Vehicle condition detection method and system based on artificial intelligence

Abstract

The invention belongs to the technical field of vehicle detection, and particularly relates to a vehicle condition detection method and system based on artificial intelligence, and the system comprises a vehicle-mounted sensor integration module, a vehicle data processing and analysis module, an intelligent diagnosis module, a fault abnormity output module, a vehicle condition evaluation module and a user terminal. According to the invention, various operation data of the vehicle are collected, data processing and mining analysis are carried out, the vehicle fault is identified based on the processing and analysis information of the vehicle, and the vehicle owner is reminded to carry out fault maintenance processing when the vehicle fault is identified, so that comprehensive monitoring and effective supervision of the vehicle are realized, and the driving safety of the vehicle is ensured. And the vehicle condition evaluation score of the corresponding vehicle is obtained by comprehensively evaluating and analyzing the vehicle condition, so that a vehicle owner user can intuitively master the vehicle condition of the corresponding vehicle and formulate corresponding maintenance measures and driving measures based on the vehicle condition, the driving safety of the user is further ensured, and the vehicle management difficulty is remarkably reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle detection, and in particular to a vehicle condition detection method and system based on artificial intelligence. Background Art

[0002] With the rapid development of the automotive industry, the number of vehicles has increased dramatically, and vehicle maintenance and management have become a major challenge. A Chinese invention patent with publication number CN107264446A discloses a vehicle condition safety detection system during operation. The system, which primarily consists of a temperature sensor, a pressure sensor, a sway sensor, a torque sensor, a wind pressure sensor, and a control circuit, can effectively and continuously detect the vehicle's operating status without changing the vehicle's structure, facilitating the timely and effective detection of safety hazards in vehicle operation.

[0003] However, in actual use, the above-mentioned technical solution only realizes the monitoring and fault identification of the vehicle operation process, and cannot combine vehicle fault identification with vehicle condition detection and comprehensive evaluation to ensure vehicle safety. It is not conducive to the owner to formulate corresponding maintenance measures and driving measures based on the vehicle condition, and it is difficult to effectively reduce the difficulty of vehicle management and the risk of user driving. The degree of intelligence is low.

[0004] In view of the above technical defects, a solution is now proposed. Summary of the Invention

[0005] The purpose of the present invention is to provide a vehicle condition detection method and system based on artificial intelligence, which solves the problem that the existing technology is unable to combine vehicle fault identification with vehicle condition detection and comprehensive evaluation to ensure the safety of vehicle use, is not conducive to vehicle owners to formulate corresponding maintenance measures and driving measures based on the vehicle condition, and is difficult to effectively reduce the difficulty of vehicle management and user driving risks.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An artificial intelligence-based vehicle condition detection system includes an on-board sensor integration module, a vehicle data processing and analysis module, an intelligent diagnosis module, a fault and abnormality output module, a vehicle condition assessment module, and a user terminal. The on-board sensor integration module monitors the vehicle by integrating several sensors, collects various vehicle operating data in real time based on the on-board sensor network, and sends the various vehicle operating data to the vehicle data processing and analysis module.

[0008] The vehicle data processing and analysis module cleans, formats, and normalizes the collected data, uses a big data processing framework to perform in-depth mining on the pre-processed data, and sends the processed and analyzed information to the intelligent diagnosis module;

[0009] The intelligent diagnosis module builds a vehicle fault diagnosis model based on machine learning and deep learning technologies. The vehicle fault diagnosis model identifies vehicle faults based on vehicle processing and analysis information. When a vehicle fault is identified, it is sent to the vehicle condition assessment module and the user terminal through the fault abnormality output module; the user terminal issues an early warning to remind the owner to repair the fault, and the vehicle condition assessment module conducts a comprehensive assessment and analysis of the vehicle condition, generates a vehicle condition assessment score for the corresponding vehicle through analysis, and sends the vehicle condition assessment score to the user terminal for display.

