Description:FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENTS RULES, 2003
COMPLETE SPECIFICATION
(SEE SECTION 10, RULE 13)

A SYSTEM AND METHOD FOR FUEL THEFT IDENTIFICATION
BY
TOR.AI LIMITED
303-303A, 403-403A, B Junction, Survey No. 1/2, Next to Kothrud Post office, near Karve Statue, Kothrud, Pune, Maharashtra 411038, India
[An Indian Company]
The following specification particularly describes the invention and the manner in which it is to be performed.

BACKGROUND
A. Technical Field:
[001] The present disclosure relates to a system and method for fuel theft identification from a construction equipment, and more particularly, the present invention relates to the system and method for fuel theft identification from remote sensing fuel data of the construction equipment.
B. Background Art:
[002] In construction equipment and/or heavy vehicles, theft of fuel is a major problem that costs the transport industry vast amounts of money. Various methods are employed for fuel theft which includes siphoning of the fuel from the vehicle's fuel tank. The theft of the fuel from the fuel tank is easy and quick operation, which is generally carried out when the construction equipment/ vehicle is stationary and the engine is stopped, for example, at night, when the vehicle is parked.
[003] There are several systems and methods presently available that tries to overcome problem of the fuel theft. One of the methods includes measuring the actual amount of fuel that has been combusted by the vehicle's engine against the fuel in the tank. However, this can be manipulated if the flow of fuel is intercepted and redirected between the device and the injector pump.
[004] Another method of preventing fuel theft involve fitting an electronic vehicle identification unit around the neck of the fuel tank. The nozzle of the fuel pump is in turn also fitted with an electronic device, with the two devices being programmed so that the fuel pump will only dispense fuel if the vehicle identification unit on the vehicle's fuel tank is actively identified. The resulting transaction is then recorded, and is thus relatively foolproof. However, this method has a limitation that fuel can still be siphoned from the fuel tank. In addition, this method only works at filling stations where such technology exists.
[005] Hence, there is a need to provide a system and method for identification of fuel theft from the construction equipment which overcomes abovementioned drawbacks.
[006] For the reasons stated above, which will become apparent to those skilled in the art upon reading and understanding the specification, there is a need in the art for a system and method for fuel theft identification from remote sensing fuel data of the construction equipment that is useable, scalable and independent of new technology platforms, uses minimum resources that is easy and cost effectively maintained and can be deployed anywhere in very little time.
[007] Proposed invention overcomes these lacunae by proposing a unique system and methodology implemented thereof for fuel theft identification from remote sensing fuel data of the construction equipment as detailed hereinafter.
SUMMARY
[008] In an implementation a method for detecting a fuel theft is disclosed. The method comprises receiving 101 raw data associated with fuel in a fuel tank of the construction equipment. The raw data is received at a receiving module from an IoT sensor mounted within the fuel tank, or is communicably connected to a fuel sensor. Further analysing 102 the raw data to detect if the raw data is clean or has error, or any missing data. Removing 103 the missing data from the raw data by the processor, wherein the removing of the missing data enables obtaining a clean data. Further removing 104, noisy data from the clean data using SDM to obtain a smoothen fuel level time series data. A noise removing module communicatively coupled to the receiver module and the processor is configured to employ the SDM to obtain the smoothen fuel level time series data.
[009] The method further comprises receiving 105, the smoothen fuel level time series data from the noise removing module, or the IoT sensor. Checking 106, fuel data pattern by extracting relevant data from the smoothen fuel level time series data. Further generating 107, fuel drop time series data from the relevant data extracted from the smoothen fuel level time series data. The method as disclosed comprises generating 108, fuel merge series data, by merging fuel drop time series data. Further obtaining 109, fuel drop in Liters from the fuel merge series data.
BRIEF DESCRIPTION OF THE DRAWINGS
[0010] The detailed description is described with reference to the accompanying figures. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the drawings to reference like features and modules.
[0011] Figure 1 is a flowchart of a method for identification of fuel theft in accordance with the present invention;
[0012] Figure 2 is a flowchart of noise removal method from the fuel level data, in accordance with the present invention;
[0013] Figure 3 and 4 are graphs showing the difference between raw fuel data and the smoothened fuel data for a Use Case 1;
[0014] Figure 5 and 6 are graphs showing the difference between raw fuel data and the smoothened fuel data for a Use Case 2;
[0015] Figure 7 and 8 are graphs showing difference between raw fuel data and the smoothened fuel data indicating fake theft alert;
[0016] Figure 9, shows a flow chart illustrating generating a fuel drop time series data in accordance with the present invention;
[0017] Figure 10, shows a flow chart illustrating generating a fuel merge drop series data in accordance with the present invention; and
[0018] Figure 11, shows a flow chart illustrating generating fuel consumption data in accordance with the present invention.
[0019] It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present invention. Similarly, it will be appreciated that any flowcharts, flow diagrams, and the like represent various processes which may be substantially represented in computer readable medium and so executed by a computer or processor, whether or not such computer or processor is explicitly shown.

