Automobile brake pad wear detection method

Abstract

The invention provides an automobile brake pad wear detection method, and relates to the technical field of brake pad detection. Carrying out a brake experiment on the brake pad, and collecting a surface temperature distribution diagram of the brake pad after braking and a temperature-time sequence of a cooling stage; fitting an exponential attenuation model according to the temperature-time sequence of the cooling stage to obtain a thermal inertia attenuation coefficient; performing feature extraction on the surface temperature distribution map to obtain feature data; weighting the feature data and the thermal inertia attenuation coefficient to obtain input data; constructing a random forest network model, optimizing the random network model by using a bitter fish optimization algorithm, and inputting experimental data for training to obtain an optimal network model; and inputting the input data into the optimal network model to obtain a detection result. According to the method, the random forest network model is constructed, the network model is optimized and trained, the optimal network model is obtained, the input data is input into the optimal network model, the detection accuracy of the brake pad is improved, and potential safety hazards are reduced.

Description

Technical Field

[0001] The invention relates to the technical field of brake pad detection, and in particular to a method for detecting wear of an automobile brake pad. Background Art

[0002] With the development of the automobile industry, the brake system is a key component of automobile safety, and the reliability of its performance directly affects driving safety. Among them, the brake pad is an important component of the brake system, and its wear condition plays a vital role in the braking effect, driving stability and safety of the car. Therefore, timely and accurate detection of the wear degree of the brake pad has become an important research topic to ensure the safety of automobile driving. The main function of the brake pad is to interact with the brake disc through friction to generate braking force to slow down or stop the car. Its main function is to generate friction with the brake disc when the car brakes, converting kinetic energy into heat energy, thereby slowing down or stopping the movement of the vehicle. With the increase of use time, the brake pad will gradually wear, which not only affects the braking performance, but also may pose a serious threat to safety. Different driving habits have a significant impact on the wear degree of the brake pad. The wear process not only affects the braking effect, but also may cause braking noise, vibration, and even damage other components of the braking system. Replace the severely worn brake pads in time to ensure the normal operation of the braking system, thereby improving driving safety, avoiding the decline in braking performance due to wear, and reducing traffic accidents caused by brake failure.

[0003] Brake pad inspection usually relies on manual inspection, which can easily lead to misjudgment and result in failure to replace the brake pad in time, thus affecting braking performance. Summary of the invention

[0004] The invention provides a method for detecting wear of automobile brake pads, which is used to solve the problem that manual inspection is required for brake pad inspection in the prior art, which is prone to misjudgment and affects the braking performance.

[0005] On the one hand, the present invention provides a method for detecting wear of a brake pad of an automobile, comprising the following steps: performing a braking test on the brake pad, collecting a surface temperature distribution diagram of the brake pad after braking and a temperature-time series in a cooling stage; According to the temperature-time series of the cooling stage, an exponential decay model is fitted to obtain a thermal inertia decay coefficient; Extracting features from the surface temperature distribution map to obtain feature data; performing weighted processing on the feature data and the thermal inertia attenuation coefficient to obtain input data; Constructing a random forest network model, optimizing the random forest network model using a bitter fish optimization algorithm, and inputting experimental data for training to obtain an optimal network model; Input the input data into the optimal network model to obtain the detection results.

[0006] According to a method for detecting wear of a vehicle brake pad provided by the present invention, the specific steps of performing a brake test on the brake pad include: Cleaning the brake pad to remove surface grease; The target speed is set, the test bench is driven to the target speed, braking pressure is applied to the brake pad, and the deceleration of the test bench is kept constant until the speed drops to zero.

[0007] According to a method for detecting wear of a vehicle brake pad provided by the present invention, the specific steps of obtaining the thermal inertia attenuation coefficient include: Using a sliding window method to smooth the data in the temperature-time series of the cooling stage to obtain smoothed data; The thermal inertia attenuation coefficient was calculated by fitting the smoothed data using nonlinear least squares.

