Service life prediction method and system for brake disc

Abstract

The invention relates to the technical field of brake wear analysis, in particular to a service life prediction method and system for a brake disc. The method comprises the following steps: firstly, acquiring a real-time road condition difference degree according to a difference condition between pedal moving speeds corresponding to a current time period and a historical time period; integrating the braking habit influence coefficient and the braking habit wear coefficient to obtain an overall habit influence index; according to the pedal moving distance sequence of the reference time period, obtaining an autocorrelation coefficient; correcting the autocorrelation coefficient according to the overall habit influence index to obtain a corrected autocorrelation coefficient; and predicting the service life of the brake disc according to the pedal moving distance sequence of the reference time period and the corrected autocorrelation coefficient. The method fully considers the influence of the real-time driving habit on the wear of the brake disc, reasonably sets the corrected autocorrelation coefficient, and improves the prediction accuracy of the service life of the brake disc.

Description

Technical Field

[0001] The present invention relates to the technical field of brake wear analysis, and in particular to a method and system for predicting the service life of a brake disc. Background Art

[0002] As a key component of the automobile braking system, the quality of the brake disc is directly related to the braking effect of the car and the safety of the driver and passengers. Therefore, it is very important to accurately predict the service life of the brake disc. By reasonably predicting the service life of the brake disc, the owner can understand the wear of the brake disc in time and replace it when necessary, thereby avoiding the reduction of braking effect due to excessive wear of the brake disc and ensuring driving safety.

[0003] As the brake disc wears, the service life of the brake disc will decrease. Increased wear of the brake disc will lead to a gradual decline in braking performance, which is manifested externally as an increase in the pedal movement distance. The pedal movement distance can be used as a key indicator to evaluate the service life of the brake disc. The ARMA model is a time series prediction model. In the prediction of the service life of the brake disc, the ARMA model can be used to predict based on the pedal movement distance sequence. Because different real-time driving habits have different effects on the wear of the brake disc, when using the ARMA model for prediction, the determination of the autocorrelation coefficient does not fully consider the driving habits on the current road, which affects the accuracy of the prediction results of the brake disc service life. Summary of the invention

[0004] In order to solve the technical problem that the existing technology has inaccurate prediction results of the service life of brake discs, the purpose of the present invention is to provide a method and system for predicting the service life of brake discs. The technical solutions adopted are as follows:

[0005] A method for predicting the service life of a brake disc, the method comprising:

[0006] Acquire a vehicle driving data set; the vehicle driving data set includes a pedal movement distance, a pedal movement speed, and a driving speed corresponding to each braking moment in a reference period; the reference period includes a current period and a historical period;

[0007] According to the difference between the pedal movement speed corresponding to the current time period and the historical time period, the real-time road condition difference is obtained; according to the numerical value of the pedal movement speed in the current time period and the real-time road condition difference, the braking habit influence coefficient is obtained; according to the numerical values ​​of the pedal movement speed and the driving speed corresponding to each braking moment in the current time period, the braking habit wear coefficient is obtained; the overall habit influence index is obtained by combining the braking habit influence coefficient and the braking habit wear coefficient; according to the pedal movement distance sequence of the reference time period, the autocorrelation coefficient is obtained; according to the overall habit influence index, the autocorrelation coefficient is corrected to obtain the corrected autocorrelation coefficient;

[0008] The service life of the brake disc is predicted based on the pedal movement distance sequence in the reference period and the corrected autocorrelation coefficient.

[0009] Furthermore, the method for obtaining the real-time traffic difference includes:

[0010] The current period and the historical period are respectively used as the periods to be analyzed; the pedal movement speeds corresponding to all braking moments in the period to be analyzed are counted in sequence according to the time sequence to obtain the pedal movement speed sequence of the period to be analyzed;

[0011] Based on the DTW algorithm, the DTW distance between the pedal movement speed sequence corresponding to the current time period and the historical time period is used as the real-time road condition difference.