DETAILED DESCRIPTION OF THE INVENTION
[0020] The embodiments herein provide a method and system for fuel theft identification from remote sensing fuel data of the construction equipment.
[0021] The systems and methods described herein are explained using examples with specific details for better understanding. However, the disclosed embodiments can be worked on by a person skilled in the art without the use of these specific details.
[0022] Throughout this application, with respect to all reasonable derivatives of such terms, and unless otherwise specified (and/or unless the particular context clearly dictates otherwise), each usage of:
“a” or “an” is meant to read as “at least one.”
“the” is meant to be read as “the at least one.”
References in the specification to “one embodiment” or “an embodiment” mean that a particular feature, structure, characteristic, or function described in connection with the embodiment is included in at least one embodiment. The appearances of the phrase “in one embodiment” in various places in the specification are not necessarily all referring to the same embodiment.
[0023] Hereinafter, embodiments will be described in detail. For clarity of the description, known constructions and functions will be omitted.
[0024] Parts of the description may be presented in terms of operations performed by at least one processor, electrical / electronic circuit, a computer system, using terms such as data, state, link, fault, packet, and the like, consistent with the manner commonly employed by those skilled in the art to convey the substance of their work to others skilled in the art. As is well understood by those skilled in the art, these quantities take the form of data stored/transferred in the form of non-transitory, computer-readable electrical, magnetic, or optical signals capable of being stored, transferred, combined, and otherwise manipulated through mechanical and electrical components of the computer system; and the term computer system includes general purpose as well as special purpose data processing machines, switches, and the like, that are standalone, adjunct or embedded. For instance, some embodiments may be implemented by a processing system that executes program instructions so as to cause the processing system to perform operations involved in one or more of the methods described herein. The program instructions may be computer-readable code, such as compiled or non-compiled program logic and/or machine code, stored in a data storage that takes the form of a non-transitory computer-readable medium, such as a magnetic, optical, and/or flash data storage medium. Moreover, such processing system and/or data storage may be implemented using a single computer system or may be distributed across multiple computer systems (e.g., servers) that are communicatively linked through a network to allow the computer systems to operate in a coordinated manner.
[0025] According to an embodiment, the present invention provides a system for fuel theft identification from remote sensing fuel data of the construction equipment.
[0026] In an implementation according to one of the embodiments of the present invention, the system for fuel theft identification from remote sensing fuel data of the construction equipment comprises a processor and IoT Sensor communicatively coupled to the processor. In preferred implementation, the IoT sensor(s) is configured within the fuel tank. The system further comprises a receiver module for receiving time series fuel level data from the construction equipment which is configured to communicate with the processor. The system furthermore comprises noise removing module communicatively coupled to the receiver module and the processor. Also, the processor of the system for fuel theft identification from remote sensing fuel data of the construction equipment is configured to store and maintain records of the fuel level data.
[0027] Specifically, the noise removing module remove the noise of the received fuel level data by smoothening of the fuel level data. In an embodiment, smoothing of the fuel level helps to identify pattern of fuel withing the time interval data using a smoothening data method (SDM) performed by the noise removing module using a processor.
[0028] Specifically, smoothening data method (SDM) excludes fuel level fluctuations from the received fuel data and showcase the fuel level pattern more visible. In an implementation of the present invention, at the first step, the SDM method reads raw fuel level values and place them in order first. The SDM method uses an optimum threshold bucket size. Further, the SDM method at second step, divides ordered data into buckets of the fuel data series. Furthermore, the SDM method comprises adjusting the bucket by "relocating forward"; that is, ignoring the first number of the fuel data series and entering the next value in the bucket. By these method steps the fuel data segregated into buckets. Specifically, for each bucket smoothen value is calculated.
[0029] The advantage of the SDM method is all unwanted outliers are eliminated from the fuel data and clean data is available. This outlier free fuel data is more accurate to identify the drop which compares the difference between two consecutive fuel level values with time difference. Once predetermined filter conditions are satisfied, the drop is generated, and theft is identified. The SDM method helps to identify real trends by eliminating noise from the data.