[0008] According to a method for detecting wear of automobile brake pads provided by the present invention, the specific steps of extracting features from the surface temperature distribution map include: Extract the temperature data of the brake pad width direction from the temperature distribution diagram, find the maximum and minimum temperature values, and calculate the maximum temperature difference; Extracting temperature data along the friction contact direction of the brake pad from the temperature distribution diagram, drawing a line along the friction contact direction of the brake pad, and recording temperature values ​​at different positions of the line to obtain a temperature sequence, and then fitting the temperature sequence using a regression method to obtain a temperature attenuation rate along the friction contact direction of the brake pad; The average temperature of the temperature distribution diagram is calculated, a temperature threshold is set, and then temperature points with a temperature higher than the average temperature are screened out according to the threshold. The areas of the temperature points are measured and summarized to obtain the total area of ​​the temperature points, and the proportion of areas with a temperature higher than the average temperature is calculated.

[0009] According to a method for detecting wear of automobile brake pads provided by the present invention, the specific steps of weighted processing include: Normalizing the thermal inertia attenuation coefficient and the characteristic data to obtain normalized data; The weight distribution is set according to actual experience, and the normalized data is weighted to obtain input data.

[0010] According to a method for detecting wear of automobile brake pads provided by the present invention, the specific steps of constructing a random forest network model include: Construct multiple decision trees, and set the maximum depth of the multiple decision trees and the minimum sample input required for the classification point to obtain an initial network model; The initial network is trained using the experimental data to obtain a random forest network model.

[0011] According to a method for detecting wear of a vehicle brake pad provided by the present invention, the specific steps of acquiring experimental data include: A braking experiment is performed using different brake pads, and the thermal inertia attenuation coefficients of the different brake pads, the maximum temperature difference in the width direction of the brake pad, the temperature attenuation rate in the friction contact direction of the brake pad, the proportion of areas with temperatures higher than the average temperature, and the corresponding wear levels and abnormality types are recorded to obtain data one; the data one is preprocessed to obtain experimental data.

[0012] According to a method for detecting wear of automobile brake pads provided by the present invention, the specific steps of preprocessing the data 1 include: Cleaning the data one, removing outliers and duplicate values ​​in the data one, and replacing missing values ​​therein with the mean to obtain cleaned data; The cleaning data is normalized to obtain experimental data.

[0013] According to a method for detecting wear of automobile brake pads provided by the present invention, the specific steps of optimizing the random forest network by the bitter fish optimization algorithm include: The mean square error is used as the fitness function of the random forest network model; Initialize the population and randomly generate the positions of individual bitter fish. Each individual bitter fish represents a hyperparameter group of the random forest network model. Set up an iterative mechanism. Each time a new population is formed, the perception range and hunger step threshold of the individual bitter fish are set according to the environmental adaptation mechanism. Calculate the fitness function of the individual bitter fish in the initialized population, and update the position of each individual bitter fish according to the behavior strategy to obtain population one; The fitness value of each individual in the population is calculated. If the output fitness value is higher than the preset fitness threshold, the optimal hyperparameter is output. Otherwise, the iteration is continued until the fitness value is higher than the preset fitness threshold or the maximum number of iterations is reached to obtain the optimal hyperparameter.

[0014] According to a method for detecting wear of a vehicle brake pad provided by the present invention, the behavior strategy includes: The individual bitter fish compares its own fitness with the average fitness value of the individual bitter fish within the sensing range. If it is better than the average fitness value of the individual bitter fish within the sensing range, the position of the individual bitter fish is updated according to local foraging; If the number of hungry steps of the bitter fish individual reaches the threshold of hungry steps, the bitter fish individual updates its position according to random migration; If the bitter fish individual does not meet the conditions of local foraging and random migration, the bitter fish individual will update the individual position through group cooperation. When the positions of all bitter fish individuals are updated, population one is obtained.

[0015] The present invention provides a method for detecting wear of automobile brake pads. The present invention constructs a random forest network model, optimizes it using a bitter fish optimization algorithm, inputs experimental data for training, obtains an optimal network model, performs weighted processing on the thermal inertia attenuation coefficient and characteristic data obtained in the experiment, obtains input data, and inputs the input data into the optimal network model to obtain a detection result. The accuracy of brake pad detection is improved and safety hazards are reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are 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.

