A fault detection system and method based on unmanned vehicle

Abstract

The present invention relates to the field of intelligent transportation technology, and in particular to a system and method for fault detection based on unmanned vehicles, including a vehicle information collection module, a tire data monitoring module, a compensation level analysis module, and an evaluation result feedback module; the tire data monitoring module calculates and analyzes the comprehensive fluctuation trend of the sample vehicle tire according to the first state information to obtain the T3 fluctuation trend value of the sample vehicle tire, and analyzes to obtain a direct abnormal signal; the abnormal detection formula is calculated and analyzed according to the second state information to obtain an indirect abnormal signal, so that the system can monitor in real time and timely discover abnormal behavior and potential faults of vehicle tires, thereby improving the overall performance of the system. The present invention is used to solve the technical problem of being unable to efficiently monitor the tire fault detection effect of unmanned vehicles and conduct targeted evaluation feedback.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a system and method for detecting faults of unmanned vehicles. Background Art

[0002] Autonomous driving refers to a mode in which the vehicle is driven without the need for direct control by a human driver, but instead through automated systems and technologies. It aims to improve the safety, reliability and stability of autonomous vehicles and promote the further development and application of autonomous driving technology.

[0003] With the continuous exploration and development of autonomous driving technology, it has potential application prospects, especially in the field of intelligent transportation technology. However, the fault detection effect of unmanned vehicles is different from the expected normal working state. The current technology cannot monitor the abnormal tire fault of unmanned vehicles with high accuracy, and it is difficult to carry out targeted processing operations to improve the poor effect of unmanned vehicle tire fault detection. To this end, the present invention proposes a fault detection system and method based on unmanned vehicles, which monitors the tire information of sample vehicles through a tire data monitoring module, including tire pressure status, tire temperature status and tire wear status, as well as steering wheel change data and tire reaction data, obtains the T3 fluctuation trend value and abnormal detection formula of the sample vehicle tire, comprehensively analyzes the tire compensation coefficient, and determines the compensation level of the abnormal tire, and obtains the compensation evaluation result to maximize the stability and reliability of system detection. Summary of the invention

[0004] The purpose of the present invention is to solve the problems in the background technology and to propose a fault detection system and method based on an unmanned vehicle.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A fault detection system based on an unmanned vehicle, comprising: a vehicle information collection module, a tire data monitoring module, a compensation level analysis module and an evaluation result feedback module;

[0007] The vehicle information collection module is used to collect information about unmanned vehicles and send the information to the tire data monitoring module; the unmanned vehicle information is collected by connecting the unmanned vehicle to a cloud server or a vehicle management center through an on-board communication module (such as a 4G / 5G module) to achieve remote monitoring and data collection;

[0008] The tire data monitoring module is used to monitor the tire information of the sample vehicle, and the monitoring of the tire information of the sample vehicle includes the first state information and the second state information of the tire of the sample vehicle; the first state information includes the tire pressure condition, the tire temperature condition and the tire wear condition, and the second state information includes the change data of the steering wheel and the reaction data of the tire; the comprehensive fluctuation trend of the tire of the sample vehicle is calculated and analyzed according to the first state information to obtain the T3 fluctuation trend value of the tire of the sample vehicle, and the direct abnormal signal is obtained by analysis; the abnormal detection formula is calculated and analyzed according to the second state information to obtain the indirect abnormal signal;

[0009] The compensation level analysis module is used to comprehensively analyze the tire compensation coefficient according to the calculation result of the abnormal detection formula, and determine the compensation level of the abnormal tire to obtain the primary compensation signal and the secondary compensation signal, thereby obtaining the compensation evaluation result;

[0010] The evaluation result feedback module is used to obtain different abnormal signals and compensation signals and the corresponding sample vehicle numbers, and send them to the background for optimization through the intelligent feedback terminal.

[0011] It should be noted that the application object of a system and method based on an unmanned vehicle fault detection in an embodiment of the present invention can be an unmanned vehicle fault detection effect in the field of intelligent transportation, and can be used to monitor the operating status of unmanned vehicle tires in real time. Specifically, it can be used to intelligently monitor abnormal conditions of unmanned vehicle tires, and intelligently evaluate and feedback the compensation degree of unmanned vehicle tires according to levels, so as to quickly understand the operating status of unmanned vehicle tires and take corresponding measures to optimize the processing.

