A connected vehicle fault prediction system and method based on grey correlation

Abstract

The present invention discloses a networked vehicle fault prediction system based on grey correlation, comprising: an on-board terminal collects real-time operation data of the on-board system, combines the identity information and location information of the networked vehicle to compile into a real-time information data packet of the on-board terminal, and sends the real-time information data packet to the roadside system; the roadside system fuses multi-source heterogeneous road traffic data and generates a road traffic information data packet, sends the road traffic information data packet to the on-board terminal, and sends the real-time information data packet to the vehicle-road collaborative cloud. The vehicle-road collaborative cloud performs fault prediction analysis based on the real-time information data packet and the vehicle fault prediction model based on grey correlation, obtains the spatial distribution inverse matrix of the relative coefficient matrix of each on-board system assembly, calculates the partial correlation probability of the fault of each on-board system based on the spatial distribution inverse matrix, and obtains the vehicle fault location. The system can accurately determine the vehicle fault location and realize the active, intelligent, and smart fault diagnosis of networked vehicles.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle fault warning technology, and in particular to a networked vehicle fault prediction system and method based on grey correlation. Background Art

[0002] With the accelerated evolution of networking and intelligent technologies, intelligent connected vehicles have entered a critical period of development. Intelligent connected vehicles have become an important strategic direction for the transformation and upgrading of the global automotive industry. In the future, the policy level will further increase support to promote the coordinated development of vehicle networking, intelligence and electrification. With the increase in the penetration rate of connected vehicles, traffic accidents caused by vehicle failures are frequent. In order to reduce traffic accidents and traffic congestion caused by vehicle failures, it is urgent to develop an effective method for predicting faults in connected vehicles. Summary of the invention

[0003] In view of the defects in the prior art, the embodiments of the present invention provide a connected vehicle fault prediction system and method based on grey correlation, which can accurately predict the vehicle fault location and realize active, intelligent and smart fault diagnosis of the connected vehicle.

[0004] In a first aspect, an embodiment of the present invention provides a connected vehicle fault prediction system based on grey correlation, comprising: a vehicle-mounted terminal, a roadside system and a vehicle-road collaborative cloud, wherein:

[0005] The vehicle-mounted terminal collects real-time operation data of the vehicle-mounted system, performs denoising and cleaning processing on the real-time operation data, and organizes the data into a vehicle-mounted terminal real-time information data packet in combination with the identity information and location information of the networked vehicle, and sends the real-time information data packet to the roadside system;

[0006] The roadside system receives real-time information data packets, obtains road conditions and forward traffic conditions information, fuses multi-source heterogeneous road traffic data and generates road traffic information data packets, sends the road traffic information data packets to the vehicle-mounted terminal, and sends the real-time information data packets to the vehicle-road collaboration cloud;

[0007] The vehicle-road collaborative cloud receives and stores real-time information data packets, performs fault prediction analysis based on the real-time information data packets and a vehicle fault prediction model based on grey correlation, obtains the spatial distribution inverse matrix of the relative coefficient matrix of each vehicle system assembly, calculates the partial correlation probability of faults of each vehicle system based on the spatial distribution inverse matrix, and obtains the vehicle fault location.

[0008] In a second aspect, an embodiment of the present invention provides a method for predicting faults of a connected vehicle based on grey correlation, comprising the following steps:

[0009] The vehicle terminal collects the real-time operation data of the vehicle system, performs denoising and cleaning processing on the real-time operation data, and organizes the data into a vehicle terminal real-time information data packet in combination with the identity information and location information of the networked vehicle, and sends the real-time information data packet to the roadside system;

[0010] The roadside system receives real-time information data packets, obtains information on road conditions and traffic conditions ahead, fuses multi-source heterogeneous road traffic data and generates road traffic information data packets, sends the road traffic information data packets to the vehicle-mounted terminal, and sends the real-time information data packets to the vehicle-road collaboration cloud;

[0011] The vehicle-road collaborative cloud receives and stores real-time information data packets, performs fault prediction analysis based on the real-time information data packets and the vehicle fault prediction model based on grey correlation, obtains the spatial distribution inverse matrix of the relative coefficient matrix of each vehicle system assembly, calculates the partial correlation probability of faults of each vehicle system based on the spatial distribution inverse matrix, and determines the vehicle fault location based on the partial correlation probability of each vehicle system.