[0010] Furthermore, the specific analysis process of the vehicle condition assessment module includes:

[0011] Obtain the vehicle's production date, mark the time interval between the production date and the current date as the vehicle production value, and obtain the vehicle's mileage and mark it as the vehicle mileage value; perform vehicle component attenuation analysis to obtain the component attenuation value of each vehicle component, compare the component attenuation value with the corresponding preset component attenuation threshold, and if the component attenuation value exceeds the corresponding preset component attenuation threshold, mark the target component i as a high attenuation component;

[0012] Obtain the percentage of high-attenuation components in the corresponding vehicle and mark it as a high-attenuation percentage value, calculate the ratio of the component attenuation value of the target component i to the corresponding preset component attenuation threshold to obtain an attenuation analysis value, and calculate the average of the attenuation analysis values ​​of all vehicle components that need to be monitored in the corresponding vehicle to obtain a vehicle decay value;

[0013] A vehicle impact value of the corresponding vehicle is obtained, and a vehicle condition analysis value is obtained by numerically calculating the vehicle impact value, vehicle production value, vehicle mileage value, high attenuation table value and vehicle decay value. Several groups of preset vehicle condition analysis value ranges are set in advance, and each group of preset vehicle condition analysis value ranges corresponds to a group of vehicle condition assessment scores. The vehicle condition analysis value is compared with all preset vehicle condition analysis value ranges one by one, and the preset vehicle condition analysis value range containing the corresponding vehicle condition analysis value is marked as a vehicle consistent range, and the vehicle condition assessment score corresponding to the vehicle consistent range is marked as the vehicle condition assessment score of the corresponding vehicle.

[0014] Furthermore, the specific analysis process of vehicle component attenuation analysis is as follows:

[0015] The components that need to be supervised in the corresponding vehicle are obtained, and the corresponding components are marked as target components i, where i is a natural number greater than 1; the usage time of the target component i is obtained and marked as the component usage value, and the number of faults involved in the target component i in the historical stage is obtained and marked as the fault matching value, and the total time that the target component i is in an unsuitable operating condition in the historical stage is obtained and marked as the unsuitable operating condition value, and the component attenuation value of the target component i is obtained by numerically calculating the component usage value, the fault matching value and the unsuitable operating condition value.

[0016] Furthermore, the specific analysis and judgment process of the unsuitable operating condition is as follows:

[0017] Obtain the corresponding operating parameters and environmental parameters of the environment that need to be monitored for the target component i, and compare each operating parameter and environmental parameter with the corresponding preset data requirements one by one. If there are operating parameters or environmental parameters that do not meet the corresponding preset data requirements, it is judged that the target component i is in an unsuitable operating state.

[0018] Furthermore, the vehicle condition assessment module is communicatively connected to the driving caution judgment module. The vehicle condition assessment module sends the vehicle condition assessment points of the corresponding vehicle to the driving caution judgment module. The driving caution judgment module generates a high-caution driving signal or a low-caution driving signal through caution judgment analysis, and sends the high-caution driving signal or the low-caution driving signal to the user terminal. When the user terminal receives the high-caution driving signal, it issues a corresponding warning.

[0019] Furthermore, the specific analysis process of the prudence judgment analysis is as follows:

[0020] Receive a vehicle condition assessment score of the corresponding vehicle, compare the vehicle condition assessment score with a preset vehicle condition assessment score threshold, and generate a high-caution driving signal if the vehicle condition assessment score does not exceed the preset vehicle condition assessment score threshold;

[0021] If the vehicle condition assessment score exceeds the preset vehicle condition assessment score threshold, a detection period is set, all faults that occur in the corresponding vehicle during the detection period are obtained, the number of faults occurring is marked as the fault occurrence value, and the fault occurrence value is numerically compared with the preset fault occurrence threshold. If the fault occurrence value exceeds the preset fault occurrence threshold, a high-caution driving signal is generated.

[0022] Furthermore, if the fault occurrence value does not exceed the preset fault occurrence threshold, all faults occurring in the corresponding vehicle during the detection period are classified, and the number of occurrences of the corresponding type of vehicle fault is marked as the vehicle obstacle value. A set of preset weight values ​​is set in advance for each type of vehicle fault, and the product of the vehicle obstacle value of the corresponding type of vehicle fault and the corresponding preset weight value is marked as the vehicle obstacle value;

[0023] The vehicle obstacle values ​​of all types of vehicle failures occurring in the corresponding vehicle during the detection period are obtained and summed up to obtain a prudence judgment coefficient, and the prudence judgment coefficient is numerically compared with a preset prudence judgment coefficient threshold. If the prudence judgment coefficient exceeds the preset prudence judgment coefficient threshold, a high-prudent driving signal is generated; if the prudence judgment coefficient does not exceed the preset prudence judgment coefficient threshold, a low-prudent driving signal is generated.