[0012] Furthermore, the method for obtaining the braking habit influence coefficient includes:

[0013] In the current period, if the pedal movement speed is greater than the preset standard speed value, it is marked as an emergency braking speed; if the pedal movement speed is not greater than the preset standard speed value, it is marked as a slow braking speed;

[0014] Calculate the average of all the emergency braking speeds in the current period as the overall emergency braking speed value; calculate the average of all the slow braking speeds in the current period as the overall slow braking speed value; calculate the difference between the overall emergency braking speed value and the overall slow braking speed value to obtain the habitual first influence coefficient;

[0015] Calculate the ratio of the total number of all the emergency braking speeds to the total number of all the pedal movement speeds in the current period to obtain the habitual second influence coefficient;

[0016] The first influence coefficient of habit, the second influence coefficient of habit and the difference of real-time road conditions are forwardly integrated to obtain the influence coefficient of braking habit.

[0017] Furthermore, the preset standard speed value is set to 5.

[0018] Furthermore, the method for obtaining the brake habit wear coefficient includes:

[0019] In the current period, the product of the pedal movement speed and the driving speed corresponding to each braking moment is calculated to obtain the wear index corresponding to the braking moment; the cumulative sum of the wear indexes corresponding to all the braking moments in the current period is calculated and normalized to obtain the braking habit wear coefficient.

[0020] Furthermore, the method for obtaining the overall habit influence index includes:

[0021] The braking habit influence coefficient and the braking habit wear coefficient are forwardly integrated to obtain an overall habit influence index.

[0022] Furthermore, the method for obtaining the autocorrelation coefficient includes:

[0023] The ARIMA model method is used to obtain the autocorrelation coefficient based on the pedal movement distance series during the reference period.

[0024] Furthermore, the method for obtaining the modified autocorrelation coefficient includes:

[0025] The product of the negative correlation mapping result of the autocorrelation coefficient corresponding to the lag order and the overall habit influence index is calculated to obtain an adjustment parameter; the product of the adjustment parameter and the autocorrelation coefficient is calculated and normalized to obtain a corrected autocorrelation coefficient.

[0026] Furthermore, the method for predicting the service life of the brake disc includes:

[0027] The ARIMA model method is used to predict the service life of brake discs based on the time series data of the moving distance in the reference period and the corrected autocorrelation coefficient.

[0028] A service life prediction system for a brake disc comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of a service life prediction method for a brake disc are implemented.

[0029] The present invention proposes a service life prediction system for brake discs, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of a service life prediction method for brake discs when executing the computer program.

[0030] The present invention has the following beneficial effects:

[0031] First, by constructing the real-time road condition difference to reflect the degree of change of the real-time road condition compared with the historical road condition, the braking habit influence coefficient is obtained according to the numerical value of the pedal movement speed in the current period and the real-time road condition difference; the braking habit influence coefficient preliminarily reflects the impact of real-time driving braking habits on brake disc wear; the braking habit wear coefficient further reflects the physical degree of real-time driving habits on brake disc wear, and the braking habit influence coefficient and the braking habit wear coefficient are combined to obtain the overall habit influence index, which is used to evaluate the overall impact of the driver's braking habits on brake disc wear. The autocorrelation coefficient is corrected according to the overall habit influence index to obtain the corrected autocorrelation coefficient. The corrected autocorrelation coefficient fully considers the impact of real-time driving habits on brake disc wear, thereby improving the accuracy and reliability of brake disc service life prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 A flowchart of a method for predicting the service life of a brake disc provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a method and system for predicting the service life of a brake disc proposed in accordance with the present invention, its specific implementation, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0035] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0036] The following is a detailed description of a method and system for predicting the service life of a brake disc provided by the present invention in conjunction with the accompanying drawings.

[0037] The embodiment of the present invention provides a method and system for predicting the service life of a brake disc. Figure 1 , which shows a flow chart of a method for predicting the service life of a brake disc provided by an embodiment of the present invention, the method comprising the following steps:

[0038] Step S1: Acquire a vehicle driving data set; the vehicle driving data set includes a pedal movement distance, a pedal movement speed, and a driving speed corresponding to each braking moment in a reference period; the reference period includes a current period and a historical period.

[0039] In order to make a reasonable prediction of the service life of the brake disc, we first obtain a set of car driving data to provide basic data support for subsequent analysis of driving habits and predictions.