[0017] Figure 1 The present invention is a flowchart of a method for detecting wear of a vehicle brake pad provided by an embodiment of the present invention.

[0018] Figure 2 It is a diagram of specific steps for extracting features from a surface temperature distribution diagram of a method for detecting wear of a vehicle brake pad provided by an embodiment of the present invention; Figure 3 The invention discloses a specific step of optimizing a random forest network using a bitter fish optimization algorithm in a method for detecting wear of a vehicle brake pad provided by an embodiment of the invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] See also Figure 1-Figure 3 , an embodiment of the present invention provides a method for detecting wear of a vehicle brake pad, the method comprising: A braking experiment is performed on the brake pad, and a surface temperature distribution diagram of the brake pad after braking and a temperature-time series in a cooling stage are collected.

[0021] In this embodiment, after the brake pad is braked, a refined temperature monitoring process can be further implemented. In specific operations, a high-resolution infrared thermal imager can be used to perform non-contact temperature field scanning on the surface of the brake pad to generate a two-dimensional temperature distribution map. A data recorder is used to record the temperature change of the brake pad during the cooling stage. Timed sampling can be set to record the temperature value at regular intervals to obtain detailed sequence data of temperature changes over time.

[0022] The specific steps of performing a brake test on the brake pad include: The brake pad is cleaned to remove surface oil and dirt.

[0023] In this embodiment, when cleaning the brake pad, you can choose a clean, lint-free soft cloth or brush and gently wipe the surface of the brake pad. This step is mainly to remove dust and loose dirt. Be careful when wiping and avoid excessive force to avoid damaging the surface of the brake pad, maintaining the working performance of the brake pad and extending the service life. An ultrasonic cleaner can also be used. Put the brake pad into the cleaning machine and add an appropriate amount of water and detergent. Turn on the ultrasonic cleaning equipment for several minutes to allow the ultrasonic vibration to act on the brake pad to remove grease and dirt. This method is particularly suitable for cleaning hard-to-reach places. After cleaning, remove the brake pad and rinse it with clean water to ensure that all detergents and residues are removed. Finally, wipe the brake pad thoroughly with a dry cloth to prevent moisture residue. Also use a pneumatic spray gun or air pump to gently blow the surface of the brake pad to remove floating dust and particulate matter. You can also spray the brake pad cleaner on the surface of the brake pad, apply it evenly and let it soak for a few minutes to fully decompose the grease. When using a detergent, there should be no oily detergent to avoid affecting the braking performance.

[0024] The target speed is set, the test bench is driven to the target speed, braking pressure is applied to the brake pad, and the deceleration of the test bench is kept constant until the speed drops to zero.

[0025] In this embodiment, the target speed can be set to 60km / h, and the braking pressure is applied through the braking system. According to the design of the braking system, a predetermined braking pressure value can be set. Ensure that the applied braking pressure is appropriate so as to effectively reduce the speed of the test bench while maintaining a constant deceleration. The value of this braking pressure should be pre-set according to the design specifications of the braking system and the experimental requirements, and ensure its appropriateness to avoid unsatisfactory braking effect caused by being too high or too low. When the test bench reaches the set target speed, the predetermined braking pressure is immediately applied. The braking pressure can be selected according to the experimental design requirements, and can also be adjusted through the braking control system.

[0026] The thermal inertia attenuation coefficient is calculated based on the temperature-time series fitting exponential decay model in the cooling stage.

[0027] The specific steps of obtaining the thermal inertia attenuation coefficient include: The data in the temperature-time series of the cooling stage are smoothed by using a sliding window method to obtain smoothed data.

[0028] In this embodiment, a window size of 5 can be selected. The choice of window size will affect the smoothing effect. A larger window will lead to smoother results, but some details may be lost. Starting from the first data point of the temperature-time series, set the position of the current window. Calculate the average value of the temperature value in the current window. For the points at the front end of the window, the actual available data points can be used for averaging. Add the calculated average value to a new list. Move the window one data point and repeat the process of calculating the average until the entire temperature data sequence is traversed. At the beginning and end of the sequence, since there are not enough data points to fill the entire window, the following two strategies can be adopted: for the points at the front end of the window, all available data points can be used for averaging; at the back end of the window, the actual available data points are used. At the front and back ends of the window, fill with fixed values ​​to ensure that the length of the output list is consistent with the original data.