[0012] Furthermore, the process of the tire data monitoring module processing the first state information to obtain the T3 fluctuation trend value of the sample vehicle tire includes:

[0013] Obtain vehicle information in the system and mark the number of the monitored sample vehicle as i, i=1, 2, 3, ..., o; o is a positive integer;

[0014] Determine the sample vehicles to be monitored, and use sensor technology and image recognition technology to monitor the tire pressure and temperature of the sample vehicles and identify the tire wear;

[0015] The tire pressure value, tire temperature value and tire wear degree of the monitored sample vehicle are marked as Bi, Ci and Di respectively;

[0016] The vehicle tire data table 1 is formed by integrating the monitoring sample vehicle tire data, and the sample vehicle tire data table 1 is stored and uploaded to the database;

[0017] Extracting real-time data of the state information from a database according to the first state information, including tire pressure value Bi, tire temperature value Ci and tire wear degree Di;

[0018] The real-time data of the first state information is normalized, and the comprehensive fluctuation trend of the sample vehicle tire is analyzed using the T3 fluctuation trend value formula, where the T3 fluctuation trend value formula is: ; In the formula, represents the T3 fluctuation trend value of the i-th sample vehicle; Represents the intercept of the multiple linear regression equation; , as well as Represents the regression coefficient of the independent variable of the multiple linear regression equation; represents the error term.

[0019] Furthermore, the process of the tire data monitoring module analyzing the T3 fluctuation trend value of the sample vehicle tire to obtain the direct abnormal signal includes:

[0020] Set T3 volatility value The critical threshold F0;

[0021] T3 Fluctuation Trend and T3 volatility value The critical threshold F0 is compared and analyzed. If it is greater than F0, the comprehensive fluctuation trend of the tire of the sample vehicle is judged to be abnormal, and the sample vehicle is marked as the target vehicle; if If it is not greater than F0, it is judged that the comprehensive fluctuation trend of the tire of the sample vehicle belongs to the normal fluctuation range, and a signal to be detected is generated;

[0022] Acquire first state information of the target vehicle;

[0023] Corresponding reference intervals are set for the tire pressure value, tire temperature value and tire wear value of the target vehicle, and different reference intervals are marked as ( );

[0024] By matching and analyzing the first state information of the target vehicle with the corresponding reference interval, if the value in the first state information is outside the reference interval, and at least one value exceeds the corresponding reference interval, a direct abnormality signal corresponding to the tire of the target vehicle is generated, wherein the direct abnormality signal includes a tire pressure abnormality signal, a tire temperature abnormality signal, and a tire wear abnormality signal;

[0025] The direct abnormal signal and the corresponding target vehicle number are sent to the intelligent feedback terminal.

[0026] Furthermore, the process in which the tire data monitoring module processes the second state information to obtain the change of the tire and the steering wheel includes:

[0027] Determine the serial number of the sample vehicle based on the signal to be detected;

[0028] Sensor technology is used to monitor the real-time changes of the steering wheel of the sample vehicle and the changes of the tire when the steering wheel is turned;

[0029] The vehicle tire data table 2 is formed by integrating the monitored sample vehicle tire data, and the sample vehicle tire data table 2 is stored and uploaded to the database;

[0030] The time when the steering wheel starts to change is marked as the first start time P1, and the steering wheel starts to turn at a first angle Q1; the time when the steering wheel stops changing is marked as the first end time P2, and the steering wheel ends turning at a second angle Q2;

[0031] Obtain the steering wheel change duration FS=P2-P1 according to the first start time and the first end time, and obtain the steering wheel change angle FJ=Q2-Q1 according to the first angle and the second angle;

[0032] The time when the tire starts to change is marked as the second start time P3, and the tire starts to turn the angle as the third angle Q3; the time when the tire stops changing is marked as the second end time P4, and the steering wheel ends the turning angle as the fourth angle Q4;

[0033] The tire rotation response duration XS=P3-P2 is obtained from the second start time and the first end time; the tire rotation continuous reaction duration LS=P4-P3 is obtained from the second start time and the second end time; and the tire rotation reaction angle LJ=Q4-Q3 is obtained from the third angle and the fourth angle.

[0034] Furthermore, the process of the tire data monitoring module processing the second state information to obtain the abnormality detection formula and the indirect abnormality signal of the sample vehicle tire includes:

[0035] According to the changes of the tire and steering wheel, an abnormality detection formula is designed, wherein the abnormality monitoring formula is: ; Wherein, threshold 1, threshold 2, threshold 3, threshold 4 and threshold 5 are preset critical values ​​of each parameter;

[0036] An indirect abnormality signal is generated according to the steering wheel abnormality, and the indirect abnormality signal and the corresponding sample vehicle number are sent to the intelligent feedback terminal.