[0040] The present invention first initiates an authorization request to obtain the vehicle driving record to the vehicle to be processed, and after the driver agrees, obtains the vehicle driving data set of the vehicle to be processed from the cloud service platform of the intelligent vehicle machine; the vehicle driving data set includes the pedal movement distance, pedal movement speed and driving speed corresponding to each braking moment in the reference period. The specific acquisition process includes: within the reference period, the driver will perform multiple braking operations. For any braking operation, the data collection content includes: braking time: the total time from the brake pedal being stepped on to the complete release during the braking operation; pedal movement distance: the total distance the brake pedal moves during the stepping on the braking operation, this data directly reflects the effectiveness of the braking system and the friction between the tire and the ground, and is a key indicator for predicting the life of the brake disc; braking moment: the first moment corresponding to the braking operation, reflecting the moment when the pedal is first stepped on during the braking operation, as the starting time point of this braking event; pedal movement speed: the ratio of the pedal movement distance to the braking time, the pedal movement speed can be obtained, and the pedal movement speed is a key parameter for measuring the speed of vehicle deceleration during the braking process; driving speed: that is, the speed of the car corresponding to the moment before the braking moment. The driving speed reflects the dynamic state of the vehicle before the braking operation, and is also of great significance for analyzing driving habits and predicting the life of the brake disc. The pedal movement distance, pedal movement speed and driving speed corresponding to each braking moment in the reference period are uploaded to the cloud service platform for storage and management. In one embodiment of the present invention, a preset time range from the current moment to before the current moment is selected as the reference period, where the preset time range is set to 100 hours, and the implementer can set it according to the implementation scenario.

[0041] In order to analyze real-time driving habits, the reference period is divided into a current period and a historical period. In one embodiment of the present invention, the preset current time range from the current moment to before the current moment is selected as the current period, wherein the preset current time range is set to 5 hours, and the implementer can set it according to the implementation scenario. In the reference period, the time range outside the current period is used as the historical period.

[0042] For the above steps, a relatively short time window is selected as the current period. This time window is close to the current moment and is used to capture and analyze the driver's recent driving behavior. Compared with the current period, the historical period has a longer time span, which covers the driver's driving record in the past period. Through the data of the historical period, the driver's long-term driving habits can be understood.

[0043] The data collection in the present invention is authorized by the user, does not violate relevant laws and regulations, and does not violate public order and good morals. In order to facilitate calculations, all indicator data involved in the calculations in the embodiments of the present invention are pre-processed to eliminate the dimension effect. The specific means of removing the dimension effect are technical means well known to those skilled in the art and are not limited here.

[0044] Step S2: According to the difference between the pedal movement speeds corresponding to the current time period and the historical time period, obtain the real-time road condition difference; according to the numerical value of the pedal movement speed in the current time period and the real-time road condition difference, obtain the braking habit influence coefficient; according to the numerical values ​​of the pedal movement speed and the driving speed corresponding to each braking moment in the current time period, obtain the braking habit wear coefficient; comprehensively obtain the braking habit influence coefficient and the braking habit wear coefficient to obtain the overall habit influence index; according to the pedal movement distance sequence of the reference time period, obtain the autocorrelation coefficient; according to the overall habit influence index, correct the autocorrelation coefficient to obtain the corrected autocorrelation coefficient.

[0045] First, by constructing the real-time road condition difference to reflect the degree of change of the real-time road condition compared with the historical road condition, the braking habit influence coefficient is obtained according to the numerical value of the pedal movement speed in the current period and the real-time road condition difference; the braking habit influence coefficient preliminarily reflects the impact of real-time driving braking habits on brake disc wear; the braking habit wear coefficient further reflects the physical degree of real-time driving habits on brake disc wear, and the braking habit influence coefficient and the braking habit wear coefficient are combined to obtain the overall habit influence index, which is used to evaluate the overall impact of the driver's braking habits on brake disc wear. The autocorrelation coefficient is corrected according to the overall habit influence index to obtain the corrected autocorrelation coefficient. The corrected autocorrelation coefficient fully considers the impact of real-time driving habits on brake disc wear, thereby improving the accuracy and reliability of brake disc service life prediction.