[0029] The thermal inertia attenuation coefficient was calculated by fitting the smoothed data using nonlinear least squares.

[0030] In this embodiment, the nonlinear least square method is used for fitting. In the fitting process, the optimization goal is to minimize the error between the fitting model and the actual observed temperature. Through iterative calculation, the model parameters are adjusted until the best fitting effect is found. The thermal inertia attenuation coefficient is obtained from the model parameters.

[0031] The surface temperature distribution diagram is subjected to feature extraction to obtain feature data. The feature data and thermal inertia attenuation coefficient are subjected to weighted processing to obtain input data.

[0032] The specific steps of extracting features from the surface temperature distribution map include: The temperature data of the brake pad width direction are extracted from the temperature distribution diagram, the maximum and minimum temperature values ​​are found, and the maximum temperature difference is calculated.

[0033] In this embodiment, the required width direction is determined, usually the center line of the brake pad or a specific width position. Then, all temperature data in this direction are extracted. In the extracted temperature data array, the maximum and minimum temperature values ​​in the array are found using a simple traversal or using built-in functions.

[0034] The temperature data along the friction contact direction of the brake pad is extracted from the temperature distribution diagram, a line is drawn along the friction contact direction of the brake pad, and the temperature values ​​at different positions of the line are recorded to obtain a temperature sequence, and then the temperature sequence is fitted using a regression method to obtain the temperature attenuation rate along the friction contact direction of the brake pad.

[0035] In this embodiment, the expression formula of temperature decay rate is:

[0036] in, is the temperature decay rate, is the temperature change value, is the distance change value.

[0037] The average temperature of the temperature distribution diagram is calculated, a temperature threshold is set, and then temperature points with a temperature higher than the average temperature are screened out according to the threshold. The areas of the temperature points are measured and summarized to obtain the total area of ​​the temperature points, and the proportion of areas with a temperature higher than the average temperature is calculated.

[0038] In this implementation, the expression formula of the average temperature is:

[0039] in, is the average temperature, is the total number of temperature points, For the The temperature value of the point.

[0040] The specific steps of weighted processing include: The thermal inertia attenuation coefficient and the characteristic data are normalized to obtain normalized data.

[0041] In this embodiment, a minimum-maximum normalization method may be used, and the expression formula is:

[0042] in, is the normalized data, is the original data point, is the minimum value in the original data set. is the maximum value in the original data set.

[0043] The weight distribution is set according to actual experience, and the normalized data is weighted to obtain input data.

[0044] A random forest network model is constructed, the random forest network model is optimized using a bitter fish optimization algorithm, and experimental data is input for training to obtain an optimal network model.

[0045] The specific steps to build a random forest network model include: Construct multiple decision trees, set the maximum depth of the decision trees and the minimum sample input required for the classification point, and obtain the initial network model.

[0046] In this embodiment, in order to prevent overfitting, the maximum depth of each decision tree can be set to 10. This means that when the decision tree is constructed, when the depth of the tree reaches 10, further node splitting will be stopped. The depth of the decision tree determines the number of data feature combinations that it can fit. When the depth is too large, the tree may learn noise or accidental patterns in the training data, resulting in overfitting. By limiting the maximum depth, the model is forced to ignore high-order feature interactions and focus on more generalized low-order features. A shallower tree structure means fewer nodes and splitting conditions, which significantly reduces the computational complexity of the training and prediction stages. At least 5 samples are required when each node is split. It is mandatory that the split operation must be based on sufficient data support to avoid statistical instability caused by too few samples. By requiring a minimum number of samples, the model is forced to make split decisions based on a wider range of samples, thereby learning more representative feature patterns. The minimum number of samples and the maximum depth jointly constrain the growth of the tree. Even if the maximum depth allows the tree to continue to grow, if the number of samples at a node is less than 5, the split will terminate early. This dual restriction ensures that the tree structure is neither too deep nor blindly split when the sample size is insufficient. By limiting the maximum depth and the minimum number of samples, the model avoids overfitting the noise in the training data and instead focuses on the essential laws in the data.