[0012] In a third aspect, an embodiment of the present invention provides a method for predicting faults of connected vehicles based on grey correlation, which is applicable to a vehicle-road collaborative cloud. The method includes the following steps:

[0013] Receive and store real-time information packets;

[0014] According to the real-time information data packet and the vehicle fault prediction model based on grey correlation, the fault prediction analysis is carried out to obtain the spatial distribution inverse matrix of the relative coefficient matrix of each vehicle system assembly;

[0015] The partial correlation probability of each vehicle system's fault is calculated based on the inverse matrix of spatial distribution, and the vehicle fault location is determined according to the partial correlation probability of each vehicle system.

[0016] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the method described in the above embodiment.

[0017] Beneficial effects of the present invention:

[0018] The present invention provides a connected vehicle fault prediction system and method based on grey correlation. The system collects real-time operation data of the vehicle system through a vehicle terminal, performs fault analysis and prediction based on a grey correlation vehicle fault model, accurately determines the vehicle fault location, and realizes active, intelligent, and smart fault diagnosis of the connected vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0020] Figure 1 A structural block diagram of a networked vehicle fault prediction system based on grey correlation provided by a first embodiment of the present invention is shown;

[0021] Figure 2 A flowchart of a method for predicting faults of connected vehicles based on grey correlation provided by the second embodiment of the present invention is shown.

[0022] Figure 3 A specific flow chart of a method for predicting faults of connected vehicles based on grey correlation provided by the second embodiment of the present invention is shown. DETAILED DESCRIPTION

[0023] 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 described embodiments are 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.

[0024] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0025] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0026] It should be further understood that the term "and / or" used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0027] As used in this specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0028] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by those skilled in the art to which the invention belongs.

[0029] like Figure 1 As shown, a structural block diagram of a networked vehicle fault prediction system based on grey correlation provided by the first embodiment of the present invention is shown. Grey correlation analysis is a grey system analysis method. It is a method to measure the degree of correlation between factors based on the similarity or difference in the development trends between factors, that is, "grey correlation". The system includes: an on-board terminal, a roadside system and a vehicle-road collaborative cloud, wherein the on-board terminal collects real-time operation data of the on-board system, performs denoising and cleaning processing on the real-time operation data, and organizes the data in combination with the identity information and location information of the networked vehicle to form a real-time information data packet for the on-board terminal, and sends the real-time information data packet to the roadside system; the roadside system receives the real-time information data packet, obtains road conditions and forward traffic conditions information, fuses multi-source heterogeneous road traffic data and generates a road traffic information data packet, and sends the road traffic information data packet to the on-board terminal, and sends the real-time information data packet to the vehicle-road collaborative cloud; the vehicle-road collaborative cloud receives and stores the real-time information data packet, performs fault prediction analysis based on the real-time information data packet and a vehicle fault prediction model based on grey correlation, obtains the spatial distribution inverse matrix of the relative coefficient matrix of each on-board system assembly, calculates the partial correlation probability of faults of each on-board system based on the spatial distribution inverse matrix, and obtains the vehicle fault location.

[0030] The grayscale correlation-based vehicle fault prediction system provided in the embodiment of the present invention adopts a vehicle-road-cloud system to change the passive fault diagnosis method, and can realize the automatic collection, uploading and storage of networked vehicle systems and road environment data. The system can automatically receive data without human operation, and calculate the fault probability through the vehicle-road collaborative cloud. The cloud computing method greatly reduces the CPU load on the vehicle side, ensures the real-time calculation and timely determines the fault warning level and disposal plan.

[0031] The vehicle terminal includes an information collection module, a vehicle system, a vehicle data processing center module, a vehicle communication module, a vehicle control center, and a warning information interaction and execution control module. The vehicle system is the main object of vehicle fault diagnosis, and the vehicle system includes the engine system, chassis system, body system, electrical system, and tire system. The information collection module includes a sound sensor and a real-time monitoring collector. The sound sensor collects the sound of the vehicle when it is running. The real-time monitoring collector collects the real-time operation data of the vehicle system and transmits the collected data to the vehicle data processing center module. The vehicle data processing center module denoises and cleans the real-time operation data, and combines the self-identity information of the networked vehicle and the vehicle location information to organize it into a vehicle terminal real-time information data packet composed of multiple data blocks, and sends the real-time information data packet to the roadside system. The vehicle communication module includes a wireless communication unit and a vehicle unit. The wireless communication unit adopts a 5G communication unit. The 5G communication unit is used to transmit data with the vehicle-road collaborative cloud, and the vehicle unit is used to directly transmit data with the roadside system.