[0046] In order to analyze the difference between the driving road conditions in the current period and the historical period, preferably, in one embodiment of the present invention, the method for obtaining the difference in real-time road conditions includes:

[0047] The current period and the historical period are respectively used as the periods to be analyzed; the pedal movement speeds corresponding to each braking moment in the period to be analyzed are counted in sequence according to the time sequence to obtain the pedal movement speed sequence of the period to be analyzed;

[0048] Based on the DTW (Dynamic Time Warping) algorithm, the DTW distance of the pedal movement speed sequence corresponding to the current period and the historical period is used as the real-time road condition difference. It should be noted that the DTW (Dynamic Time Warping) algorithm is an existing technology well known to those skilled in the art and will not be described in detail here.

[0049] For the above steps, considering that different brake pedal movement speeds reflect different car driving conditions, by comparing the difference between the pedal movement speeds corresponding to the current period and the historical period, the difference in the degree of difference in the car driving conditions corresponding to the current period and the historical period can be indirectly reflected. The DTW distance reflects the difference in the pedal movement speed sequence corresponding to the current period and the historical period. Finally, the DTW distance of the pedal movement speed sequence corresponding to the current period and the historical period is used as the real-time road condition difference. The real-time road condition difference quantifies the difference in the driving conditions between the current period and the historical period.

[0050] In other embodiments of the present invention, the method for obtaining the real-time road condition difference also includes:

[0051] The current period and the historical period are respectively used as the periods to be analyzed; based on a two-dimensional coordinate system, that is, the horizontal axis of the two-dimensional coordinate system is time, and the vertical axis is the pedal movement speed, each pedal movement speed and its corresponding braking moment constitute a data point, and the data points of all pedal movement speeds in the period to be analyzed are counted as fitting data points; using the least squares method, curve fitting is performed on all fitting data points in the period to be analyzed to obtain the braking degree fitting curve of the period to be analyzed;

[0052] The curve matching algorithm is used to obtain the difference in real-time road condition according to the difference in the braking degree fitting curves corresponding to the current period and the historical period. It should be noted that the least square method and the curve matching algorithm are prior arts well known to those skilled in the art and will not be described in detail here.

[0053] Considering that in the current period, different braking behaviors cause different wear on the brake disc, such as sudden braking behavior causes greater wear on the brake disc than slow braking behavior. By constructing a braking habit influence coefficient to reflect the impact of real-time braking behavior and real-time road condition differences on brake disc wear, preferably, in one embodiment of the present invention, the method for obtaining the braking habit influence coefficient includes:

[0054] In the current period, if the pedal movement speed is greater than the preset standard speed value, it is marked as the emergency braking speed; if the pedal movement speed is not greater than the preset standard speed value, it is marked as the slow braking speed;

[0055] Calculate the average of all emergency braking speeds in the current period as the overall emergency braking speed value; calculate the average of all slow braking speeds in the current period as the overall slow braking speed value; calculate the difference between the overall emergency braking speed value and the overall slow braking speed value to obtain the habitual first influence coefficient;

[0056] Calculate the ratio of the total number of all emergency braking speeds to the total number of all pedal movement speeds in the current period to obtain the habitual second influence coefficient;

[0057] The first influence coefficient of habit, the second influence coefficient of habit and the difference of real-time road conditions are forwardly integrated to obtain the influence coefficient of braking habit. It should be noted that forward fusion is a prior art well known to those skilled in the art, and forward fusion can adopt simple product, arithmetic mean or other suitable fusion methods. In one embodiment of the present invention, the product of the first influence coefficient of habit, the second influence coefficient of habit and the difference of real-time road conditions is calculated and normalized to obtain the influence coefficient of braking habit. In one embodiment of the present invention, the normalization process can adopt linear normalization, etc., which is not limited here. In one embodiment of the present invention, the preset standard speed value is 5, and the implementer can set it according to the implementation scenario.