[0037] Furthermore, the process of obtaining the tire compensation coefficient by the compensation level analysis module according to the calculation result of the abnormality detection formula includes:

[0038] Based on the calculation results of the anomaly detection formula, the tire anomaly set (a, b) = {(a1, b1), (a2, b2), ... ( , bk)}, where a is the duration of abnormal tire rotation reaction, b is the abnormal tire rotation reaction angle, and k represents the number of abnormal tires obtained;

[0039] Set the tire boundary point set (a', b'), where a' is the critical value of the tire rotation reaction duration, and b' is the critical value of the tire rotation reaction angle;

[0040] The adjusted compensation set is calculated according to the following formula ( , ):

[0041] ; Where c and f are constants;

[0042] Gather all compensation sets;

[0043] All the collected compensation sets are normalized to obtain the tire compensation coefficient, where the calculation formula of the tire compensation coefficient Ch is: , where s represents the number of comparisons, and They respectively represent the compensation value of the tire rotation continuous reaction time and the compensation value of the tire rotation reaction angle obtained for the hth time, represents the h-th compensation evaluation value, represents the hth compensation proportional coefficient, and 0< <1, where h=1, 2, 3, …, s; s is a positive integer.

[0044] Furthermore, the compensation level analysis module determines the compensation level of the abnormal tire by the tire compensation coefficient to obtain the primary compensation signal and the secondary compensation signal, and the process of obtaining the compensation evaluation result includes:

[0045] Set the critical threshold value Ch0 of the compensation coefficient, compare the compensation coefficient Ch with the critical threshold value Ch0 of the compensation coefficient, and obtain the compensation evaluation result G; if the difference between the two is greater than R, where R∈(0,1), then output G=1 and generate a primary compensation signal; if the difference between the two is not greater than R, then output G=0 and generate a secondary compensation signal;

[0046] The compensation evaluation result is formed according to the primary compensation signal and the secondary compensation signal.

[0047] Furthermore, the process of obtaining different abnormal signals and compensation signals for optimization by the evaluation result feedback module includes:

[0048] The evaluation result feedback module obtains direct abnormality signals, indirect abnormality signals, primary compensation signals and secondary compensation signals;

[0049] Corresponding sample vehicle numbers are associated with different abnormal signals and compensation signals;

[0050] The direct abnormal signal, indirect abnormal signal, secondary compensation signal and the corresponding sample vehicle number are sent to the administrator through the intelligent feedback terminal, and optimization operations are performed; the primary compensation signal and the sample vehicle number are sent to the administrator through the intelligent feedback terminal for online management, and the problem is immediately checked to formulate optimization measures, and the primary compensation signal is reported to the next higher level supervisor.

[0051] A method for detecting faults in an unmanned vehicle, comprising:

[0052] Calculate and analyze the comprehensive fluctuation trend of the sample vehicle tire according to the first state information to obtain the T3 fluctuation trend value of the sample vehicle tire, and analyze to obtain a direct abnormal signal; calculate and analyze the abnormality detection formula according to the second state information to obtain an indirect abnormal signal;

[0053] The tire compensation coefficient is comprehensively analyzed according to the calculation result of the abnormality detection formula, and the compensation level of the abnormal tire is determined to obtain the primary compensation signal and the secondary compensation signal, thereby obtaining the compensation evaluation result;

[0054] Obtain different abnormal signals, compensation signals and corresponding sample vehicle numbers, and send them to the background for optimization through the intelligent feedback terminal.

[0055] Compared with the existing technology, the advantages of the present invention based on an unmanned vehicle fault detection system and method are:

[0056] The present invention monitors the tire information of the sample vehicle, divides the first state information and the second state information of the sample vehicle tire, calculates and analyzes the comprehensive fluctuation trend of the sample vehicle tire according to the first state information, thereby obtaining the T3 fluctuation trend value of the sample vehicle tire, and obtains the direct abnormal signal through analysis; calculates and analyzes the abnormal detection formula according to the second state information, thereby obtaining the indirect abnormal signal, so as to perform monitoring and analysis in a more orderly manner;

[0057] The present invention comprehensively analyzes the tire compensation coefficient according to the calculation result of the abnormal detection formula, and determines the compensation level of the abnormal tire to obtain the primary compensation signal and the secondary compensation signal, thereby obtaining the compensation evaluation result, which helps to more accurately capture the change trend of system performance;

[0058] The present invention obtains different abnormal signals and compensation signals and corresponding sample vehicle numbers, and sends them to the background for optimization through an intelligent feedback terminal, so that subsequent analysis is more accurate and ensures that the extracted information can accurately reflect the current working status.