[0024] Furthermore, the vehicle condition assessment module is communicatively connected to the vehicle collision detection module. The vehicle collision detection module analyzes the collision damage condition of the corresponding vehicle in the historical stage, obtains the vehicle collision value of the corresponding vehicle through analysis, and sends the vehicle collision value of the corresponding vehicle to the vehicle condition assessment module.

[0025] Furthermore, the specific analysis process of the vehicle collision detection module is as follows:

[0026] The number of collisions that occurred with the corresponding vehicle in the historical period is obtained and marked as the vehicle collision frequency value. When the vehicle collision occurs, the duration of the collision process, the average collision force, and the maximum collision force are collected and marked as the collision duration value, the collision force table value, and the collision force amplitude value, respectively. The collision retrospective value is obtained by numerically calculating the collision duration value, the collision force table value, and the collision force amplitude value.

[0027] The collision tracing value is numerically compared with the preset collision tracing threshold. If the collision tracing value exceeds the preset collision tracing threshold, the corresponding vehicle collision process is marked as a high-damage collision process; the number of occurrences of high-damage collision processes corresponding to the corresponding vehicle in the historical stage is obtained to mark the vehicle damage frequency value, and the average of all collision tracing values ​​corresponding to the corresponding vehicle in the historical stage is calculated to obtain the vehicle collision table value; the vehicle collision value is obtained by numerically calculating the vehicle collision frequency value, vehicle damage frequency value and vehicle collision table value.

[0028] Furthermore, the present invention also proposes a vehicle condition detection method based on artificial intelligence, comprising the following steps:

[0029] Step 1: Collect various operating data of the vehicle in real time based on the vehicle-mounted sensor network;

[0030] Step 2: Clean, format and normalize the collected data, and use the big data processing framework to conduct in-depth mining on the pre-processed data;

[0031] Step 3: Using a vehicle fault diagnosis model to analyze information based on the vehicle's processing to identify a vehicle fault, and notifying the vehicle owner when a vehicle fault is identified;

[0032] Step 4: Perform a comprehensive evaluation and analysis on the vehicle condition to generate a vehicle condition evaluation score for the corresponding vehicle, and send the vehicle condition evaluation score for the corresponding vehicle to the user terminal for display.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] 1. The present invention collects various operating data of vehicles and performs data processing and mining analysis. Based on the processed and analyzed information, vehicle faults are identified. When a vehicle fault is identified, the owner is reminded to perform repairs, thereby achieving comprehensive monitoring and effective supervision of the vehicle. Furthermore, by comprehensively evaluating and analyzing the vehicle condition to obtain a vehicle condition assessment score, the owner is facilitated to formulate appropriate maintenance and driving measures, ensuring the user's driving safety and significantly reducing the difficulty of vehicle management.

[0035] 2. In the present invention, the vehicle condition assessment module transmits the vehicle condition assessment of the corresponding vehicle to the driving caution judgment module. The driving caution judgment module generates a high-caution driving signal or a low-caution driving signal through caution judgment analysis. When the high-caution driving signal is generated, the vehicle owner is reminded to drive cautiously and strengthen the maintenance management of the corresponding vehicle, further reducing the driving risk of the vehicle owner, and having a high degree of intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings;

[0037] Figure 1 This is a system block diagram of Embodiment 1 and Embodiment 2 of the present invention;

[0038] Figure 2 This is a system block diagram of Embodiment 3 of the present invention;

[0039] Figure 3 This is a flow chart of the method of embodiment 4 of the present invention. DETAILED DESCRIPTION

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments 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 making creative efforts are within the scope of protection of the present invention.

[0041] Example 1: Figure 1As shown, the present invention proposes an artificial intelligence-based vehicle condition detection system, which includes an on-board sensor integration module, a vehicle data processing and analysis module, an intelligent diagnosis module, a fault and abnormality output module, a vehicle condition assessment module and a user terminal; the on-board sensor integration module monitors the vehicle by integrating several sensors, and collects various operating data of the vehicle in real time based on the on-board sensor network, including but not limited to engine status, fuel consumption, emission data, tire pressure, brake system status and other data, and sends the various operating data of the vehicle to the vehicle data processing and analysis module; the vehicle data processing and analysis module cleans, formats and normalizes the collected data, removes noise data, improves data quality, and provides a reliable basis for subsequent analysis, and uses a big data processing framework to perform in-depth mining and analysis on the pre-processed data, and sends the processed and analyzed information to the intelligent diagnosis module.