[0058] For the above steps, the braking event in which the pedal moving speed is greater than the preset standard speed value is marked as an emergency braking speed, indicating that the driver has performed a relatively rapid braking operation. The braking event in which the pedal moving speed is not greater than the preset standard speed value is marked as a slow braking speed, indicating that the driver has performed a relatively gentle braking operation. The difference between the overall emergency braking speed value and the overall slow braking speed value is calculated to obtain the habit first influence coefficient, which reflects the speed difference between the driver's emergency braking and slow braking behaviors in the current period. The larger the habit first influence coefficient, the greater the wear of the brake disc by the driver's braking behavior. The ratio of the total number of all emergency braking speeds to the total number of all pedal moving speeds is calculated to obtain the habit second influence coefficient; the habit second influence coefficient reflects the frequency of the driver's emergency braking behavior in the current period. The real-time road condition difference reflects the difference between the road condition in the current period and the historical road condition. The larger the real-time road condition difference, the more attention should be paid to the braking behavior in the current period. The braking habit influence coefficient is obtained by combining the habit first influence coefficient, the habit second influence coefficient and the real-time road condition difference. The higher the braking habit influence coefficient, the greater the impact of the driver's braking habit on the brake disc wear in the current period.

[0059] Considering that the driving speed of a car has a significant impact on the degree of brake disc wear, especially when driving at high speed, even if the number of emergency brakes is not large, the wear on the brake disc will be relatively serious due to the huge braking force required. The driving speed not only reflects the movement state of the vehicle, but also reflects the characteristics of driving habits. Therefore, combining the pedal movement speed and driving speed corresponding to the braking moment, a braking habit wear coefficient is constructed to accurately quantify the impact of the driver's driving habits on the wear of the brake disc. Preferably, in one embodiment of the present invention, the method for obtaining the braking habit wear coefficient includes:

[0060] In the current period, the product of the pedal movement speed and the driving speed corresponding to each braking moment is calculated to obtain the wear index corresponding to the braking moment; the cumulative sum of the wear indexes corresponding to all braking moments in the current period is calculated and normalized to obtain the braking habit wear coefficient. In one embodiment of the present invention, the normalization process can adopt linear normalization, etc., which is not limited here.

[0061] For the above steps, the wear index corresponds to the degree of wear of the brake system under the combined effect of the vehicle's driving speed and the brake pedal speed during the braking operation at the braking moment. The cumulative sum of the wear indexes corresponding to all braking moments in the current period is calculated and normalized to obtain the brake habit wear coefficient. The pedal movement speed and driving speed corresponding to each braking event in the current period, as well as the influence of the combined effect of these speeds on the degree of wear of the brake system are comprehensively considered, thereby obtaining a brake habit wear coefficient that reflects the influence of the driver's braking habits on the wear of the brake disc.

[0062] In order to comprehensively analyze the impact of real-time braking habits on brake disc wear, preferably, in one embodiment of the present invention, the method for obtaining the overall habit impact index includes:

[0063] The braking habit influence coefficient and the braking habit wear coefficient are forwardly integrated to obtain the overall habit influence index. It should be noted that forward fusion is a prior art well known to those skilled in the art, and forward fusion can adopt simple product, arithmetic mean or other suitable fusion methods. In one embodiment of the present invention, the mean of the braking habit influence coefficient and the braking habit wear coefficient is calculated to obtain the overall habit influence index.

[0064] For the above steps, the overall habit impact index comprehensively reflects the impact of real-time braking habits on brake disc wear.

[0065] In order to adjust the autocorrelation coefficient, it is first necessary to obtain the autocorrelation coefficient. Preferably, in one embodiment of the present invention, the method for obtaining the autocorrelation coefficient includes:

[0066] The ARIMA model method is used to obtain the autocorrelation coefficient based on the pedal movement distance sequence of the reference period. It should be noted that the method for obtaining the autocorrelation coefficient is a prior art well known to those skilled in the art, and is only briefly described here: according to the time sequence, all pedal movement distances in the reference period are counted in sequence to obtain the pedal movement distance sequence of the reference period; based on the ARMA (AutoRegressive Moving Average) model, the autocorrelation coefficient is obtained based on the pedal movement distance sequence.

