Vehicle health monitoring and maintenance management system based on AI intelligent prediction

Abstract

The invention discloses a vehicle health monitoring and maintenance management system based on AI intelligent prediction, and relates to the technical field of vehicle data monitoring. The vehicle health monitoring and maintenance management system based on AI intelligent prediction comprises a data collection module, a data processing module, a braking habit evaluation module and a data analysis module. The data collection module is used for acquiring a brake transmission data set and a brake life prediction data set; the data processing module is used for normalizing the brake transmission data set and the brake life prediction data set to obtain a pedal transmission prediction value; the braking habit evaluation module is used for analyzing the braking habit of the driver, carrying out intelligent adjustment based on an analysis result, and sending out a warning for the braking habit of the driver at the same time; and a data analysis module. By calculating the predicted value of the service life of the brake disc, the problems that waste is caused by early replacement of the brake disc and driving safety is affected by too late replacement are solved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle data monitoring technology, and specifically to a vehicle health monitoring and maintenance management system based on AI intelligent prediction. Background Art

[0002] With the rapid development of science and technology, new energy vehicles and autonomous driving technologies have gradually matured. However, no matter how vehicles develop, one key issue remains: safety. If there were a way to promptly detect vehicle health issues, many accidents could be avoided. Vehicle health monitoring technology is a relevant technology. As a core component for ensuring driving safety, the performance of a vehicle's braking system directly determines the vehicle's safety, making it particularly important.

[0003] For example, a Chinese patent with publication number CN117454085A discloses a method and system for online vehicle monitoring. The method decomposes a data sequence to obtain data components; obtains a correlation coefficient based on the difference characteristics between the data sequence and the data components; obtains a denoising component and a retained component based on the difference characteristics of the correlation coefficient; obtains an adaptive filtering window based on the distribution characteristics of the data points in the denoising component; obtains a filtering weight based on the difference characteristics of the data points in the adaptive filtering window; obtains a filtering value based on the filtering weight and the corresponding data point; obtains a denoising effect index based on the difference characteristics between the filtering value and the denoising component; and obtains a denoising final component based on the denoising effect index. The present invention obtains a denoising signal based on the retained component and the denoising final component, thereby improving the denoising effect and ensuring the accuracy of monitoring the vehicle status.

[0004] For example, a Chinese patent with publication number CN117194901A, a method and system for monitoring the working status of an unmanned vehicle, iteratively screens out the residual amplitude that does not have Gaussianity, designs a vibration element based on the maximum and minimum residual amplitudes of the screened residual amplitudes, and convolves the first original signal to obtain the second original signal. The upper and lower envelopes of the second original signal are then segmented and matched, and the symmetry and maximum amplitude difference of the matching signal segments are calculated. Then, based on the correlation between the two, the estimated residual noise intensity is obtained, and a Gaussian filter of the same intensity is generated. The component signals after LMD decomposition of the second original signal are smoothed to filter out deep noise. The present invention effectively improves the accuracy of monitoring data by optimizing the monitoring data preprocessing system through adaptive vibration elements and Gaussian filter kernels.

[0005] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0006] While most vehicle maintenance systems on the market can effectively monitor brake pad wear and provide warnings when critical wear is reached, brake discs lack corresponding monitoring capabilities. Brake disc replacement and monitoring standards are unclear, and premature replacement increases vehicle maintenance costs, while delayed replacement can create safety risks during driving. Summary of the Invention

[0007] Technical problems solved

[0008] In response to the shortcomings of the existing technology, the present invention provides a vehicle health monitoring and maintenance management system based on AI intelligent prediction, which solves the problem of lack of predictive ability for brake disc durability in the existing technology, realizes accurate prediction of brake disc life, and thus significantly improves driving safety.

[0009] Technical Solution

[0010] To achieve the above objectives, the present invention is implemented through the following technical solutions: a vehicle health monitoring and maintenance management system based on AI intelligent prediction, including: a data collection module, a data processing module, a braking habit evaluation module and a data analysis module; the data collection module is used to obtain a braking transmission data set and a braking life prediction data set; the data processing module is used to normalize the braking transmission data set and the braking life prediction data set to obtain a pedal transmission prediction value; the braking habit evaluation module is used to analyze the driver's braking habits, and make intelligent adjustments based on the analysis results, and at the same time issue warnings regarding their braking habits; the data analysis module is used to predict the life of the brake disc and issue an early warning based on the results of the life prediction.