[0042] The intelligent diagnosis module builds a vehicle fault diagnosis model based on machine learning and deep learning technologies. The vehicle fault diagnosis model identifies vehicle faults based on vehicle processing and analysis information. When a vehicle fault is identified, the fault cause is analyzed and repair suggestions are provided. The identified fault information is sent to the vehicle condition assessment module and the user terminal through the fault abnormality output module. The user terminal issues an early warning to remind the owner to perform fault repairs, which is conducive to avoiding accidents for car owners and users, realizing comprehensive monitoring and effective supervision of vehicles, and ensuring vehicle driving safety.

[0043] The vehicle condition assessment module comprehensively evaluates and analyzes the vehicle's condition, generates a vehicle condition assessment score, and sends the score to the user terminal for display. This helps the owner intuitively understand the vehicle's condition and formulate appropriate maintenance and driving measures based on the vehicle's condition to ensure the user's driving safety. The specific analysis process of the vehicle condition assessment module is as follows:

[0044] Vehicle component attenuation analysis is used to obtain the component attenuation value of each vehicle component. Specifically, the components that need to be monitored in the corresponding vehicle (including key components such as the vehicle's engine, battery, and brake system) are obtained and marked as target component i, where i is a natural number greater than 1; the usage time of target component i is obtained and marked as the component usage value, and the number of faults involved in the target component i in the historical stage is marked as the fault matching value;

[0045] Obtain the corresponding operating parameters that need to be monitored for target component i (for example, for a vehicle battery, monitor the vibration amplitude, voltage, current and other operating parameters of the vehicle battery) and the environmental parameters of the environment in which it is located (for example, the temperature, humidity and other environmental parameters of the environment in which the corresponding component is located). Compare each operating parameter and environmental parameter with the corresponding preset data requirements one by one. If there are operating parameters or environmental parameters that do not meet the corresponding preset data requirements, indicating that the target component i is currently prone to damage, the target component i is judged to be in an unsuitable operating condition state. Obtain the total length of time that the target component i has been in the unsuitable operating condition state in the historical stage and mark it as an unsuitable operating condition value.

[0046] By formula The component attenuation value XLi of the target component i is obtained by numerically calculating the component usage value SYi, the fault matching value ZWi, and the operating condition non-fitness value NPi; wherein ey, kp, and hu are preset weight coefficients, hu>kp>ey>0; and the larger the value of the component attenuation value XLi, the worse the overall component condition of the target component i;

[0047] Compare the component attenuation value XLi with the corresponding preset component attenuation threshold. If the component attenuation value XLi exceeds the corresponding preset component attenuation threshold, it indicates that the component condition of the target component i is generally poor and the performance of the target component i is severely attenuated. Then, the target component i is marked as a high-attenuation component.

[0048] The number ratio of high-attenuation components in the corresponding vehicle is obtained and marked as a high-attenuation ratio, and the component attenuation value XLi of the target component i is calculated by ratio with the corresponding preset component attenuation threshold to obtain an attenuation analysis value, and the attenuation analysis values ​​of all vehicle components that need to be monitored in the corresponding vehicle are averaged to obtain a vehicle decay value;

[0049] Obtain the vehicle's production date, mark the time interval between the production date and the current date as the vehicle production value, obtain the vehicle's mileage and mark it as the vehicle mileage value, and obtain the vehicle impact value of the corresponding vehicle;

[0050] By formula The vehicle impact value QF, the vehicle production value HP, the vehicle mileage value ZS, the high attenuation table value TM, and the vehicle decay value FX are numerically calculated to obtain a vehicle condition analysis value WP; wherein q1, q2, q3, q4, and q5 are preset weight coefficients with values ​​greater than zero, and the larger the value of the vehicle condition analysis value WP, the worse the overall vehicle condition of the corresponding vehicle;

[0051] Several groups of preset vehicle condition analysis value ranges are set in advance, and each group of preset vehicle condition analysis value ranges corresponds to a group of vehicle condition assessment scores. It should be noted that the larger the value of the preset vehicle condition analysis value range, the smaller the value of the vehicle condition assessment score corresponding to it, and the worse the vehicle condition of the corresponding vehicle. The vehicle condition analysis value WP is compared with all the preset vehicle condition analysis value ranges one by one, and the preset vehicle condition analysis value range containing the corresponding vehicle condition analysis value WP is marked as the vehicle consistent range, and the vehicle condition assessment score corresponding to the vehicle consistent range is marked as the vehicle condition assessment score of the corresponding vehicle.