[0059] To sum up, the present invention can monitor tire faults of unmanned vehicles through comprehensive data processing and analysis according to actual conditions. The evaluation result feedback module associates different abnormal signals and compensation signals with the corresponding sample vehicle numbers, and sends them to the background intelligent terminal for optimization. The system can better cope with possible abnormal situations, and at the same time, promptly repair and optimize when problems are found, thereby improving the overall performance of the system, thereby ensuring the normal operation of a subsequent fault detection system and method based on unmanned vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 This is a module diagram of a fault detection system based on an unmanned vehicle proposed by the present invention.

[0061] Figure 2 The present invention provides a flow chart of a method for detecting faults in an unmanned vehicle. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the implementation regulations described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] Reference Figure 1 , a fault detection system based on unmanned vehicles, the system includes a vehicle information collection module, a tire data monitoring module, a compensation level analysis module and an evaluation result feedback module;

[0064] The vehicle information collection module is used to collect information about unmanned vehicles and send the information to the tire data monitoring module; the unmanned vehicle information is collected by connecting the unmanned vehicle to a cloud server or a vehicle management center through an on-board communication module (such as a 4G / 5G module) to achieve remote monitoring and data collection;

[0065] The tire data monitoring module is used to monitor the tire information of the sample vehicle, and the monitoring of the tire information of the sample vehicle includes the first state information and the second state information of the tire of the sample vehicle; the first state information includes the tire pressure condition, the tire temperature condition and the tire wear condition, and the second state information includes the change data of the steering wheel and the reaction data of the tire; the comprehensive fluctuation trend of the tire of the sample vehicle is calculated and analyzed according to the first state information to obtain the T3 fluctuation trend value of the tire of the sample vehicle, and the direct abnormal signal is obtained by analysis; the abnormal detection formula is calculated and analyzed according to the second state information to obtain the indirect abnormal signal;

[0066] The compensation level analysis module is used to comprehensively analyze the tire compensation coefficient according to the calculation result of the abnormal detection formula, and determine the compensation level of the abnormal tire to obtain the primary compensation signal and the secondary compensation signal, thereby obtaining the compensation evaluation result;

[0067] The evaluation result feedback module is used to obtain different abnormal signals and compensation signals and the corresponding sample vehicle numbers, and send them to the background for optimization through the intelligent feedback terminal.

[0068] It should be noted that the application object of a system and method based on an unmanned vehicle fault detection in an embodiment of the present invention can be an unmanned vehicle fault detection effect in the field of intelligent transportation, and can be used to monitor the operating status of unmanned vehicle tires in real time. Specifically, it can be used to intelligently monitor abnormal conditions of unmanned vehicle tires, and intelligently evaluate and feedback the compensation degree of unmanned vehicle tires according to levels, so as to quickly understand the operating status of unmanned vehicle tires and take corresponding measures to optimize the processing.

[0069] The process of the tire data monitoring module processing the first state information to obtain the T3 fluctuation trend value of the sample vehicle tire includes:

[0070] S101, obtaining vehicle information in the system, and marking the number of the monitored sample vehicle as i, i=1, 2, 3, ..., o; o is a positive integer;

[0071] S102, determining sample vehicles to be monitored, and using sensor technology and image recognition technology to monitor tire pressure conditions and tire temperature conditions of the sample vehicles and identify tire wear conditions;

[0072] S103, marking the tire pressure value, tire temperature value and tire wear degree of the monitored sample vehicle as Bi, Ci and Di respectively;

[0073] S104, forming a vehicle tire data table 1 by integrating the monitored sample vehicle tire data, and storing and uploading the sample vehicle tire data table 1 to a database;

[0074] S105, extracting real-time data of the state information from a database according to the first state information, including a tire pressure value Bi, a tire temperature value Ci, and a tire wear degree Di;

[0075] S106, normalizing the real-time data of the first state information, and analyzing the comprehensive fluctuation trend of the sample vehicle tire using the T3 fluctuation trend value formula, wherein the T3 fluctuation trend value formula is: ; In the formula, represents the T3 fluctuation trend value of the i-th sample vehicle; Represents the intercept of the multiple linear regression equation; , as well as Represents the regression coefficient of the independent variable of the multiple linear regression equation; represents the error term.