[0011] Furthermore, the brake transmission data set includes a speed impact value, a pedal braking value, a hydraulic adjustment value, a master cylinder piston area, and a hydraulic cylinder piston area; the brake life prediction data set includes the number of brake pedal steppings, the brake pedal stepping time, the pedal force critical value, the stepping critical time, the friction coefficient between the brake pad and the brake disc, the contact area between the brake pad and the brake disc, and the initial thickness value of the brake disc.

[0012] Furthermore, the specific process of obtaining the pedal transmission prediction value is as follows: obtaining the pedal braking value, the master cylinder piston area and the hydraulic cylinder piston area, and obtaining the pedal transmission prediction value by comprehensively calculating the pedal braking value, the master cylinder piston area and the hydraulic cylinder piston area.

[0013] Furthermore, the method for obtaining the pedal transmission prediction value is as follows: Where k b represents the pedal transmission prediction value, A p represents the piston area of ​​the hydraulic cylinder, k pIndicates the pedal braking value, A b Indicates the piston area of ​​the master cylinder.

[0014] Furthermore, the specific process of analyzing the driver's braking habits is as follows: obtaining the pedal braking value, brake pedal pressing time, pedal force critical value and pressing critical time, and obtaining the abnormal data value through comprehensive calculation of the pedal braking value, brake pedal pressing time, pedal force critical value and pressing critical time.

[0015] Furthermore, the method for obtaining abnormal data values ​​is as follows: Where S represents the abnormal data value, w1 represents the weight factor of the pedaling time, w2 represents the pedal braking weight factor, T act Indicates the current brake pedal pressing time, T th Indicates the critical duration of pedaling, F act Indicates the current pedal transmission prediction value, F th Indicates the pedal force threshold.

[0016] Furthermore, the specific process of making intelligent adjustments based on the analysis results and issuing warnings based on their braking habits is as follows: the total number of abnormal data values ​​is compared with the first threshold in real time. When the total number of abnormal data values ​​is less than the first threshold, no warning is issued. When the total number of abnormal data values ​​is greater than or equal to the first threshold, the hydraulic resistance of the hydraulic cylinder is increased according to the current situation, and a warning pop-up window is popped up on the vehicle's central control screen and a sound is emitted to issue an early warning.

[0017] Furthermore, the specific process of predicting the life of the brake disc is as follows: obtaining the friction coefficient between the brake pad and the brake disc, the speed influence value, the contact area between the brake pad and the brake disc, the hydraulic adjustment value, the brake pedal stepping time, the number of brake pedal stepping times, and the initial thickness value of the brake disc, and obtaining the predicted life value of the brake disc through comprehensive calculation of the friction coefficient between the brake pad and the brake disc, the speed influence value, the contact area between the brake pad and the brake disc, the brake pedal stepping time, the number of brake pedal stepping times, and the initial thickness value of the brake disc.

[0018] Furthermore, the life prediction value of the brake disc is obtained as follows: Where y represents the life expectancy of the brake disc, y0 represents the initial thickness of the brake disc, n represents the number of times the brake pedal is stepped on, f represents the wear coefficient of the brake disc, μ represents the friction coefficient between the brake pad and the brake disc, A represents the contact area between the brake pad and the brake disc, and k represents the contact area between the brake pad and the brake disc. b represents the pedal transmission prediction value, T represents the brake pedal pressing time, c(v) is the speed influence value, j p is the hydraulic adjustment value.

[0019] Furthermore, the specific process of making an early warning based on the result of life prediction is as follows: comparing the predicted life value of the brake disc with the second threshold in real time; when the predicted life value of the brake disc is greater than the second threshold, no reminder is given; when the predicted life value of the brake disc is less than or equal to the second threshold, a warning pop-up window is displayed on the vehicle's central control screen, a sound alarm is sounded, and information is sent to the mobile phone APP for early warning.

[0020] Beneficial effects

[0021] The present invention has the following beneficial effects:

[0022] (1) The present invention calculates the life prediction value of the brake disc, so that the driver can replace the brake disc before it reaches the end of its life, thereby preventing the braking performance from being reduced due to excessive wear of the brake disc. The maintenance time can be reasonably arranged in advance, avoiding the situation of emergency repairs, and will not affect life. By monitoring the wear of the brake disc to predict the service life, the replacement cycle can be optimized, avoiding the waste caused by premature replacement and the impact of late replacement on driving safety, thereby reducing the maintenance cost.