[0067] In order to adjust the autocorrelation coefficient, preferably, in one embodiment of the present invention, the method for obtaining the corrected autocorrelation coefficient includes:

[0068] The product of the negative correlation mapping result corresponding to the lag order of the autocorrelation coefficient and the overall habit influence index is calculated to obtain the adjustment parameter; the product of the adjustment parameter and the autocorrelation coefficient is calculated and normalized to obtain the corrected autocorrelation coefficient. It should be noted that the normalization method is: normalization is performed using the tanh normalization function.

[0069] For the above steps, the lag order corresponding to the autocorrelation coefficient reflects the time distance between the historical data and the current moment, and the overall habit influence index fully reflects the impact of real-time braking habits on the wear of the brake disc. When the overall habit influence index is larger, it means that the driver's braking habits have a stronger impact on the wear of the brake disc. In this case, it is more inclined to believe that the brake disc state at the current moment is more affected by recent driving behavior rather than the lag effect of distant historical data. Therefore, the product of the negative correlation mapping result of the lag order corresponding to the autocorrelation coefficient and the overall habit influence index is calculated to obtain the adjustment parameter; in the prediction of the service life of the brake disc, the adjustment parameter is used to correct the autocorrelation coefficient to more accurately reflect the wear of the brake disc. By combining the adjustment parameter with the autocorrelation coefficient, the corrected autocorrelation coefficient can be obtained. The corrected autocorrelation coefficient can more accurately reflect the trend of real-time wear of the brake disc and help to accurately predict the service life of the brake disc.

[0070] Step S3: predicting the service life of the brake disc according to the pedal movement distance sequence in the reference period and the corrected autocorrelation coefficient.

[0071] Through the above steps, a corrected autocorrelation coefficient is constructed which fully considers the effect of real-time driving habits on brake disc wear, thereby improving the accuracy and reliability of brake disc service life prediction.

[0072] In order to accurately predict the service life of the brake disc, preferably, in one embodiment of the present invention, the method for predicting the service life of the brake disc includes:

[0073] The ARIMA model method is used to predict the service life of brake discs based on the time series data of the moving distance in the reference period and the corrected autocorrelation coefficient.

[0074] It should be noted that the ARMA model method for prediction is an existing technology well known to those skilled in the art, and only a brief description is given here: according to the moving distance time series data of the reference period and the corrected autocorrelation coefficient, the appropriate ARIMA model parameters are selected, including the autoregressive term p, the difference order d, and the moving average term q; the prediction model is constructed using the selected ARIMA model parameters. The ARIMA model is trained using the data in the reference period, and the model is verified using cross-validation or other verification methods to ensure the accuracy and reliability of the model. The trained ARIMA model is applied to the moving distance time series data in the prediction time period to obtain the moving distance value at the prediction moment. According to the predicted moving distance value, combined with the law of brake disc wear and the empirical formula, the predicted service life of the brake disc is calculated and output. For example, if the predicted moving distance value is greater than the preset distance threshold, the service life of the brake disc is output and a life warning is performed. The preset distance threshold in the present invention is 32, and the implementer can set it according to the implementation scenario.

[0075] The present invention proposes a service life prediction system for brake discs, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, steps of a service life prediction method for brake discs are implemented.

[0076] In summary, the embodiment of the present invention provides a method and system for predicting the service life of a brake disc. First, the difference in real-time road conditions is obtained based on the difference between the pedal movement speeds corresponding to the current time period and the historical time period; the overall habit influence index is obtained by combining the braking habit influence coefficient and the braking habit wear coefficient; the autocorrelation coefficient is obtained based on the pedal movement distance sequence of the reference time period; the autocorrelation coefficient is corrected based on the overall habit influence index to obtain the corrected autocorrelation coefficient; the service life of the brake disc is predicted based on the pedal movement distance sequence of the reference time period and the corrected autocorrelation coefficient. The present invention fully considers the impact of real-time driving habits on brake disc wear and reasonably sets the corrected autocorrelation coefficient to improve the accuracy of brake disc service life prediction.