[0047] The initial network is trained using the experimental data to obtain a random forest network model.

[0048] The specific steps of obtaining the experimental data include: The braking experiment was conducted using different brake pads, and the thermal inertia attenuation coefficients of the different brake pads, the maximum temperature difference in the width direction of the brake pads, the temperature attenuation rate in the friction contact direction of the brake pads, the proportion of areas with temperatures higher than the average temperature, and the corresponding wear levels and abnormal types were recorded to obtain data 1. The data 1 was preprocessed to obtain experimental data.

[0049] In this embodiment, braking tests are performed on different brake pads one by one. After each test, the performance of each brake pad and the temperature change data at a specific time point are recorded. Multiple temperature sensors can be used to measure the temperature of the brake pad at different locations. The sensors cover the width direction and friction contact direction of the brake pad to obtain comprehensive temperature distribution data.

[0050] The specific steps of preprocessing the data 1 include: The data one is cleaned to remove outliers and duplicate values ​​in the data one, and the mean is used to replace the missing values ​​therein to obtain cleaned data.

[0051] In this embodiment, by drawing a box plot, outliers in the data set that are outside the upper and lower quartiles can be intuitively identified. These points are usually considered extreme values. The Z-score of each data point can also be calculated, and a threshold is usually set. If the Z-score of a data point exceeds the set range, it can be considered an outlier. Use the unique identifier of each data in the data set to determine which data is repeated. Based on these identifiers, remove duplicate entries to ensure that each record is unique. During the cleaning process, the mean is used to replace the missing data, and the mean is obtained by calculating the average value of the valid values ​​in the cleaned data set. Replacing missing values ​​with the mean can effectively reduce the deviation caused by missing values. When integrating and cleaning data, ensure the consistency of the format of all data, and unify the temperature value in degrees Celsius to facilitate subsequent analysis. At the same time, check the correctness of the numerical type to ensure that all numbers are stored as numerical types, not text or other types. Generate a new cleaned data set that does not contain outliers and duplicates, and the missing values ​​are filled with the mean, and all data formats are consistent.

[0052] The cleaning data is normalized to obtain experimental data.

[0053] In this embodiment, the cleaned data can be normalized using minimum-maximum normalization. The normalized data is converted to the same scale, eliminating the impact of inconsistent dimensions between different features. In a deep learning model, normalization can make the loss function smoother, thereby accelerating the learning process. Especially when processing extreme value data, the original features can cause numerical stability problems. By scaling the data to between 0 and 1, the stability of numerical operations can be improved. It helps to avoid overfitting of the model. By limiting the training data to the same range, the generalization ability of the model on unknown data can be improved.

[0054] The specific steps of the Bitter Fish Optimization Algorithm for optimizing the random forest network include: The mean square error is used as the fitness function of the random forest network model.

[0055] In this embodiment, the mean square error expression formula is:

[0056] in, is the mean square error, is the actual value, i.e. The actual output in samples is is the predicted value, i.e., the model The output predicted on samples.

[0057] Initialize the population and randomly generate individual positions of bitter fish. Each bitter fish individual represents a hyperparameter group of the random forest network model.

[0058] An iterative mechanism is set up. Each time a new population is formed, the perception range and hunger step threshold of the individual bitter fish are set according to the environmental adaptation mechanism.

[0059] In this embodiment, the environmental adaptation mechanism is to gradually reduce the perception range of individual bitter fish as the number of iterations increases. Improve the selectivity of individual bitter fish in resource-scarce conditions and improve their efficiency in surviving in the environment. Each iteration can be set to reduce the perception range by a certain percentage, so that the individual can still effectively capture resources when adapting to a smaller resource area. In each iteration, the hunger step threshold is gradually increased. This means that when the individual bitter fish is looking for food, it will increase the number of steps it moves to ensure that it can move more sustainably in an environment with scarce resources. An increasing ratio can be set to extend the time the individual swims in the environment.

[0060] Calculate the fitness function of the individual bitter fish in the initialized population, and update the position of each individual bitter fish according to the behavioral strategy to obtain population one.