[0052] Example 2: Figure 1 As shown, the difference between this embodiment and the first embodiment is that the vehicle condition assessment module is communicatively connected to the vehicle collision detection module. The vehicle collision detection module analyzes the collision damage of the corresponding vehicle in the historical stage, obtains the vehicle collision value QF of the corresponding vehicle through analysis, and sends the vehicle collision value QF of the corresponding vehicle to the vehicle condition assessment module. This can reasonably analyze and accurately assess the collision damage of the corresponding vehicle in the historical stage, and provide data support for the analysis process of the vehicle condition assessment module to ensure the accuracy of its analysis results. The specific analysis process of the vehicle collision detection module is as follows:

[0053] The number of collisions that occurred with the corresponding vehicle in the historical period is obtained and marked as the vehicle collision frequency value. When the vehicle collision occurs, the duration of the collision process, the average collision force, and the maximum collision force are collected and marked as the collision duration value, collision force value, and collision force amplitude value respectively;

[0054] By formula The impact duration value TW, the impact force table value QL, and the impact force amplitude HN are numerically calculated to obtain the impact retrospective value GY; wherein up, ng, and ry are preset weight coefficients with values ​​greater than zero, and the larger the impact retrospective value GY, the more serious the damage to the corresponding vehicle during the corresponding impact process;

[0055] Compare the collision tracing value GY with the preset collision tracing threshold. If the collision tracing value GY exceeds the preset collision tracing threshold, indicating that the damage suffered by the corresponding vehicle in the corresponding collision process is relatively serious, the corresponding vehicle collision process is marked as a high-damage collision process. Obtain the number of occurrences of the high-damage collision process corresponding to the corresponding vehicle in the historical stage to mark the vehicle damage frequency value, and calculate the average of all collision tracing values ​​corresponding to the corresponding vehicle in the historical stage to obtain the vehicle collision table value.

[0056] By formula The vehicle collision frequency value SL, the vehicle damage frequency value YP and the vehicle collision table value ZX are numerically calculated to obtain the vehicle impact value QF; wherein wq, te, and mu are preset weight coefficients whose values ​​are greater than zero, and the larger the value of the vehicle impact value QF, the more serious the damage suffered by the corresponding vehicle due to the collision in the historical stage.

[0057] Example 3: Figure 2 As shown, the difference between this embodiment and the first and second embodiments is that the vehicle condition assessment module is communicatively connected to the driving caution determination module. The vehicle condition assessment module sends the vehicle condition assessment of the corresponding vehicle to the driving caution determination module, and the driving caution determination module generates a high-caution driving signal or a low-caution driving signal through caution determination analysis.

[0058] A high-caution driving signal or a low-caution driving signal is sent to the user terminal. When the user terminal receives the high-caution driving signal, it issues a corresponding warning to remind the car owner to drive carefully and strengthen the maintenance management of the corresponding vehicle, which is conducive to reducing the driving risk of the car owner. The specific analysis process of the caution judgment analysis is as follows:

[0059] Receive the vehicle condition assessment score of the corresponding vehicle, compare the vehicle condition assessment score with a preset vehicle condition assessment score threshold, and generate a high-caution driving signal if the vehicle condition assessment score does not exceed the preset vehicle condition assessment score threshold, indicating that the vehicle condition of the corresponding vehicle is poor and the driving risk is high;

[0060] If the vehicle condition assessment score exceeds the preset vehicle condition assessment score threshold, indicating that the vehicle condition of the corresponding vehicle is good, a detection period is set. Preferably, the detection period is thirty days. All faults that occur to the corresponding vehicle during the detection period are obtained, and the number of faults is marked as a fault occurrence value. The fault occurrence value is numerically compared with the preset fault occurrence threshold. If the fault occurrence value exceeds the preset fault occurrence threshold, indicating that the corresponding vehicle frequently fails during the detection period and the driving risk is high, a high-caution driving signal is generated.