[0077] It should be noted that the sequence of the above embodiments of the present invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0078] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for predicting the service life of a brake disc, characterized in that: The method comprises: Acquire a vehicle driving data set; the vehicle driving data set includes a pedal movement distance, a pedal movement speed, and a driving speed corresponding to each braking moment in a reference period; the reference period includes a current period and a historical period; According to the difference between the pedal movement speed corresponding to the current time period and the historical time period, the real-time road condition difference is obtained; according to the numerical value of the pedal movement speed in the current time period and the real-time road condition difference, the braking habit influence coefficient is obtained; according to the numerical values ​​of the pedal movement speed and the driving speed corresponding to each braking moment in the current time period, the braking habit wear coefficient is obtained; the overall habit influence index is obtained by combining the braking habit influence coefficient and the braking habit wear coefficient; according to the pedal movement distance sequence of the reference time period, the autocorrelation coefficient is obtained; according to the overall habit influence index, the autocorrelation coefficient is corrected to obtain the corrected autocorrelation coefficient; The service life of the brake disc is predicted based on the pedal movement distance sequence in the reference period and the corrected autocorrelation coefficient.

2. A method for predicting the service life of a brake disc according to claim 1, characterized in that: The method for obtaining the real-time traffic condition difference comprises: The current period and the historical period are respectively used as the periods to be analyzed; the pedal movement speeds corresponding to all braking moments in the period to be analyzed are counted in sequence according to the time sequence to obtain the pedal movement speed sequence of the period to be analyzed; Based on the DTW algorithm, the DTW distance between the pedal movement speed sequence corresponding to the current time period and the historical time period is used as the real-time road condition difference.

3. A method for predicting the service life of a brake disc according to claim 1, characterized in that: The method for obtaining the braking habit influence coefficient includes: In the current period, if the pedal movement speed is greater than the preset standard speed value, it is marked as an emergency braking speed; if the pedal movement speed is not greater than the preset standard speed value, it is marked as a slow braking speed; Calculate the average of all the emergency braking speeds in the current period as the overall emergency braking speed value; calculate the average of all the slow braking speeds in the current period as the overall slow braking speed value; calculate the difference between the overall emergency braking speed value and the overall slow braking speed value to obtain the habitual first influence coefficient; Calculate the ratio of the total number of all the emergency braking speeds to the total number of all the pedal movement speeds in the current period to obtain the habitual second influence coefficient; The first influence coefficient of habit, the second influence coefficient of habit and the difference of real-time road conditions are forwardly integrated to obtain the influence coefficient of braking habit.

4. A method for predicting the service life of a brake disc according to claim 3, characterized in that: The preset standard speed value is set to 5.

5. A method for predicting the service life of a brake disc according to claim 1, characterized in that: The method for obtaining the brake habit wear coefficient includes: In the current period, the product of the pedal movement speed and the driving speed corresponding to each braking moment is calculated to obtain the wear index corresponding to the braking moment; the cumulative sum of the wear indexes corresponding to all the braking moments in the current period is calculated and normalized to obtain the braking habit wear coefficient.

6. A method for predicting the service life of a brake disc according to claim 1, characterized in that: The method for obtaining the overall habit influence index includes: The braking habit influence coefficient and the braking habit wear coefficient are forwardly integrated to obtain an overall habit influence index.

7. A method for predicting the service life of a brake disc according to claim 1, characterized in that: The method for obtaining the autocorrelation coefficient includes: The ARIMA model method is used to obtain the autocorrelation coefficient based on the pedal movement distance series during the reference period.

8. A method for predicting the service life of a brake disc according to claim 1, characterized in that: The method for obtaining the modified autocorrelation coefficient includes: The product of the negative correlation mapping result of the autocorrelation coefficient corresponding to the lag order and the overall habit influence index is calculated to obtain an adjustment parameter; the product of the adjustment parameter and the autocorrelation coefficient is calculated and normalized to obtain a corrected autocorrelation coefficient.

9. A method for predicting the service life of a brake disc according to claim 1, characterized in that: Methods for predicting the service life of brake discs include: The ARIMA model method is used to predict the service life of the brake disc based on the moving distance time series data of the reference period and the corrected autocorrelation coefficient.

10. A system for predicting the service life of a brake disc, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of a method for predicting the service life of a brake disc as described in any one of claims 1 to 9 are implemented.

Images