[0032] The roadside system includes an information sensing device, a roadside data processing center module and a communication module. The information sensing device is used to obtain information on road conditions and traffic conditions ahead. The roadside data processing center module is used to fuse multi-source heterogeneous road data and generate road traffic information data packets. The communication module includes a roadside unit and a wireless communication unit. The wireless communication unit adopts a 5G communication unit. The roadside unit is used to transmit the road traffic information data packets directly to the vehicle-mounted unit. The vehicle-mounted terminal obtains the road traffic information data packets to assist driving. The 5G communication unit is used to send the real-time information data packets sent by the vehicle-mounted terminal to the vehicle-road collaborative cloud.

[0033] The vehicle-road cooperative cloud includes a wireless communication unit, a data storage center module, a vehicle-road cooperative calculation module, a warning level calculation module and a warning information release module. The wireless communication unit adopts a 5G communication unit, and the 5G communication unit is used to receive real-time information data packets. The data storage center module stores real-time information data packets and calculation data generated by the vehicle-road cooperative cloud. The vehicle-road cooperative calculation module is used to calculate the single vehicle fault correlation factor under the influence of a single vehicle parameter index based on the real-time information data packet and the vehicle fault prediction model based on the grey correlation, calculate the coupling difference between multiple vehicle parameter indicators and their corresponding vehicle standard parameter indicators based on the grey correlation vehicle fault prediction model to obtain a first value, and calculate the coupling difference between the vehicle parameter indicator and the vehicle fault parameter indicator to obtain a second value, calculate the multi-vehicle fault correlation factor under the influence of the multi-vehicle parameter indicator based on the single vehicle fault correlation factor, the first value and the second value, and judge whether the vehicle system has a fault risk based on the multi-vehicle fault correlation factor. If there is a risk, the vehicle parameter indicator weights of each vehicle system are calculated based on the spatial distribution matrix and the key parameter variable set is determined, and the coupling difference between the key parameter variable and the vehicle fault parameter indicator is calculated to obtain a third value, and the spatial distribution inverse matrix of the relative coefficient matrix of each vehicle system assembly is calculated based on the third value. The warning level calculation module is used to compare the partial correlation probability of each vehicle system with the corresponding fault probability level threshold of each vehicle system to obtain the fault warning level of each vehicle system and determine the disposal plan according to the fault warning level. The warning information release module is used to release the fault warning level and disposal plan. The fault warning level and disposal plan are transmitted to the vehicle terminal through the 5G communication unit.

[0034] The vehicle failure probability prediction model based on grey correlation analyzes the correlation between each vehicle system parameter index and the failure index, thereby reducing the difficulty of mining the correlation relationship of massive data. From the two perspectives of the correlation factor of a single parameter index of the vehicle system to the vehicle failure and the coupling correlation factor of multiple vehicle parameter indexes to the vehicle failure, it is judged whether the vehicle currently has a failure risk, and the fault location is accurately determined through the partial correlation probability of the vehicle system failure. The impact of each indicator of the vehicle system on the vehicle failure is analyzed from the micro-granularity to the macro-coupling level to ensure the accuracy and precision of the model prediction.

[0035] According to the weight of each vehicle system indicator, the key parameter variable set is output, and the partial correlation probability of each vehicle system fault is calculated based on the spatial distribution inverse matrix SDM. The fault warning level of each vehicle system is accurately controlled according to the key parameter variable set and the partial correlation probability of fault. The failure probability of each system is analyzed independently to reduce the amount of calculation, which can significantly reduce the model calculation time and further improve the real-time and accuracy of model prediction.

[0036] According to the vehicle fault correlation factors under the influence of multiple indicators, connected vehicles with fault mutation risks are screened out, and the vehicle operation data of the fault-risk connected vehicles are analyzed by the vehicle-road collaborative cloud. The fault location is then accurately determined through the partial correlation probability of the on-board system failure, and the fault risk warning level is determined according to the partial correlation probability of each on-board system. A warning and disposal plan is given in a timely manner, which fundamentally ensures the safety of vehicle operation, significantly reduces traffic accidents and traffic congestion rates caused by vehicle failures, and ensures the stable operation of traffic flow.

[0037] The vehicle terminal receives the fault warning level and disposal plan sent by the vehicle-road collaborative cloud through the 5G communication unit. The vehicle data processing center module processes the fault warning level and disposal plan and sends it to the vehicle-road control center. The vehicle control center module is responsible for controlling the work of each functional module of the vehicle terminal. The vehicle control center module receives the real-time information data packet sent by the vehicle data processing center module, converts the disposal plan into a specific control instruction and sends it to the warning information interaction and execution control module. The warning information interaction and execution control module executes the specific control instruction and executes the specific control instruction to each vehicle system. The system uses 5G network communication to transmit data information, greatly reducing the information transmission delay.