[0061] Furthermore, if the fault occurrence value does not exceed the preset fault occurrence threshold, all faults occurring in the corresponding vehicle during the detection period are classified, and the number of occurrences of the corresponding type of vehicle fault is marked as the vehicle fault type value. A set of preset weight values ​​greater than zero is set in advance for each type of vehicle fault. The higher the safety risk brought by the corresponding type of vehicle fault, the greater the value of the preset weight value corresponding to it.

[0062] The product of the vehicle obstacle value of the corresponding type of vehicle failure and the corresponding preset weight value is marked as the vehicle obstacle value, the vehicle obstacle value of all types of vehicle failures occurring in the corresponding vehicle during the detection period is obtained and summed up to obtain the prudence judgment coefficient, and the prudence judgment coefficient is numerically compared with the preset prudence judgment coefficient threshold. If the prudence judgment coefficient exceeds the preset prudence judgment coefficient threshold, it indicates that the driving risk of the corresponding vehicle during the detection period is high, and a high-prudent driving signal is generated; if the prudence judgment coefficient does not exceed the preset prudence judgment coefficient threshold, it indicates that the driving risk of the corresponding vehicle during the detection period is low, and a low-prudent driving signal is generated.

[0063] Example 4: Figure 3 As shown, the difference between this embodiment and the first, second and third embodiments is that the present invention proposes a vehicle condition detection method based on artificial intelligence, comprising the following steps:

[0064] Step 1: Collect various operating data of the vehicle in real time based on the vehicle-mounted sensor network;

[0065] Step 2: Clean, format and normalize the collected data, and use the big data processing framework to conduct in-depth mining on the pre-processed data;

[0066] Step 3: Using a vehicle fault diagnosis model to analyze information based on the vehicle's processing to identify a vehicle fault, and notifying the vehicle owner when a vehicle fault is identified;

[0067] Step 4: Perform a comprehensive evaluation and analysis on the vehicle condition to generate a vehicle condition evaluation score for the corresponding vehicle, and send the vehicle condition evaluation score for the corresponding vehicle to the user terminal for display.

[0068] The working principle of the present invention is as follows: when in use, the vehicle-mounted sensor integration module collects various operating data of the vehicle in real time based on the vehicle-mounted sensor network, the vehicle data processing and analysis module processes and mines the collected data, the vehicle fault diagnosis model identifies vehicle faults based on the vehicle's processing and analysis information, analyzes the cause of the fault when the vehicle fault is identified and provides maintenance suggestions, the fault abnormality output module sends the fault information to the user terminal to remind the owner to perform fault repair processing, which is beneficial to avoid accidents for the owner user, realize comprehensive monitoring and effective supervision of the vehicle, and ensure vehicle driving safety, and the vehicle condition assessment module conducts a comprehensive assessment and analysis of the vehicle condition to obtain the corresponding vehicle condition assessment score, which is beneficial for the owner user to intuitively grasp the corresponding vehicle condition and formulate corresponding maintenance measures and driving measures based on the vehicle condition, ensure the user's driving safety, and significantly reduce the difficulty of vehicle management.

[0069] The above formulas are all dimensionless and calculated by taking their numerical values. The formula is a formula for the latest real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions. The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made based on the contents of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that technicians in the relevant technical field can well understand and use the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A vehicle condition detection system based on artificial intelligence, characterized in that: It includes an on-board sensor integration module, a vehicle data processing and analysis module, an intelligent diagnosis module, a fault and abnormality output module, a vehicle condition assessment module and a user terminal; the on-board sensor integration module monitors the vehicle by integrating several sensors, and collects various operating data of the vehicle in real time based on the on-board sensor network; the vehicle data processing and analysis module cleans, formats and normalizes the collected data, and uses a big data processing framework to conduct in-depth mining of the pre-processed data; The intelligent diagnosis module identifies vehicle faults through the vehicle fault diagnosis model based on the vehicle's processing and analysis information, and when a vehicle fault is identified, it is sent to the vehicle condition assessment module and the user terminal through the fault abnormality output module; the user terminal issues an early warning to remind the owner to perform fault repair processing, and the vehicle condition assessment module conducts a comprehensive assessment and analysis of the vehicle condition, generates a vehicle condition assessment score for the corresponding vehicle through analysis, and sends the vehicle condition assessment score to the user terminal for display.