[0076] The process of the tire data monitoring module analyzing the T3 fluctuation trend value of the sample vehicle tire to obtain the direct abnormal signal includes:

[0077] S201, set T3 fluctuation trend value The critical threshold F0;

[0078] S202, T3 fluctuation trend value and T3 volatility value The critical threshold F0 is compared and analyzed. If it is greater than F0, the comprehensive fluctuation trend of the tire of the sample vehicle is judged to be abnormal, and the sample vehicle is marked as the target vehicle; if If it is not greater than F0, it is judged that the comprehensive fluctuation trend of the tire of the sample vehicle belongs to the normal fluctuation range, and a signal to be detected is generated;

[0079] S203, obtaining first state information of the target vehicle;

[0080] S204, setting corresponding reference intervals for the tire pressure value, tire temperature value and tire wear value of the target vehicle, and marking different reference intervals as ( );

[0081] S205, matching and analyzing the first state information of the target vehicle with the corresponding reference interval, if the value in the first state information is outside the reference interval, and at least one value exceeds the corresponding reference interval, generating a direct abnormality signal corresponding to the tire of the target vehicle, wherein the direct abnormality signal includes a tire pressure abnormality signal, a tire temperature abnormality signal, and a tire wear abnormality signal;

[0082] S206. Send the direct abnormal signal and the corresponding target vehicle number to the intelligent feedback terminal.

[0083] The process of the tire data monitoring module processing the second state information to obtain the change of the tire and the steering wheel includes:

[0084] S301, determining the number of a sample vehicle based on the signal to be detected;

[0085] S302, using sensor technology to monitor the real-time changes of the steering wheel of the sample vehicle and the changes of the tires when the steering wheel is turned;

[0086] S303, forming a second vehicle tire data table by integrating the monitored sample vehicle tire data, and storing and uploading the second sample vehicle tire data table to a database;

[0087] S304, marking the time when the steering wheel starts to change as a first start time P1, and marking the steering wheel starting turning angle as a first angle Q1; marking the time when the steering wheel stops changing as a first end time P2, and marking the steering wheel ending turning angle as a second angle Q2;

[0088] S305, obtaining a steering wheel change duration FS=P2-P1 according to the first start time and the first end time, and obtaining a steering wheel change angle FJ=Q2-Q1 according to the first angle and the second angle;

[0089] S306, marking the time when the tire starts to change as the second start time P3, and marking the tire start steering angle as the third angle Q3; marking the time when the tire stops changing as the second end time P4, and marking the steering wheel end steering angle as the fourth angle Q4;

[0090] S307, obtain the tire rotation response time XS=P3-P2 from the second start time and the first end time; obtain the tire rotation continuous reaction time LS=P4-P3 from the second start time and the second end time; and obtain the tire rotation reaction angle LJ=Q4-Q3 from the third angle and the fourth angle.

[0091] The process of the tire data monitoring module processing the second state information to obtain the abnormality detection formula and the indirect abnormality signal of the sample vehicle tire includes:

[0092] S401. Design an abnormality detection formula according to the changes of the tire and the steering wheel, wherein the abnormality monitoring formula is: ; Wherein, threshold 1, threshold 2, threshold 3, threshold 4 and threshold 5 are preset critical values ​​of each parameter;

[0093] S402: Generate an indirect abnormality signal according to the steering wheel abnormality, and send the indirect abnormality signal and the corresponding sample vehicle number to the intelligent feedback terminal.

[0094] The process of the compensation level analysis module processing the calculation result of the abnormal detection formula to obtain the tire compensation coefficient includes:

[0095] S501, based on the calculation result of the anomaly detection formula, obtain the tire anomaly set (a, b) = {(a1, b1), (a2, b2), ... ( , bk)}, where a is the duration of abnormal tire rotation reaction, b is the abnormal tire rotation reaction angle, and k represents the number of abnormal tires obtained;

[0096] S502, setting a set of tire boundary points (a', b'), where a' is a critical value of the tire rotation continuous reaction time, and b' is a critical value of the tire rotation reaction angle;

[0097] S503, calculate the adjusted compensation set according to the following formula: , ):

[0098] ; Where c and f are constants;

[0099] S504, collect all compensation sets;

[0100] S505: normalize all the collected compensation sets to obtain a tire compensation coefficient, wherein the calculation formula of the tire compensation coefficient Ch is: , where s represents the number of comparisons, and They respectively represent the compensation value of the tire rotation continuous reaction time and the compensation value of the tire rotation reaction angle obtained for the hth time, represents the h-th compensation evaluation value, represents the hth compensation proportional coefficient, and 0< <1, where h=1, 2, 3, …, s; s is a positive integer.