[0038] The vehicle fault prediction system based on gray correlation of the present invention calculates the fault correlation factor of the vehicle based on the gray correlation vehicle fault prediction model, determines whether the vehicle as a whole has a fault risk, and in the case of a fault risk, further locates the fault position and determines the vehicle fault warning level based on the partial correlation probability of each vehicle system fault calculated based on the spatial distribution matrix of the relative coefficient of the vehicle system assembly, determines the corresponding disposal plan according to the fault warning level, and sends the fault warning level and the corresponding disposal plan to the vehicle terminal, fundamentally preventing the occurrence of vehicle faults. The system can accurately locate the vehicle-road fault position, realize the active, intelligent and smart fault diagnosis of networked vehicles, ensure the safety of vehicle operation, significantly reduce traffic accidents and traffic congestion rates caused by vehicle faults, and ensure the stable operation of traffic flow.

[0039] like Figure 2 , as shown in FIG3 , a flowchart of a method for predicting faults of a networked vehicle based on grey correlation provided by another embodiment of the present invention is shown. The method is applicable to the system described in the first embodiment above, and the method comprises the following steps:

[0040] The on-board terminal collects the real-time operation data of the on-board system, performs denoising and cleaning processing on the real-time operation data, and organizes it into a real-time information data packet of the on-board terminal in combination with the identity information and location information of the connected vehicle, and sends the real-time information data packet to the roadside system.

[0041] Specifically, the information collection module collects real-time operating data of the vehicle systemi ={e i , c i , b i , d i , l i}, where: engine operation data block e i ={e 1 , e 2 , e 3 ,...e n},e 1 , e 2 ...e n They are the operating parameters of each function of the engine system, the body operation data block b i = {b 1 , b 2 , b 3 , ...b n}, b 1 , b 2 , ...b n They are the function operation parameters of the body system and the chassis operation data block c i ={c 1 , c 2 , c 3 , ...c n}, c 1 , c 2 , ...c n They are the operating parameters of each function of the chassis system and the operating data block of the electrical system. i ={d 1 , d 2 , d 3 ,...d n}, d 1 , d 2 ,...d n They are the operating parameters of each function of the electrical system and the tire operating data block l i = {l 1 , l 2 , l 3 ,...l n}, l 1 , l 2 ,...l n They are the operating parameters of various tire functions, and the data are sent to the on-board data processing center. The on-board data processing center module denoises and cleans the data from different on-board systems, and combines the connected vehicle's own vehicle identity information and vehicle location information to organize them into a real-time information data packet of the on-board terminal composed of multiple data blocks. The real-time information data packet is sent to the roadside system through the vehicle control center module using the on-board unit.

[0042] The roadside system receives real-time information data packets, obtains information on road conditions and traffic conditions ahead, fuses multi-source heterogeneous road traffic data and generates road traffic information data packets, sends the road traffic information data packets to the vehicle-mounted terminal, and sends the real-time information data packets to the vehicle-road collaborative cloud.

[0043] The vehicle-road collaborative cloud receives and stores real-time information data packets, performs fault prediction analysis based on the real-time information data packets and the vehicle fault prediction model based on grey correlation, obtains the spatial distribution inverse matrix of the relative coefficient matrix of each vehicle system assembly, calculates the partial correlation probability of faults of each vehicle system based on the spatial distribution inverse matrix, and determines the vehicle fault location based on the partial correlation probability of each vehicle system.

[0044] Specifically, the vehicle system fault information data packet M is pre-stored in the data storage center module. i ={e mi , c mi , b mi , d mi , l mi}, where the engine fault information data block e mi ={e m1 , e m2 , e m3 ,...e mn},e m1 , e m2 , e m3 ,...e mn They are respectively the operating parameters of each fault module of the engine system, the fault information data block b of the body system mi = {b m1 , b m2 , b m3 , ...b mn}, b m1 , b m2 , b m3 , ...b mn They are the operating parameters of each fault module of the body system, the chassis system fault information data block c mi ={c m1 , c m2 , c m3 , ...c mn}, c m1 , c m2 , c m3 , ...c mn They are respectively the operating parameters of each fault module of the chassis system, the fault information data block of the electrical system mi ={d m1 , d m2 , d m3 ,...d mn}, d m1 , d m2 , d m3 ,...d mn They are respectively the operating parameters of each fault module of the electrical system, the tire system fault information data block l mi = {l m1 , l m2 , l m3 ,...l mn} m1 , l m2 , l m3 ,...l mn They are the operating parameters of each fault module of the tire system.