2. The vehicle condition detection system based on artificial intelligence according to claim 1 is characterized in that: The specific analysis process of the vehicle condition assessment module includes: The attenuation value of each vehicle component is obtained through vehicle component attenuation analysis. If the component attenuation value exceeds the corresponding preset component attenuation threshold, the target component i is marked as a high attenuation component. The vehicle condition analysis value is obtained by numerically calculating the vehicle impact value, vehicle production value, vehicle mileage value, high attenuation table value and vehicle decay value, and the preset vehicle condition analysis value range containing the corresponding vehicle condition analysis value is marked as the vehicle consistency range, and the vehicle condition assessment score corresponding to the vehicle consistency range is marked as the vehicle condition assessment score of the corresponding vehicle.

3. The vehicle condition detection system based on artificial intelligence according to claim 2 is characterized in that: The specific analysis process of vehicle component attenuation analysis is as follows: The components that need to be supervised in the corresponding vehicle are obtained, and the corresponding components are marked as target components i, where i is a natural number greater than 1; the component attenuation value of the target component i is obtained by numerically calculating the component usage time value, fault matching value and operating condition unsuitability value.

4. The vehicle condition detection system based on artificial intelligence according to claim 3 is characterized in that: The specific analysis and judgment process of the unsuitable operating condition is as follows: The corresponding operating parameters and environmental parameters of the environment in which the target component i needs to be monitored are obtained. If there are operating parameters or environmental parameters that do not meet the corresponding preset data requirements, it is determined that the target component i is in an unsuitable operating condition.

5. The vehicle condition detection system based on artificial intelligence according to claim 1 is characterized in that: The vehicle condition assessment module is communicatively connected to the driving caution judgment module. The vehicle condition assessment module sends the vehicle condition assessment points of the corresponding vehicle to the driving caution judgment module. The driving caution judgment module generates a high-caution driving signal or a low-caution driving signal through caution judgment analysis, and sends the high-caution driving signal or the low-caution driving signal to the user terminal.

6. The vehicle condition detection system based on artificial intelligence according to claim 5 is characterized in that: The specific analysis process of the prudence judgment analysis is as follows: If the vehicle condition assessment score does not exceed the preset vehicle condition assessment score threshold, a high-caution driving signal is generated; if the vehicle condition assessment score exceeds the preset vehicle condition assessment score threshold, a detection period is set to obtain all faults that occur to the corresponding vehicle during the detection period. If the fault occurrence value exceeds the preset fault occurrence threshold, a high-caution driving signal is generated.

7. The vehicle condition detection system based on artificial intelligence according to claim 6 is characterized in that: If the fault occurrence value does not exceed the preset fault occurrence threshold, all faults occurring in the corresponding vehicle during the detection period will be classified, and the vehicle obstacle values ​​of all types of vehicle faults occurring in the corresponding vehicle during the detection period will be summed up to obtain the prudence judgment coefficient. If the prudence judgment coefficient exceeds the preset prudence judgment coefficient threshold, a high-prudent driving signal will be generated; otherwise, a low-prudent driving signal will be generated.

8. The vehicle condition detection system based on artificial intelligence according to claim 2 is characterized in that: The vehicle condition assessment module is communicatively connected to the vehicle collision detection module. The vehicle collision detection module analyzes the collision damage condition of the corresponding vehicle in the historical stage, obtains the vehicle collision value of the corresponding vehicle through the analysis, and sends the vehicle collision value of the corresponding vehicle to the vehicle condition assessment module.

9. The vehicle condition detection system based on artificial intelligence according to claim 8 is characterized in that: The specific analysis process of the vehicle collision detection module is as follows: The number of collisions of the corresponding vehicle in the historical stage and the number of high-damage collision processes are obtained and marked as the vehicle collision frequency value and the vehicle damage frequency value respectively, and the vehicle collision table value is obtained by averaging all collision tracing values ​​corresponding to the corresponding vehicle in the historical stage; the vehicle collision value is obtained by numerically calculating the vehicle collision frequency value, the vehicle damage frequency value and the vehicle collision table value.

10. A vehicle condition detection method based on artificial intelligence, characterized in that: The method adopts the vehicle condition detection system based on artificial intelligence as described in any one of claims 1-9.

Images