[0030] The system further includes an analytical module configured to perform comparison of two consecutive fuel levels and the difference between these two values intend towards down trend with predefined threshold values leads towards fuel theft. This immediately identifies the theft and provides alerts to the operator/administrator within time duration.
[0031] In an embodiment, the system for identification of the fuel theft can be used within a time interval to identify fuel theft.
[0032] In an implementation according to one of the embodiments of the present invention, the present invention provides a method for fuel theft identification from remote sensing fuel data of the construction equipment.
[0033] At first step, the method comprises receiving by a processor a time series fuel level data from construction equipment devices. In an embodiment, the time series fuel level data is provided by an IoT sensor configured within the fuel tank.
[0034] At second step, the method comprises removing noise from the received fuel data, by a noise removing module configured within the processor. Specifically, the removal of noise smoothens fuel level data which helps to identify the pattern of fuel withing the time interval data.
[0035] At third step, the method comprises comparing of two consecutive fuel levels, by analytical module configured within the processor. Specifically, the difference between these two values of the fuel level intend towards down trend with predefined threshold values shows the fuel theft.
[0036] The method of present invention immediately identifies the fuel theft and provides alerts withing time duration. Specifically, the method can be used within the time interval to identify fuel theft.
[0037] Part List
- a processor
- IoT Sensor mounted on a construction equipment communicatively coupled to the processor.
- a receiver module for receiving time series fuel level data from the construction equipment which is configured to communicate with the processor.
- a communication means.
- noise removing module communicatively coupled to the receiver module and the processor.
[0038] Figure 1 shows a flowchart of a method for identification of fuel theft in accordance with the present invention.
[0039] Further, the figure 2 shows flowchart of noise removal method from the fuel level data, in accordance with the present invention. In an implementation, the noise removal is carried out using smoothening data method.
[0040] Figure 3 and 4 shows graphs showing the difference between raw fuel data and the smoothened fuel data. The smoothening of the fuel level data helps to identify the pattern of fuel withing the time interval data a user data 1.
[0041] Figure 5 and 6 shows graphs showing the difference between raw fuel data and the smoothened fuel data. The smoothening of the fuel level data helps to identify the pattern of fuel withing the time interval data for a user data 2.
[0042] Figure 7 and 8 shows graphs showing the how the system and method avoids fake fuel theft alert by smoothening of the fuel data. Specifically, actual fuel theft occurs when the fuel level time series meets all the theft identification conditions, otherwise can be considered as fake theft. There are the situations like Barricades during movement or engine operation, sudden jump after the beginning and ending of the motion, major jumps to the minimum or maximum fuel level when fuel level fluctuations occur. These fluctuations influence masses of fuel litres, which can mark in identification of the fuel thefts. In such situations, smoothening data method (SDM) helps to remove and clean these fluctuated data points and helps to smoothen the fuel level values.
[0043] Also, the fuel level can change suddenly at the point of movement start/stop, which may indicate fuel theft. In this situation, the smoothened data method removes such spikes and plain fuel level time series data is obtained. Sometimes fuel level values jump to minimum as 0 fuel level or maximum value and immediately reaches to actual value. These major jumps can detect the fake thefts. Such major jumps can be removed using smoothen data method.
[0044] In accordance with the exemplary embodiment Figure 1 to Figure 2, and Figure 9 to Figure 11, a method for detecting a fuel theft is disclosed. The method as disclosed comprises, at step 101, capturing or receiving raw data associated with fuel in a fuel tank of the construction equipment. The raw data is received at a receiving module from an IoT sensor mounted on or within the fuel tank, or in proximity to fuel tank. In another aspect the IoT sensor, may be communicably connected to a fuel sensor.
[0045] Further the IoT sensor may be configured to send the raw data to the processor via the communication means. The processor may be placed at a remote location. Further the processor may be coupled to a memory module. The memory module may be volatile memory or non-volatile memory.
[0046] At the processor, analysing the raw data at step 102 to detect if the raw data is clean or has error, or any missing data. Further at step 103, removing the missing data from the raw data by the processor. The removing of the missing data enables obtaining a clean data. At step 104, removing noisy data from the clean data using SDM to obtain a smoothen fuel level time series data. Further a noise removing module communicatively coupled to the receiver module and the processor is configured to employ the SDM to obtain the smoothen fuel level time series data.
[0047] Further in accordance with the exemplary embodiment, removing noisy data from the clean data comprises, reading the time series data at step 201. At step 202, arranging the raw data received by ascending data time. Removing the noise in the raw data and find the stability of fuel level parameter by using smoothening data method (SDM) at step 203.