[0045] The vehicle-road collaborative calculation module calls data for relevant analysis and calculation. The specific calculation method is as follows:

[0046] Multi-block analysis data preprocessing, real-time information data blocks of each vehicle terminal

[0047] e i ={e 1 , e 2 , e 3 ,...e n}, b i = {b 1 , b 2 , b 3 , ...b n},c i ={c 1 , c 2 , c 3 , ...c n},

[0048] d i ={d 1 , d 2 , d 3 ,...d n}, l i = {l 1 , l 2 , l 3 ,...l n}Perform standard metrology preprocessing to correct for changes related to external factors of the data block, etc.;

[0049] A vehicle fault prediction model based on grey correlation is established, and the single vehicle fault correlation factor σ′ under the influence of single vehicle parameter index is calculated based on the model. The formula is as follows:

[0050]

[0051] Among them, 0<λ<1 is the correlation coefficient, which is determined by the operating status of the vehicle system. Based on this model, the association between multiple vehicle operating indicators and vehicle fault indicators is mined. Considering that in the real-time information data packet of the vehicle terminal, if a certain vehicle parameter indicator has a small difference with its corresponding vehicle standard parameter, it is considered that the factor on its correlation index is high. Then the coupling difference between each vehicle parameter indicator and its corresponding vehicle standard parameter indicator is calculated.

[0052]

[0053] in, Yes X i The average value of the vehicle parameter index and the vehicle fault parameter index coupling difference are further calculated.

[0054]

[0055] Finally, the multi-vehicle fault correlation factor σ considering the coupling effect of multi-vehicle parameter indicators can be reconstructed as:

[0056]

[0057] In the actual operation process, the fault warning coefficient σ is determined according to the actual operation capability of the vehicle system. min The vehicle-road collaborative calculation module determines whether the vehicle system has a failure risk based on the vehicle failure correlation factor. If σ<σ min It is judged that there is no failure risk; if σ>σ min ,The vehicle-road collaborative cloud further calculates the partial correlation coefficients of the ,operating indicators of each vehicle system to locate the faulty system.

[0058] Calculate the vehicle parameter index weights of each vehicle system based on the spatial distribution matrix:

[0059] Weight of each indicator of engine system:

[0060] The key parameter variable set is determined by the weight of each indicator of the engine system Similarly, according to the above formula, the weights of the indicators and the key parameter variable sets of the chassis system, body system, electrical system and tire system are calculated as follows: r(c i , c mi ) r(b i , b mi ), r(d i , d mi ), and r(l i , l mi ),

[0061] Calculate the coupling difference between the engine key parameter variables and the fault parameter indicators:

[0062]

[0063] According to the above formula, the spatial distribution inverse matrix SDM of the total relative coefficient matrix is ​​calculated:

[0064]

[0065] Based on the spatial distribution inverse matrix SDM, the partial correlation probability of engine failure can be calculated as: Similarly, the partial correlation probability P of chassis system failure can be obtained c , partial correlation probability of body system failure P b , partial correlation probability of electrical system fault P d , partial correlation probability of tire system failure P l .

[0066] The vehicle-road collaborative cloud determines the fault location and fault warning level based on the partial correlation coefficient of each vehicle system fault. Taking the engine system as an example: if 0<P e <0.3, it is judged that the current engine system is a level 1 fault warning, and the vehicle-road collaborative cloud sends a level 1 fault warning and disposal plan to the vehicle terminal through the 5G communication unit; 0.3≤P e <0.6, it is judged that the current engine system is in a level 2 fault warning, and the vehicle-road collaborative cloud sends a level 2 fault warning and disposal plan to the vehicle terminal through the 5G communication unit; P e ≥0.6, the engine system is judged to be in the third-level fault warning. The vehicle-road collaborative cloud sends the third-level fault warning and disposal plan to the vehicle terminal through the 5G communication unit. The corresponding level of disposal plan is determined according to the actual operation situation and professional fault assessment experts. The vehicle control center of the vehicle terminal receives the corresponding instructions and plans through the 5G communication unit, and executes the corresponding instructions and plans through the early warning information interaction and execution control module. After a certain time interval, the information collection module collects the operation data information of each vehicle system, and the vehicle-road collaborative cloud updates the vehicle operation data.

[0067] The present invention provides a vehicle fault prediction method based on gray correlation, which uses a vehicle fault prediction model based on gray correlation to calculate the fault correlation factor of the vehicle, and judge whether the vehicle as a whole has a fault risk. In the case of a fault risk, the partial correlation probability of each vehicle system fault is further calculated based on the inverse matrix of the spatial distribution of the relative coefficient of the vehicle system assembly, and the fault position is located and the vehicle fault warning level is judged. The corresponding treatment plan is determined according to the fault warning level, and the fault warning level and the corresponding treatment plan are sent to the vehicle terminal, which fundamentally prevents the occurrence of vehicle faults. The method can accurately locate the vehicle-road fault position, realize the active, intelligent and smart fault diagnosis of networked vehicles, ensure the safety of vehicle operation, significantly reduce traffic accidents and traffic congestion rates caused by vehicle faults, and ensure the stable operation of traffic flow.