[0023] (2) The present invention provides an early warning by popping up a warning window on the vehicle's central control screen and emitting a sound alarm simultaneously, so that the driver can be immediately warned by sound when driving the vehicle, causing the driver to be alert. The warning information can be immediately provided to the driver through the warning pop-up window. The driver can learn the specific usage of the brake disc at the first time through the central control screen, so that he can take measures quickly, thereby improving driving safety. The warning information can also be obtained instantly through the mobile phone APP warning, whether the driver is in the car or not, so that maintenance measures can be arranged.

[0024] (3) The present invention can learn about the driver's driving habits by recording relevant data in real time, and thus record the driver's bad habit of sudden braking. When the number of sudden braking is too many, a sound will be emitted to alert the driver, and a warning window will pop up on the central control screen to give the driver an early warning, so that the driver can realize his wrong habits and improve his driving habits to enhance the overall driving experience and reduce the risk of accidents caused by bad driving. In addition, reducing the number of unnecessary sudden braking can reduce the wear and tear on the vehicle's braking system and related components, and increase the service life of the brake pads and brake discs.

[0025] (4) The present invention can accurately calculate the downforce by calculating the pedal transmission prediction value, so that the driver can more accurately predict the vehicle's braking behavior based on his own braking force. The accurate prediction not only improves driving comfort, but also enhances driving safety, allowing the driver to make more reasonable responses under different driving conditions.

[0026] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a flowchart of the vehicle health monitoring and maintenance management system based on AI intelligent prediction;

[0028] Figure 2 This is the structural diagram of the vehicle health monitoring and maintenance management system based on AI intelligent prediction. DETAILED DESCRIPTION

[0029] 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.

[0030] See also Figure 1-Figure 2 The embodiment of the present invention provides a technical solution: a vehicle health monitoring and maintenance management system based on AI intelligent prediction, including: a data collection module, a data processing module, a braking habit evaluation module and a data analysis module; the data collection module is used to obtain a braking transmission data set and a braking life prediction data set; the data processing module is used to normalize the braking transmission data set and the braking life prediction data set to obtain a pedal transmission prediction value; the braking habit evaluation module is used to analyze the driving habits of the driver and issue a warning based on the analysis results for his driving habits; the data analysis module is used to predict the life of the brake disc and issue an early warning based on the results of the life prediction. The monitoring system includes a vehicle health monitoring and maintenance management system based on the AI ​​intelligent prediction, including: a data collection module, a data processing module, a braking habit evaluation ... In the master control system, the vehicle master control system is connected to the network cloud. The vehicle master control system can also be connected to the mobile phone network through the vehicle application. Users can receive and view vehicle information through the mobile phone APP. At the same time, the vehicle central control display screen can also be queried. Through the detection of on-board sensors, vehicle operation data, driver operation data, environmental data and vehicle brake structure information are obtained in real time. The obtained vehicle operation data, driver operation data, environmental data and vehicle brake structure data information are stored to establish a vehicle master control system database, collect data in real time and update existing data sets. The latest acquired data will incorporate old data into historical data records, and the monitoring system focuses on capturing data directly related to braking operations.

[0031] Specifically, the brake transmission data set includes speed influence value, pedal braking value, hydraulic adjustment value, master cylinder piston area and hydraulic cylinder piston area; the brake life prediction data set includes brake pedal stepping times, brake pedal stepping time, pedal force critical value, stepping critical time, friction coefficient between brake pad and brake disc, contact area between brake pad and brake disc and brake disc initial thickness value; the speed influence value, hydraulic adjustment value, master cylinder piston area, hydraulic cylinder piston area, pedal force critical value, stepping critical time, friction coefficient between brake pad and brake disc, contact area between brake pad and brake disc, brake disc initial thickness value, pedal braking value, brake pedal stepping times and brake pedal stepping time are all recorded in the vehicle master control system database.