[0048] At step 204, defining a bucket or set. The bucket or the set may be configured to comprise No. of Observations/ Data Points in Raw Data (n) that are deducted from a Threshold Bucket Size with Minimum Data Points (s), and further incremented with 1. In an equation form
Bucket or Set = n – s + 1
[0049] Further 206, dividing the data set from the received raw data, and the smoothed data. At 207, checking the length of the set. In case the bucket size is not odd, at step 208, the smoothen value is obtained via the following equation:
Sk = [ D [s/2]th Value + D [s/2 + 1]th Value ] /2
[0050] Further in case the bucket size is odd, at step 209, the smoothen value is obtained via the following equation:
Sk = D [s/2]th Value
[0051] Further at step 210, computing by the processor the smoothen fuel level time series data after SDM.
[0052] At step 105, receiving the smoothen fuel level time series data from the noise removing module, or the IoT sensor. Further at step 106, checking fuel data pattern by extracting relevant data from the smoothen fuel level time series data.
[0053] In accordance with the exemplary embodiment, at step 107, generating fuel drop time series data from the relevant data extracted from the smoothen fuel level time series data. The generating fuel drop time series data further comprise at step 901, maintaining the fuel drop series, drop start flag, drop sum, and down trend counter. At step 902, reading fuel level from smoothen fuel level series data from ith to nth location. Further in an aspect of the present invention, at step 903, computing the difference of two consecutive fuel level values at ith and (i+1)th location from the smoothen fuel level series.
[0054] Further the method as disclosed comprises detecting fuel difference to be more than Zero (0), at step 904. At step 906, upon detecting fuel difference is more than zero, setting drop start flag as False. Further at step 907, checking the fuel drop start session in case the fuel difference is less than zero. At step 905, checking if Drop Start Flag is set. Further at step 908, setting drop start flag as true. In case the at step 905, if drop start flag is set, then at step 908, rising up Down Trend Counter by one and Drop Sum by Fuel Level Difference.
[0055] At step 910, appending drop tuple in fuel drop series with down trend counter, drop sum and time difference. Further at step 911, reading the next consecutive tuple from the series. At step 912, fuel drop series is generated.
[0056] At step 108, generating fuel merge series data, by merging fuel drop time series data. Generating fuel merge series data, further comprises reading fuel drop series with current and previous tuple 1001. Further the current level is determined to be less than previous fuel level and time difference and less than predefined difference. At step 1002, updating drop record with of current record in case the previous step Yes, or in case of a No, at step 1003, maintaining merge drop series.
[0057] At step 1004, discarding the record in case TimeDifference in Drops >=FuelFillingThresholdTime And TotalDrop >= FuelFillingThresholdDrop is false. In case the condition is true, total fuel drops is observed.
[0058] Further at step 109, obtaining fuel drop in Liters from the fuel merge series data. In accordance with the exemplary embodiment, at step 1101, reading pre-processed fuel series data. Further at step 1102, Start_Median_Fuel_Level as Median of Start Predefined Fuel Level Values, End_Median_Fuel_Level as Median of End Predefined Fuel Level Values, and Drop_Total as Total Drop.
[0059] In some embodiments, the disclosed techniques can be implemented, at least in part, by computer program instructions encoded on a non-transitory computer-readable storage media in a machine-readable format, or on other non-transitory media or articles of manufacture. Such computing systems (and non-transitory computer-readable program instructions) can be configured according to at least some embodiments presented herein, including the processes shown and described in connection with figures.
[0060] The programming instructions can be, for example, computer executable and/or logic implemented instructions. In some examples, a computing device is configured to provide various operations, functions, or actions in response to the programming instructions conveyed to the computing device by one or more of the computer readable medium, the computer recordable medium, and/or the communications medium. The non-transitory computer readable medium can also be distributed among multiple data storage elements, which could be remotely located from each other. The computing device that executes some or all of the stored instructions can be a microfabrication controller, or another computing platform. Alternatively, the computing device that executes some or all of the stored instructions could be remotely located computer system, such as a server.
[0061] Further, while one or more operations have been described as being performed by or otherwise related to certain modules, devices or entities, the operations may be performed by or otherwise related to any module, device or entity.
[0062] Further, the operations need not be performed in the disclosed order, although in some examples, an order may be preferred. Also, not all functions need to be performed to achieve the desired advantages of the disclosed system and method, and therefore not all functions are required.