[0068] The present invention further provides an embodiment of a computer-readable storage medium, wherein the computer storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the method described in the above embodiment.

[0069] The computer-readable storage medium may be an internal storage unit of the terminal described in the foregoing embodiments, such as a hard disk or memory of the terminal. The computer-readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Further, the computer-readable storage medium may also include both an internal storage unit of the terminal and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by the terminal. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0070] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0071] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the terminals and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0072] In the several embodiments provided in the present application, it should be understood that the disclosed terminal and method can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A networked vehicle fault prediction system based on grey correlation, characterized in that: include: Vehicle terminal, roadside system and vehicle-road collaborative cloud, among which, The vehicle-mounted terminal collects real-time operation data of the vehicle-mounted system, performs denoising and cleaning processing on the real-time operation data, and organizes the data into a vehicle-mounted terminal real-time information data packet in combination with the identity information and location information of the networked vehicle, and sends the real-time information data packet to the roadside system; The roadside system receives real-time information data packets, obtains road conditions and forward traffic conditions information, fuses multi-source heterogeneous road traffic data and generates road traffic information data packets, sends the road traffic information data packets to the vehicle-mounted terminal, and sends the real-time information data packets to the vehicle-road collaboration cloud; The vehicle-road collaboration cloud receives and stores real-time information data packets, performs fault prediction analysis based on the real-time information data packets and a vehicle fault prediction model based on grey correlation, obtains a spatial distribution inverse matrix of the relative coefficient matrix of each vehicle system assembly, calculates the partial correlation probability of faults of each vehicle system based on the spatial distribution inverse matrix, and obtains the vehicle fault location; The vehicle-road collaboration cloud includes a vehicle-road collaboration calculation module, which is used to calculate a single vehicle fault correlation factor under the influence of a single vehicle parameter index according to a real-time information data packet and a vehicle fault prediction model based on grey correlation, calculate the coupling difference between multiple vehicle parameter indexes and their corresponding vehicle standard parameter indexes based on the vehicle fault prediction model to obtain a first value, and calculate the coupling difference between the vehicle parameter index and the vehicle fault parameter index to obtain a second value, calculate the multiple vehicle fault correlation factors under the influence of multiple vehicle parameter indexes according to the single vehicle fault correlation factor, the first value and the second value, judge whether the vehicle-mounted system has a fault risk according to the multiple vehicle fault correlation factors, and if there is a risk, calculate the vehicle parameter index weights of each vehicle-mounted system based on the spatial distribution matrix and determine the key parameter variable set, and calculate the coupling difference between the key parameter variables and the vehicle fault parameter index to obtain a third value, and calculate the spatial distribution inverse matrix of the relative coefficient matrix of each vehicle-mounted system assembly according to the third value; The vehicle-road collaborative calculation module calls data for relevant analysis and calculation. The specific calculation method is as follows: Multi-block analysis data preprocessing, real-time information data blocks of each vehicle terminal e i ={e 1 ,e 2 ,e 3 ,...e n },b i = {b 1 ,b 2 ,b 3 , ...b n },c i ={c 1 , c 2 , c 3 ...c n }, d i ={d 1 , d 2 , d 3 ,...d n }, l i = {l 1 , l 2 , l 3 ,...l n } Perform standard metrology preprocessing to correct for variations related to external factors in the data block; A vehicle fault prediction model based on grey correlation is established, and the single vehicle fault correlation factor σ′ under the influence of single vehicle parameter index is calculated based on the model. The formula is as follows: Among them, 0<λ<1 is the correlation coefficient, which is determined by the operating status of the vehicle system; Calculate the coupling difference between each vehicle parameter index and its corresponding vehicle standard parameter index in, Yes X i The average value of the vehicle parameter index and the vehicle fault parameter index coupling difference are calculated Finally, the multi-vehicle fault correlation factor σ considering the coupling effect of multi-vehicle parameter indicators can be reconstructed as: In the actual operation process, the fault warning coefficient σ is determined according to the actual operation capability of the vehicle system. min ; According to the vehicle fault correlation factor, determine whether the vehicle system has a fault risk. If σ<σ min It is judged that there is no failure risk; if σ>σ min , calculate the partial correlation coefficient of each vehicle system operation index to locate the faulty system; Calculate the vehicle parameter index weights of each vehicle system based on the spatial distribution matrix: Weight of each indicator of engine system: The key parameter variable set is determined by the weight of each indicator of the engine system Similarly, according to the above formula, we can calculate: the weight of each index of chassis system r(c i , c mi ) and key parameter variable sets Weight of each index of the body system r(b i , b mi ) and key parameter variable sets The weight of each indicator of the electrical system r(d i , d mi ) and key parameter variable set r(d i ,d mi ), The weight of each indicator of tire system r(l i , l mi ) and key parameter variable sets Calculate the coupling difference between the engine key parameter variables and the fault parameter indicators: According to the above formula, the spatial distribution inverse matrix SDM of the total relative coefficient matrix is ​​calculated: Based on the spatial distribution inverse matrix SDM, the partial correlation probability of engine failure can be calculated as: Similarly, the partial correlation probability P of chassis system failure can be obtained c , partial correlation probability of body system failure P b , partial correlation probability of electrical system fault P d , partial correlation probability of tire system failure P l ; Determine the fault location and fault warning level according to the partial correlation coefficient of each vehicle system fault. e <0.3, it is judged that the current engine system is in the first level fault warning, 0.3≤P e <0.6, it is judged that the current engine system is in the second level fault warning, P e ≥0.6, it is judged that the current engine system is in the third level fault warning.