[0032] Specifically, the process for obtaining the pedal transmission prediction value is as follows: the pedal braking value, the master cylinder piston area, and the hydraulic cylinder piston area are obtained, and the pedal transmission prediction value is obtained by comprehensively calculating the pedal braking value, the master cylinder piston area, and the hydraulic cylinder piston area. When the brake pedal is stepped on, the pedal is subjected to force, which will be transmitted to the master cylinder and the hydraulic cylinder, and then to the brake pads. The method for obtaining the pedal transmission prediction value is as follows: Where k b Indicates the pedal transmission prediction value, which is the calculated downforce of the brake pad after the brake pedal is stepped on. p Represents the hydraulic cylinder piston area, which is the area of ​​the piston end inside the hydraulic cylinder that transmits force to the brake pad. The force is transmitted through the piston movement. k p Indicates the pedal braking value, which is used to measure the force exerted on the brake pedal when it is stepped on. A b Represents the piston area of ​​the master cylinder, which is the area of ​​the piston end in the master cylinder used to transmit force to the hydraulic cylinder.

[0033] In this embodiment, by calculating the pedal transmission prediction value, the downforce can be accurately calculated, which enables the driver to more accurately predict the vehicle's braking behavior based on his or her own braking force. The accurate prediction not only improves driving comfort, but also enhances driving safety, allowing the driver to make more reasonable responses under different driving conditions.

[0034] Specifically, the specific process of analyzing the driver's braking habits is as follows: First, collect key data related to the braking operation, including obtaining the pedal braking value, brake pedal pressing time, pedal force threshold value and pressing time threshold. Then, through the comprehensive calculation and analysis of the pedal braking value, brake pedal pressing time, pedal force threshold value and pressing time threshold, obtain abnormal data values. The method for obtaining abnormal data values ​​is as follows: Where S represents the abnormal data value, indicating that the braking operation data is abnormal, w1 represents the weight factor of the pedaling time, and w2 represents the pedal braking weight factor. Both the pedaling time weight factor and the pedal braking weight factor are obtained from the vehicle master control system database. T act Indicates the current brake pedal pressing time, which is the time from the start of pressing the brake pedal to the braking force reaching the critical braking force, T th It represents the critical pedaling time, obtained through experiments and historical data, and is used to measure the time when the pedaling force is too heavy. act Indicates the current pedal transmission prediction value, which indicates the pedaling force recognized by the pressure sensor when the brake pedal is currently pressed. th The threshold value for pedal force, obtained through experiments and historical data, is used to measure whether the pedaling force is too strong. The specific process for making intelligent adjustments based on the analysis results and issuing warnings about braking habits is as follows: The total number of abnormal data values ​​is compared with a first threshold in real time. When the total number of abnormal data values ​​is less than the first threshold, no warning is issued. When the total number of abnormal data values ​​is greater than or equal to the first threshold (the first threshold is the number of sudden braking events set by analyzing historical data in the vehicle's master control system database), the hydraulic resistance of the hydraulic cylinder is increased through the damper based on the current situation. The specific adjustment method is that after detecting that the driver has bad driving habits, the hydraulic resistance is increased through the damper, making the brake pedal more forceful. When the driver steps on the brake pedal, the braking effect becomes smaller than before. At the same time, a pop-up window with abnormal braking warning text and a warning of safe braking methods pops up on the vehicle's central control screen, and a sound is emitted to broadcast the warning text in response to the pop-up window as a warning.

[0035] In this embodiment, the driver's driving habits can be learned by recording relevant data in real time, thereby recording the driver's bad habit of sudden braking. When the number of sudden brakes is too many, a sound will be emitted to alert the driver. At the same time, a warning pop-up window will pop up on the central control screen to issue an early warning to the driver, so that the driver can realize his wrong habits and improve his driving habits to enhance the overall driving experience, reduce the risk of accidents caused by poor driving, and reduce the number of unnecessary sudden brakes, which can reduce the wear and tear on the vehicle's braking system and related components and increase the service life of brake pads and brake discs.