[0101] The compensation level analysis module determines the compensation level of the abnormal tire by the tire compensation coefficient to obtain the primary compensation signal and the secondary compensation signal, and the process of obtaining the compensation evaluation result includes:

[0102] S601, setting a critical threshold value Ch0 of the compensation coefficient, comparing the compensation coefficient Ch with the critical threshold value Ch0 of the compensation coefficient, and obtaining a compensation evaluation result G; if the difference between the two is greater than R, where R∈(0,1), then output G=1, and generate a primary compensation signal; if the difference between the two is not greater than R, then output G=0, and generate a secondary compensation signal;

[0103] S602: Construct a compensation evaluation result according to the primary compensation signal and the secondary compensation signal.

[0104] The process of obtaining different abnormal signals and compensation signals for optimization by the evaluation result feedback module includes:

[0105] S701, the evaluation result feedback module obtains a direct abnormal signal, an indirect abnormal signal, a primary compensation signal, and a secondary compensation signal;

[0106] S702, associating corresponding sample vehicle numbers with different abnormal signals and compensation signals;

[0107] S703. Send the direct abnormal signal, indirect abnormal signal, secondary compensation signal and the corresponding sample vehicle number to the administrator through the intelligent feedback terminal, and perform optimization operations; send the primary compensation signal and the sample vehicle number to the administrator through the intelligent feedback terminal for online management, and immediately query the problem and formulate optimization measures, and report the primary compensation signal to the next higher level supervisor.

[0108] In an embodiment of the present invention, the comprehensive fluctuation trend of the sample vehicle tire is calculated and analyzed according to the first state information to obtain the T3 fluctuation trend value of the sample vehicle tire, and the direct abnormal signal is obtained by analysis; the abnormal detection formula is calculated and analyzed according to the second state information to obtain the indirect abnormal signal, and the tire compensation coefficient is comprehensively analyzed according to the calculation result of the abnormal detection formula, and the compensation level of the abnormal tire is determined to obtain the first-level compensation signal and the second-level compensation signal, thereby obtaining the compensation evaluation result, and by obtaining different abnormal signals and compensation signals and the corresponding sample vehicle numbers, the intelligent feedback end sends them to the background for optimization, aiming to improve the safety, reliability and stability of unmanned vehicles. In summary, the examples of the present invention involve data collection and analysis, result generation and decision-making of optimization measures, and solve the problem of being unable to efficiently monitor the tire fault detection effect of unmanned vehicles and conduct targeted evaluation feedback. In actual situations, more data and context information may be required to make specific decisions and optimization plans.

[0109] Reference Figure 2 , a method for fault detection based on an unmanned vehicle, comprising:

[0110] Calculate and analyze the comprehensive fluctuation trend of the sample vehicle tire according to the first state information to obtain the T3 fluctuation trend value of the sample vehicle tire, and analyze to obtain a direct abnormal signal; calculate and analyze the abnormality detection formula according to the second state information to obtain an indirect abnormal signal;

[0111] The tire compensation coefficient is comprehensively analyzed according to the calculation result of the abnormality detection formula, and the compensation level of the abnormal tire is determined to obtain the primary compensation signal and the secondary compensation signal, thereby obtaining the compensation evaluation result;

[0112] Obtain different abnormal signals, compensation signals and corresponding sample vehicle numbers, and send them to the background for optimization through the intelligent feedback terminal.

[0113] In addition, the formulas involved in the above are all calculated by removing dimensions and taking their numerical values. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The proportional coefficient in the formula and the various preset thresholds in the analysis process are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data; the size of the proportional coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the proportional coefficient depends on the amount of sample data and the preliminary setting of the corresponding processing coefficient for each group of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0114] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically based on the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0115] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0116] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0117] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0118] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0119] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0120] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0121] Finally: The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A fault detection system based on an unmanned vehicle, characterized in that: It includes vehicle information collection module, tire data monitoring module, compensation level analysis module and evaluation result feedback module; The vehicle information collection module is used to collect the information of the unmanned vehicle and send the information to the tire data monitoring module; The tire data monitoring module is used to monitor the tire information of the sample vehicle, and the monitoring of the tire information of the sample vehicle includes the first state information and the second state information of the tire of the sample vehicle; the first state information includes the tire pressure condition, the tire temperature condition and the tire wear condition, and the second state information includes the change data of the steering wheel and the reaction data of the tire; the comprehensive fluctuation trend of the tire of the sample vehicle is calculated and analyzed according to the first state information to obtain the T3 fluctuation trend value of the tire of the sample vehicle, and the direct abnormal signal is obtained by analysis; the abnormal detection formula is calculated and analyzed according to the second state information to obtain the indirect abnormal signal; The compensation level analysis module is used to comprehensively analyze the tire compensation coefficient according to the calculation result of the abnormal detection formula, and determine the compensation level of the abnormal tire to obtain the primary compensation signal and the secondary compensation signal, thereby obtaining the compensation evaluation result; The evaluation result feedback module is used to obtain different abnormal signals and compensation signals and the corresponding sample vehicle numbers, and send them to the background for optimization through the intelligent feedback terminal.