2. The system according to claim 1, characterized in that The vehicle-road collaborative cloud also includes a warning level calculation module, which is used to compare the partial correlation probability of each vehicle system with the corresponding fault probability level threshold of each vehicle system, obtain the fault warning level of each vehicle system, and determine the handling plan according to the fault warning level.

3. The system according to claim 2, characterized in that The vehicle-road collaborative cloud also includes a warning information release module, which is used to release fault warning levels and handling plans.

4. A method for predicting faults of connected vehicles based on grey correlation, characterized in that: The following steps are involved: The vehicle terminal collects the real-time operation data of the vehicle system, performs denoising and cleaning processing on the real-time operation data, and organizes the data into a vehicle terminal real-time information data packet in combination with the identity information and location information of the networked vehicle, and sends the real-time information data packet to the roadside system; The roadside system receives real-time information data packets, obtains road conditions and forward traffic conditions, fuses multi-source heterogeneous road traffic data and generates road traffic information data packets, sends the road traffic information data packets to the vehicle-mounted terminal, and sends the real-time information data packets to the vehicle-road collaboration cloud; The vehicle-road collaboration cloud receives and stores real-time information data packets, performs fault prediction analysis based on the real-time information data packets and the vehicle fault prediction model based on grey correlation, obtains the spatial distribution inverse matrix of the relative coefficient matrix of each vehicle system assembly, calculates the partial correlation probability of each vehicle system based on the spatial distribution inverse matrix, and determines the vehicle fault location based on the partial correlation probability of each vehicle system; The specific method of performing fault prediction analysis based on the real-time information data packet and the vehicle fault prediction model based on grey correlation degree includes: Multi-block analysis data preprocessing, real-time information data blocks of each vehicle terminal e i ={e 1 ,e 2 ,e 3 ,...e n },b i = {b 1 ,b 2 ,b 3 , ...b n },c i ={c 1 ,c 2 ,c 3 , ...c n },d i ={d 1 ,d 2 , d 3 ...d n }, l i = {l 1 , l 2 , l 3 ,...l n } Perform standard metrology preprocessing to correct for variations related to external factors in the data block; A vehicle fault prediction model based on grey correlation is established, and the single vehicle fault correlation factor σ′ under the influence of single vehicle parameter index is calculated based on the model. The formula is as follows: Among them, 0<λ<1 is the correlation coefficient, which is determined by the operating status of the vehicle system; Calculate the coupling difference between each vehicle parameter index and its corresponding vehicle standard parameter index in, Yes X i The average value of the vehicle parameter index and the vehicle fault parameter index coupling difference are calculated Finally, the multi-vehicle fault correlation factor σ considering the coupling effect of multi-vehicle parameter indicators can be reconstructed as: In the actual operation process, the fault warning coefficient σ is determined according to the actual operation capability of the vehicle system. min ; According to the vehicle fault correlation factor, determine whether the vehicle system has a fault risk. If σ<σ min It is judged that there is no risk of failure; if σ>σ min , calculate the partial correlation coefficient of each vehicle system operation index to locate the faulty system; Calculate the vehicle parameter index weights of each vehicle system based on the spatial distribution matrix: Weight of each indicator of engine system: The key parameter variable set is determined by the weight of each indicator of the engine system Similarly, the weights of various indicators of the chassis system are calculated according to the above formula r(c i , c mi ) and key parameter variable sets Weight of each index of the body system r(b i , b mi ) and key parameter variable sets The weight of each indicator of the electrical system r(d i , d mi ) and key parameter variable set r(d i , d mi ) The weight of each indicator of tire system r(l i , l mi ) and key parameter variable sets Calculate the coupling difference between the engine key parameter variables and the fault parameter indicators: According to the above formula, the spatial distribution inverse matrix SDM of the total relative coefficient matrix is ​​calculated: Based on the spatial distribution inverse matrix SDM, the partial correlation probability of engine failure can be calculated as: Similarly, the partial correlation probability P of chassis system failure can be obtained c , partial correlation probability of body system failure P b , partial correlation probability of electrical system fault P d , partial correlation probability of tire system failure P l ; Determine the fault location and fault warning level according to the partial correlation coefficient of each vehicle system fault. e <0.3, it is judged that the current engine system is in the first level fault warning, 0.3≤P e <0.6, it is judged that the current engine system is in the second level fault warning, P e ≥0.6, it is judged that the current engine system is in the third level fault warning.