[0036] Specifically, the specific process of predicting the life of the brake disc is as follows: first, key parameters related to braking performance are collected, including the friction coefficient between the brake pad and the brake disc, the speed influence value, the contact area between the brake pad and the brake disc, the hydraulic adjustment value, the brake pedal pressing time, the number of brake pedal pressing times, and the initial thickness of the brake disc. Then, by analyzing these key parameters, the friction coefficient between the brake pad and the brake disc, the speed influence value, the contact area between the brake pad and the brake disc, the brake pedal pressing time, the number of brake pedal pressing times, and the initial thickness of the brake disc, a comprehensive calculation is performed to obtain the predicted value of the brake disc life. The method for obtaining the predicted value of the brake disc life is as follows: Where y represents the life expectancy of the brake disc, is the current thickness of the brake disc, y0 represents the initial thickness of the brake disc, is the initial thickness of the brake disc, n represents the number of times the brake pedal is stepped on, is the total number of times the driver steps on the brake pedal for the first time to the present, f represents the wear coefficient of the brake disc, is a parameter that quantifies the wear rate of the brake disc during the friction process, μ represents the friction coefficient between the brake pad and the brake disc, is the friction force between the brake pad and the brake disc during braking, A represents the contact area between the brake pad and the brake disc, is the contact area between the brake pad and the brake disc, k b represents the pedal transmission prediction value, which is the pedal force recognized by the pressure sensor when the brake pedal is stepped on. T represents the brake pedal stepping time, which is the time from the start to the end of stepping on the brake pedal. c(v) is the speed impact value, which is the additional wear effect caused by speed. v is the speed, and h is the speed. p is the hydraulic adjustment value, is the proportional coefficient of the brake pedal resistance increase, and represents the change in resistance, j p The value range is 0 to 1. p When it is equal to 0, the result remains unchanged, indicating that no abnormality is recognized and the strength does not change. p When it is greater than 0, the result will be less than 1, indicating that the force has changed and the braking force will decrease.

[0037] In this embodiment, by calculating the predicted life value of the brake disc, the driver can replace the brake disc before it reaches the end of its life, preventing the braking performance from being degraded due to excessive wear of the brake disc. The maintenance time can be reasonably arranged in advance, avoiding emergency repairs and not affecting life. By monitoring the wear of the brake disc to predict the service life, the replacement cycle can be optimized, avoiding waste caused by premature replacement and affecting driving safety due to late replacement, thereby reducing maintenance costs.

[0038] Specifically, the specific process of making an early warning based on the results of life prediction is as follows: real-time comparison of the predicted life value of the brake disc and the second threshold value. The second threshold value is obtained through the vehicle master control system database and is set according to the brake disc replacement standard of the current model, so that it can continue to be used when it reaches the second threshold value. When the predicted life value of the brake disc is greater than the second threshold value, no reminder will be given. When the predicted life value of the brake disc is less than or equal to the second threshold value, a prominent red warning exclamation mark will pop up on the vehicle's central control screen, and a warning pop-up window with prominent text describing that the brake disc's service life is about to expire will pop up, and a sound alarm will be issued at the same time. The content of the sound alarm is to broadcast the text in the pop-up window, and send a message with prominent text describing that the brake disc's service life is about to expire to the mobile phone APP as a warning.

[0039] In this embodiment, a warning is issued by popping up a warning window on the vehicle's central control screen and emitting a sound alarm simultaneously, so that the driver can be immediately warned by sound when driving the vehicle, alerting the driver. The warning information can be immediately provided to the driver through the warning pop-up window. The driver can know the specific usage of the brake disc at the first time through the central control screen, so that he can take measures quickly, thereby improving driving safety. The warning is also issued through the mobile phone APP, so that the driver can obtain the warning information immediately regardless of whether he is in the car, so that maintenance measures can be arranged.

[0040] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. However, the terms "include," "comprise," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0041] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to the specific embodiments described. Obviously, many modifications and variations are possible based on the content of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. Vehicle health monitoring and maintenance management system based on AI intelligent prediction, characterized by: include: Data collection module, data processing module, braking habit assessment module and data analysis module; The data collection module is used to obtain a brake transmission data set and a brake life prediction data set; The data processing module is used to normalize the brake transmission data set and the brake life prediction data set to obtain a pedal transmission prediction value; The braking habit assessment module is used to analyze the driver's braking habits, make intelligent adjustments based on the analysis results, and issue warnings based on their braking habits; The data analysis module is used to predict the life of the brake disc and issue an early warning based on the result of the life prediction.