[0061] The fitness value of each individual in the population is calculated. If the output fitness value is higher than the preset fitness threshold, the optimal hyperparameter is output. Otherwise, the iteration is continued until the fitness value is higher than the preset fitness threshold or the maximum number of iterations is reached to obtain the optimal hyperparameter.

[0062] The behavioral strategies include: The individual bitter fish compares its own fitness with the average fitness value of the individual bitter fish within the perception range. If it is better than the average fitness value of the individual bitter fish within the perception range, the position of the individual bitter fish is updated according to local foraging.

[0063] In this embodiment, the local foraging expression formula is:

[0064] in, The updated position of the bitter fish individual. For the bitter fish in the individual's current position, is the step size factor, is a random number between 0 and 1. It is the individual position with the best fitness within the perception range of the bitter fish.

[0065] If the number of hunger steps of the bitter fish individual reaches the hunger step threshold, the bitter fish individual updates its position according to random migration.

[0066] In this embodiment, the random migration expression formula is:

[0067] in, The updated position of the bitter fish individual. and are the upper and lower bounds of the search space, A random number between 0 and 1.

[0068] If the bitter fish individual does not meet the conditions of local foraging and random migration, the bitter fish individual will update the individual position through group cooperation. When the positions of all bitter fish individuals are updated, population one is obtained.

[0069] In this embodiment, the group collaboration expression formula is:

[0070] in, The updated position of the bitter fish individual. is the collaboration factor, is a random number between 0 and 1. is the historical global optimal position, For bitter fish in individual current location.

[0071] Input the input data into the optimal network model to obtain the detection results.

[0072] Example 1: Use a cleaner and a brush to remove the oil and dust on the surface of the brake pad. Set the test bench to 60km / h. After reaching the target speed, apply the brake pressure and maintain the deceleration at -5m / s² until the speed drops to zero. Record the surface temperature distribution of the brake pad after braking and the temperature-time series of the cooling stage. Use the sliding window method to smooth the collected temperature-time series data. The window size is set to 5 seconds. Apply the nonlinear least squares method to fit the smoothed data to obtain the thermal inertia attenuation coefficient, and the calculated result is 0.85. Extract the temperature data in the width direction from the temperature distribution diagram, find the maximum temperature of 350°C and the minimum temperature of 200°C, and calculate the maximum temperature difference of 150°C. Extract the temperature data in the friction contact direction, plot the temperature series and apply the regression method to obtain the temperature attenuation rate of 0.5°C / m. Calculate the average value of the temperature distribution to be 275°C), set the temperature threshold to 300°C, filter out the temperature points above this value, measure the total area of ​​the temperature points and calculate the area proportion to be 20%. The thermal inertia attenuation coefficient is 0.85 and the feature data is normalized. After normalization, the thermal inertia attenuation coefficient is 0.5 and the feature data is 0.6. The weights are set according to experience, the weight of the thermal inertia attenuation coefficient is 0.4, the weight of the feature data is 0.6, and the input data is 0.54. Construct 10 decision trees, set the maximum depth to 10, and the minimum number of sample splits to 5. Use the collected experimental data to train the initial network and obtain a random forest network model. Clean the experimental data, remove outliers, records with temperature values ​​exceeding 500°C and duplicate values, use the mean to replace the missing value 0.7, and use the mean of the feature 0.75 instead. Normalize the cleaned data to obtain the final experimental data. Use the mean square error as the fitness function, initialize the population, and generate 10 bitter fish individuals, each representing a set of hyperparameters. An iteration mechanism is set up to calculate the fitness of each individual and update the position until a fitness value is found that is higher than the preset threshold (0.95) or the maximum number of iterations (100) is reached to obtain the optimal hyperparameters.

[0073] The present invention constructs a random forest network model, uses a bitter fish optimization algorithm to optimize the random network model, inputs experimental data for training, obtains an optimal network model, performs weighted processing on the thermal inertia attenuation coefficient and characteristic data obtained from the brake pad experiment, obtains input data, and inputs the input data into the optimal network model to obtain a detection result. The accuracy of brake pad detection is improved and safety hazards are reduced.