5. A method for predicting faults of connected vehicles based on grey correlation, applicable to vehicle-road collaborative cloud, characterized in that: The method comprises the following steps: Receive and store real-time information packets; According to the real-time information data packet and the vehicle fault prediction model based on grey correlation, the fault prediction analysis is carried out to obtain the spatial distribution inverse matrix of the relative coefficient matrix of each vehicle system assembly; The partial correlation probability of the fault of each vehicle system is calculated based on the inverse matrix of the spatial distribution, and the vehicle fault location is determined according to the partial correlation probability of each vehicle system; The specific method of performing fault prediction analysis based on the real-time information data packet and the vehicle fault prediction model based on grey correlation degree includes: Multi-block analysis data preprocessing, real-time information data blocks of each vehicle terminal e i ={e 1 ,e 2 ,e 3 ,...e n },b i = {b 1 ,b 2 ,b 3 , ...b n },c i ={c 1 ,c 2 , c 3 , ...c n },d i ={d 1 ,d 2 ,d 3 ,...d n }, l i = {l 1 , l 2 , l 3 ,...l n } Perform standard metrology preprocessing to correct for variations related to external factors in the data block; A vehicle fault prediction model based on grey correlation is established, and the single vehicle fault correlation factor σ′ under the influence of single vehicle parameter index is calculated based on the model. The formula is as follows: Among them, 0<λ<1 is the correlation coefficient, which is determined by the operating status of the vehicle system; Calculate the coupling difference between each vehicle parameter index and its corresponding vehicle standard parameter index in, Yes X i The average value of the vehicle parameter index and the vehicle fault parameter index coupling difference are calculated Finally, the multi-vehicle fault correlation factor σ considering the coupling effect of multi-vehicle parameter indicators can be reconstructed as: In the actual operation process, the fault warning coefficient σ is determined according to the actual operation capability of the vehicle system. min ; According to the vehicle fault correlation factor, determine whether the vehicle system has a fault risk. If σ<σ min It is judged that there is no risk of failure; if σ>σ min , calculate the partial correlation coefficient of each vehicle system operation index to locate the faulty system; Calculate the vehicle parameter index weights of each vehicle system based on the spatial distribution matrix: Weight of each indicator of engine system: The key parameter variable set is determined by the weight of each indicator of the engine system Similarly, the weights of various indicators of the chassis system are calculated according to the above formula r(c i , c mi ) and key parameter variable sets Weight of each index of the body system r(b i , b mi ) and key parameter variable sets The weight of each indicator of the electrical system r(d i , d mi ) and key parameter variable set r(d i , d mi ), The weight of each indicator of tire system r(l i , l mi ) and key parameter variable sets Calculate the coupling difference between the engine key parameter variables and the fault parameter indicators: According to the above formula, the spatial distribution inverse matrix SDM of the total relative coefficient matrix is ​​calculated: Based on the spatial distribution inverse matrix SDM, the partial correlation probability of engine failure can be calculated as: Similarly, the partial correlation probability P of chassis system failure can be obtained c , partial correlation probability of body system failure P b , partial correlation probability of electrical system fault P d , partial correlation probability of tire system failure P l ; Determine the fault location and fault warning level according to the partial correlation coefficient of each vehicle system fault. <P e <0.3, it is judged that the current engine system is in the first level fault warning, 0.3≤P e <0.6, it is judged that the current engine system is in the second level fault warning, P e ≥0.6, it is judged that the current engine system is in the third level fault warning.

6. A computer-readable storage medium, characterized in that: The computer storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor, the processor is caused to perform the method according to claim 5.

Images