2. The vehicle health monitoring and maintenance management system based on AI intelligent prediction according to claim 1 is characterized by: The brake transmission data set includes speed influence value, pedal brake value, hydraulic adjustment value, master cylinder piston area and hydraulic cylinder piston area; the brake life prediction data set includes brake pedal stepping times, brake pedal stepping time, pedal force critical value, stepping critical time, friction coefficient between brake pad and brake disc, contact area between brake pad and brake disc and brake disc initial thickness value.

3. The vehicle health monitoring and maintenance management system based on AI intelligent prediction according to claim 2 is characterized by: The specific process of obtaining the pedal transmission prediction value is as follows: The pedal braking value, the master cylinder piston area and the hydraulic cylinder piston area are obtained, and the pedal transmission prediction value is obtained by comprehensively calculating the pedal braking value, the master cylinder piston area and the hydraulic cylinder piston area.

4. The vehicle health monitoring and maintenance management system based on AI intelligent prediction according to claim 2 is characterized by: The method to obtain the pedal transmission prediction value is as follows: In the formula, k b represents the pedal transmission prediction value, A p represents the piston area of ​​the hydraulic cylinder, k p Indicates the pedal brake value, A b Indicates the piston area of ​​the master cylinder.

5. The vehicle health monitoring and maintenance management system based on AI intelligent prediction according to claim 2 is characterized by: The specific process of analyzing the driver's braking habits is as follows: The pedal braking value, brake pedal stepping time, pedal force critical value and stepping critical time are obtained, and the abnormal data value is obtained by comprehensive calculation of the pedal braking value, brake pedal stepping time, pedal force critical value and stepping critical time.

6. The vehicle health monitoring and maintenance management system based on AI intelligent prediction according to claim 5 is characterized by: The method to get the abnormal data value is as follows: In the formula, S represents the abnormal data value, w1 represents the weight factor of the pedaling time, w2 represents the pedal braking weight factor, T act Indicates the current brake pedal pressing time, T th Indicates the critical duration of pedaling, F act Indicates the current pedal transmission prediction value, F th Indicates the pedal force threshold.

7. The vehicle health monitoring and maintenance management system based on AI intelligent prediction according to claim 5 is characterized by: The specific process of making intelligent adjustments based on the analysis results and issuing warnings for the braking habits is as follows: The total number of abnormal data values ​​is compared with the first threshold in real time. When the total number of abnormal data values ​​is less than the first threshold, no warning is issued. When the total number of abnormal data values ​​is greater than or equal to the first threshold, the hydraulic resistance of the hydraulic cylinder is increased according to the current situation. At the same time, a warning window pops up on the vehicle's central control screen and a sound is emitted to warn.

8. The vehicle health monitoring and maintenance management system based on AI intelligent prediction according to claim 2 is characterized by: The specific process of predicting the life of the brake disc is as follows: The friction coefficient between the brake pad and the brake disc, the speed influence value, the contact area between the brake pad and the brake disc, the hydraulic adjustment value, the brake pedal stepping time, the brake pedal stepping times, and the initial thickness of the brake disc are obtained. The life prediction value of the brake disc is obtained by comprehensive calculation through the friction coefficient between the brake pad and the brake disc, the speed influence value, the contact area between the brake pad and the brake disc, the brake pedal stepping time, the brake pedal stepping times, and the initial thickness of the brake disc.

9. The vehicle health monitoring and maintenance management system based on AI intelligent prediction according to claim 8 is characterized by: The method to obtain the predicted value of the brake disc life is as follows: Where y represents the life prediction value of the brake disc, y0 represents the initial thickness of the brake disc, n represents the number of times the brake pedal is stepped on, f represents the wear coefficient of the brake disc, μ represents the friction coefficient between the brake pad and the brake disc, A represents the contact area between the brake pad and the brake disc, and k b represents the pedal transmission prediction value, T represents the brake pedal stepping time, c(v) is the speed influence value, j p It is the hydraulic adjustment value.

10. The vehicle health monitoring and maintenance management system based on AI intelligent prediction according to claim 8 is characterized by: The specific process of making an early warning based on the result of life prediction is as follows: The predicted life value of the brake disc is compared with the second threshold in real time. When the predicted life value of the brake disc is greater than the second threshold, no reminder is given. When the predicted life value of the brake disc is less than or equal to the second threshold, a warning pop-up window is displayed on the vehicle's central control screen, a sound alarm is sounded, and information is sent to the mobile phone APP for early warning.

Images