2. The unmanned vehicle fault detection system according to claim 1, characterized in that: The process of the tire data monitoring module processing the first state information to obtain the T3 fluctuation trend value of the sample vehicle tire includes: Obtain vehicle information in the system and mark the number of the monitored sample vehicle as i, i=1, 2, 3, ..., o; o is a positive integer; Determine the sample vehicles to be monitored, and use sensor technology and image recognition technology to monitor the tire pressure and temperature of the sample vehicles and identify the tire wear; The tire pressure value, tire temperature value and tire wear degree of the monitored sample vehicle are marked as Bi, Ci and Di respectively; The vehicle tire data table 1 is formed by integrating the monitoring sample vehicle tire data, and the sample vehicle tire data table 1 is stored and uploaded to the database; Extracting real-time data of the state information from a database according to the first state information, including tire pressure value Bi, tire temperature value Ci and tire wear degree Di; The real-time data of the first state information is normalized, and the comprehensive fluctuation trend of the sample vehicle tire is analyzed using the T3 fluctuation trend value formula, where the T3 fluctuation trend value formula is: ; In the formula, represents the T3 fluctuation trend value of the i-th sample vehicle; Represents the intercept of the multiple linear regression equation; , as well as Represents the regression coefficient of the independent variable of the multiple linear regression equation; represents the error term.

3. The unmanned vehicle fault detection system according to claim 2, characterized in that: The process of the tire data monitoring module analyzing the T3 fluctuation trend value of the sample vehicle tire to obtain the direct abnormal signal includes: Set T3 volatility value The critical threshold F0; T3 Fluctuation Trend and T3 volatility value The critical threshold F0 is compared and analyzed. If it is greater than F0, the comprehensive fluctuation trend of the tire of the sample vehicle is judged to be abnormal, and the sample vehicle is marked as the target vehicle; if If it is not greater than F0, it is judged that the comprehensive fluctuation trend of the tire of the sample vehicle belongs to the normal fluctuation range, and a signal to be detected is generated; Acquire first state information of the target vehicle; Corresponding reference intervals are set for the tire pressure value, tire temperature value and tire wear value of the target vehicle, and different reference intervals are marked as ( ); By matching and analyzing the first state information of the target vehicle with the corresponding reference interval, if the value in the first state information is outside the reference interval, and at least one value exceeds the corresponding reference interval, a direct abnormality signal corresponding to the tire of the target vehicle is generated, wherein the direct abnormality signal includes a tire pressure abnormality signal, a tire temperature abnormality signal, and a tire wear abnormality signal; The direct abnormal signal and the corresponding target vehicle number are sent to the intelligent feedback terminal.

4. The unmanned vehicle fault detection system according to claim 3 is characterized in that: The process of the tire data monitoring module processing the second state information to obtain the change of the tire and the steering wheel includes: Determine the serial number of the sample vehicle based on the signal to be detected; Sensor technology is used to monitor the real-time changes of the steering wheel of the sample vehicle and the changes of the tire when the steering wheel is turned; The vehicle tire data table 2 is formed by integrating the monitored sample vehicle tire data, and the sample vehicle tire data table 2 is stored and uploaded to the database; The time when the steering wheel starts to change is marked as the first start time P1, and the steering wheel starts to turn at a first angle Q1; the time when the steering wheel stops changing is marked as the first end time P2, and the steering wheel ends turning at a second angle Q2; Obtain the steering wheel change duration FS=P2-P1 according to the first start time and the first end time, and obtain the steering wheel change angle FJ=Q2-Q1 according to the first angle and the second angle; The time when the tire starts to change is marked as the second start time P3, and the tire starts to turn the angle as the third angle Q3; the time when the tire stops changing is marked as the second end time P4, and the steering wheel ends the turning angle as the fourth angle Q4; The tire rotation response duration XS=P3-P2 is obtained from the second start time and the first end time; the tire rotation continuous reaction duration LS=P4-P3 is obtained from the second start time and the second end time; and the tire rotation reaction angle LJ=Q4-Q3 is obtained from the third angle and the fourth angle.

