor and common master clock, are used to make corrections to the output of the track scanning sensors to accommodate dynamic forces in use.
The inspection system may be provided in a single housing for mounting to a conventional passenger and may operate automatically in an unattended mode. The location of track components and/or defects may be logged. In an aspect, any or a combination of machine learning mechanisms such as decision tree learning, Bayesian network, deep learning, random forest, supervised vector machines, reinforcement learning, prediction models, Statistical Algorithms, Classification, Logistic Regression, Support Vector Machines, Linear Discriminant Analysis, K- Nearest Neighbours, Decision Trees, Random Forests, Regression, Linear Regression, Support Vector Regression, Logistic Regression, Ridge Regression, Partial Least-Squares Regression, Non-Linear Regression, Clustering, Hierarchical Clustering – Agglomerative, Hierarchical Clustering– Divisive, K-Means Clustering, K-Nearest Neighbours Clustering, EM (Expectation-Maximization) Clustering, Principal Components Analysis Clustering (PCA), Dimensionality Reduction, Non-Negative Matrix Factorization (NMF), Kernel PCA, Linear Discriminant Analysis (LDA), Generalized Discriminant Analysis (kernel trick again), Ensemble Algorithms, Deep Learning, Reinforcement Learning, AutoML (Bonus) and the like can be employed to learn sensor/hardware components. The term “non-transitory storage device” or “storage” or “memory,” as used herein relates to random access memory, read-only memory and variants thereof, in which a computer can store data or software for any duration.
It should be apparent to those skilled in the art that many more modifications besides those already described are possible without departing from the inventive concepts herein. The inventive subject matter, therefore, is not to be restricted except in the spirit of the appended claims. Moreover, in interpreting both the specification and the claims, all terms should be interpreted in the broadest possible manner consistent with the context. In particular, the terms “comprises” and “comprising” should be interpreted as referring to elements, components, or steps in a non-exclusive manner, indicating that the referenced elements, components, or steps may be present, utilized, or combined with other elements, components, or steps that are not expressly referenced. Where the specification claims refer to at least one of something selected from the group consisting of A, B, C …. and N, the text should be interpreted as requiring only one element from the group, not A plus N, or B plus N, etc.
The railway industry spent almost 40% of revenue on maintaining, renewing and expanding infrastructure over past decades. Advanced railway maintenance is crucial to improve safety and reduce operational costs. Recently, condition monitoring of railway infrastructure has become more and more important, leading railway companies to take advantage of artificial intelligence (AI) based technologies. Fleet reliability is a key lever for increasing efficiency and reducing total cost for smart railway operation. Predictive maintenance represents a great opportunity to yield the next big efficiency leap in maintenance reducing the number of failures, the amount of unplanned maintenance and, eventually, the required level of reserve asset capacity for rail operators. Wheel failures and broken rails are two main factors that cause train derailments in today’s railway operations. Wheel failures, which account for half of all train derailments, cost billions of dollars to the North America rail industry; and another main cause of derailments is broken rails due to rail defects. To minimize rail breaks and help avoid catastrophic events such as derailments, railways are now closely monitoring the performance of wheels and trying to remove them before they start imparting high impact forces to the rails. Many techniques for detecting wheel flats and out of round issues have been developed and installed at strategic locations on the rail network. These detectors measure the vertical force or impact of each passing wheel. One of them is called Wheel Impact Load Detectors (WILD). A central system receives the data in real-time and advises the staff when the impact of a given wheel is too high.
In the North American railway network, a set of threshold values has been developed and implemented to flag the bad actor wheels since 2004. Building on WILD techniques, we have developed the WILD Predictor to predict wheel failures before they reach these threshold values. The WILD predictor can predict wheel flats, out of round wheels, and estimate the time for wheels to reach the impact force thresholds using the machine learning-based predictive models. There are many available techniques developed by the railway industry and community to detect rail surface defects. One cost-effective method of detecting rail surface defects such as shelling, squats, split heads, engine burns, etc. is to use accelerometers mounted to the bogie side frames or wheel axles. The collected acceleration data from the sensors were processed with a pre-determined threshold value to judge the rail surface defects. The technique is simple, useful, and applicable for detecting rail joints or broken rails. However, much more work remains to be done in order to distinguish the joint (or broken rail) from various track surface defects since these surface defects generate high amplitude vertical accelerations in the axles and side frames as well. Due to such limitations, the existing threshold-based algorithms usually require additional visual inspection of these areas of track, which greatly increase the cost and complexity of the techniques. Therefore, more intelligent algorithms are needed so that the accelerometers can automatically distinguish the rail defects from rail joint (or broken rail) and other special track features with discontinuities. As the first step to distinguish rail surface defects from other track features, the present work is focused on the detection of rail joints on both sides of the track. To this end, we first developed machine learning methods to build the models to detect the rail joints using the accelerating data collected from an inspection vehicle [16]. The developed models can detect the rail joints with high accuracy. However, this method has two weaknesses: the model requires the feature data from raw data and each side of the track needs a separate model for detection. This creates difficulties to deploy or apply the models in railway operations. To address these limitations, we propose to develop deep learning-based models by applying convolutional neural networks (CNN).

We Claims:

1. This helps in preventing derailment and helps in optimal repair. A system is discussed which is computer software code for operating a railroad train to minimize wheel and track wear.
2. The total solution has become complex and functionality involves the combination of an expanded range of capabilities and specific technology requirements.
3. While product plays a major role, suppliers have specific domain expertise, geographical presence, and knowledge of certain industry dynamics.
4. These must all be evaluated in a supplier selection process.
5. System has various modules and connected components. The system has the proper internet connectivity to coordinate among all modules and components of the present invention.
6. To minimize rail breaks and help avoid catastrophic events such as derailments, railways are now closely monitoring the performance of wheels and trying to remove them before they start imparting high impact forces to the rails.
7. This often involves using intelligent software to collect and analyse data about users so that predictive and preventative maintenance can take place rather than reactive repairs.