Claims:We Claim:

1. A method for detecting a fuel theft, the method comprises:
receiving 101 raw data associated with fuel in a fuel tank of the construction equipment, wherein the raw data is received at a receiving module from an IoT sensor mounted within the fuel tank, or is communicably connected to a fuel sensor;
analysing 102 the raw data to detect if the raw data is clean or has error, or any missing data;
removing 103 the missing data from the raw data by the processor, wherein the removing of the missing data enables obtaining a clean data;
removing 104, noisy data from the clean data using SDM to obtain a smoothen fuel level time series data, wherein a noise removing module communicatively coupled to the receiver module and the processor is configured to employ the SDM to obtain the smoothen fuel level time series data;
receiving 105, the smoothen fuel level time series data from the noise removing module, or the IoT sensor;
checking 106, fuel data pattern by extracting relevant data from the smoothen fuel level time series data;
generating 107, fuel drop time series data from the relevant data extracted from the smoothen fuel level time series data.
generating 108, fuel merge series data, by merging fuel drop time series data; and
obtaining 109, fuel drop in Liters from the fuel merge series data.

2. The method as claimed in claim 1, wherein removing noisy data from the clean data comprises, reading the time series data 201.

3. The method as claimed in claim 2, comprises arranging the raw data received by ascending data time.

4. The method as claimed in claim 2, comprises removing the noise in the raw data and find the stability of fuel level parameter by using smoothening data method (SDM) 203.

5. The method as claimed in claim 2, comprises defining 204, a bucket or set.

6. Further 206, dividing the data set from the received raw data, and the smoothed data.

7. The method as claimed in claim 2, comprises checking 207, the length of the set.

8. The method as claimed in claim 2, comprises computing 210, by the processor the smoothen fuel level time series data after SDM.

9. The method as claimed in claim 1, wherein the generating fuel drop time series data further comprise maintaining 901, the fuel drop series, drop start flag, drop sum, and down trend counter.

10. The method as claimed in claim 9, comprises reading 902, fuel level from smoothen fuel level series data from ith to nth location.

11. The method as claimed in claim 9, comprises computing 903, the difference of two consecutive fuel level values at ith and (i+1)th location from the smoothen fuel level series.

12. The method as claimed in claim 9, comprises detecting 904, fuel difference to be more than Zero (0).

13. The method as claimed in claim 9, comprises upon detecting fuel difference is more than zero, setting drop start flag as False 906.

14. The method as claimed in claim 9, comprises checking 907, the fuel drop start session in case the fuel difference is less than zero.

15. The method as claimed in claim 9, comprises rising 908, up Down Trend Counter by one and Drop Sum by Fuel Level Difference.

16. The method as claimed in claim 9, comprises appending 910, drop tuple in fuel drop series with down trend counter, drop sum and time difference.

17. The method as claimed in claim 9, comprises reading 911, the next consecutive tuple from the series.

18. The method as claimed in claim 1, wherein generating fuel merge series data, further comprises reading fuel drop series with current and previous tuple 1001.

19. The method as claimed in claim 18, comprises updating 1002 drop record with of current record in case the previous step Yes, or in case of a No, maintaining 1003, merge drop series.

Dated this on 24 July 2024

Prafulla Wange
Agent for Applicant (IN/PA-2058)