5. The unmanned vehicle fault detection system according to claim 1, characterized in that: The process of the tire data monitoring module processing the second state information to obtain the abnormality detection formula and the indirect abnormality signal of the sample vehicle tire includes: According to the changes of the tire and steering wheel, an abnormality detection formula is designed, wherein the abnormality monitoring formula is: ; Wherein, threshold 1, threshold 2, threshold 3, threshold 4 and threshold 5 are preset critical values ​​of each parameter; An indirect abnormality signal is generated according to the steering wheel abnormality, and the indirect abnormality signal and the corresponding sample vehicle number are sent to the intelligent feedback terminal.

6. The unmanned vehicle fault detection system according to claim 1, characterized in that: The process of the compensation level analysis module processing the calculation result of the abnormal detection formula to obtain the tire compensation coefficient includes: Based on the calculation results of the anomaly detection formula, the tire anomaly set (a, b) = {(a1, b1), (a2, b2), ... ( , bk)}, where a is the duration of abnormal tire rotation reaction, b is the abnormal tire rotation reaction angle, and k represents the number of abnormal tires obtained; Set the tire boundary point set (a', b'), where a' is the critical value of the tire rotation reaction duration, and b' is the critical value of the tire rotation reaction angle; The adjusted compensation set is calculated according to the following formula ( , ): ; In the formula, c and f are constants; Gather all compensation sets; All the collected compensation sets are normalized to obtain the tire compensation coefficient, where the calculation formula of the tire compensation coefficient Ch is: , where s represents the number of comparisons, and They respectively represent the compensation value of the tire rotation continuous reaction time and the compensation value of the tire rotation reaction angle obtained for the hth time, represents the h-th compensation evaluation value, represents the hth compensation proportional coefficient, and 0< <1, where h=1, 2, 3, …, s; s is a positive integer.

7. The unmanned vehicle fault detection system according to claim 6, characterized in that: The compensation level analysis module determines the compensation level of the abnormal tire by the tire compensation coefficient to obtain the primary compensation signal and the secondary compensation signal, and the process of obtaining the compensation evaluation result includes: Set the critical threshold value Ch0 of the compensation coefficient, compare the compensation coefficient Ch with the critical threshold value Ch0 of the compensation coefficient, and obtain the compensation evaluation result G; if the difference between the two is greater than R, where R∈(0,1), then output G=1 and generate a primary compensation signal; if the difference between the two is not greater than R, then output G=0 and generate a secondary compensation signal; The compensation evaluation result is formed according to the primary compensation signal and the secondary compensation signal.

8. The unmanned vehicle fault detection system according to claim 1, characterized in that: The process of obtaining different abnormal signals and compensation signals for optimization by the evaluation result feedback module includes: The evaluation result feedback module obtains direct abnormality signals, indirect abnormality signals, primary compensation signals and secondary compensation signals; Corresponding sample vehicle numbers are associated with different abnormal signals and compensation signals; The direct abnormal signal, indirect abnormal signal, secondary compensation signal and the corresponding sample vehicle number are sent to the administrator through the intelligent feedback terminal, and optimization operations are performed; the primary compensation signal and the sample vehicle number are sent to the administrator through the intelligent feedback terminal for online management, and the problem is immediately checked to formulate optimization measures, and the primary compensation signal is reported to the next higher level supervisor.

9. A method for detecting faults in an unmanned vehicle, characterized in that: Applied to a fault detection system based on an unmanned vehicle as claimed in any one of claims 1 to 8, the method comprising: Calculate and analyze the comprehensive fluctuation trend of the sample vehicle tire according to the first state information to obtain the T3 fluctuation trend value of the sample vehicle tire, and analyze to obtain a direct abnormal signal; calculate and analyze the abnormality detection formula according to the second state information to obtain an indirect abnormal signal; The tire compensation coefficient is comprehensively analyzed according to the calculation result of the abnormality detection formula, and the compensation level of the abnormal tire is determined to obtain the primary compensation signal and the secondary compensation signal, thereby obtaining the compensation evaluation result; Obtain different abnormal signals, compensation signals and corresponding sample vehicle numbers, and send them to the background for optimization through the intelligent feedback terminal.

Images