[0074] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0075] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting wear of automobile brake pads, characterized in that: include: Perform a braking test on the brake pad, and collect a surface temperature distribution diagram of the brake pad after braking and a temperature-time series in a cooling stage; According to the temperature-time series of the cooling stage, an exponential decay model is fitted to obtain a thermal inertia decay coefficient; Extracting features from the surface temperature distribution map to obtain feature data; performing weighted processing on the feature data and the thermal inertia attenuation coefficient to obtain input data; Constructing a random forest network model, optimizing the random forest network model using a bitter fish optimization algorithm, and inputting experimental data for training to obtain an optimal network model; Input the input data into the optimal network model to obtain the detection results.

2. A method for detecting wear of automobile brake pads according to claim 1, characterized in that: The specific steps of performing a brake test on the brake pad include: Cleaning the brake pad to remove surface grease; The target speed is set, the test bench is driven to the target speed, braking pressure is applied to the brake pad, and the deceleration of the test bench is kept constant until the speed drops to zero.

3. The method for detecting wear of automobile brake pads according to claim 1, characterized in that: The specific steps of obtaining the thermal inertia attenuation coefficient include: Using a sliding window method to smooth the data in the temperature-time series of the cooling stage to obtain smoothed data; The thermal inertia attenuation coefficient was calculated by fitting the smoothed data using nonlinear least squares.

4. The method for detecting wear of automobile brake pads according to claim 1, characterized in that: The specific steps of extracting features from the surface temperature distribution map include: Extract the temperature data in the width direction of the brake pad from the temperature distribution diagram to find the maximum and minimum temperature values, and calculate the maximum temperature difference; Extracting temperature data along the friction contact direction of the brake pad from the temperature distribution diagram, drawing a line along the friction contact direction of the brake pad, and recording temperature values ​​at different positions of the line to obtain a temperature sequence, and then fitting the temperature sequence using a regression method to obtain a temperature attenuation rate along the friction contact direction of the brake pad; The average temperature of the temperature distribution diagram is calculated, a temperature threshold is set, and then the temperature points with a temperature higher than the average temperature are screened out according to the threshold, the areas of the temperature points are measured and summarized to obtain the total area of ​​the temperature points, and the proportion of the area with a temperature higher than the temperature average is calculated.

5. The method for detecting wear of automobile brake pads according to claim 1, characterized in that: The specific steps of weighted processing include: Normalizing the thermal inertia attenuation coefficient and the characteristic data to obtain normalized data; The weight distribution is set according to actual experience, and the normalized data is weighted to obtain input data.

6. The method for detecting wear of automobile brake pads according to claim 1, characterized in that: The specific steps of building a random forest network model include: Construct multiple decision trees, and set the maximum depth of the multiple decision trees and the minimum sample input required for the classification point to obtain an initial network model; The initial network is trained using the experimental data to obtain a random forest network model.

7. The method for detecting wear of automobile brake pads according to claim 4, characterized in that: The specific steps of obtaining the experimental data include: A braking experiment is performed using different brake pads, and the thermal inertia attenuation coefficients of the different brake pads, the maximum temperature difference in the width direction of the brake pad, the temperature attenuation rate in the friction contact direction of the brake pad, the proportion of areas with temperatures higher than the average temperature, and the corresponding wear levels and abnormality types are recorded to obtain data one; the data one is preprocessed to obtain experimental data.

8. The method for detecting wear of automobile brake pads according to claim 5, characterized in that: The specific steps of preprocessing the data 1 include: Cleaning the data one, removing outliers and duplicate values ​​in the data one, and replacing missing values ​​therein with the mean to obtain cleaned data; The cleaning data is normalized to obtain experimental data.

9. The method for detecting wear of automobile brake pads according to claim 4, characterized in that: The specific steps of the Bitter Fish Optimization Algorithm for optimizing the random forest network include: The mean square error is used as the fitness function of the random forest network model; Initialize the population and randomly generate the positions of individual bitter fish. Each individual bitter fish represents a hyperparameter group of the random forest network model. Set up an iterative mechanism. Each time a new population is formed, the perception range and hunger step threshold of the individual bitter fish are set according to the environmental adaptation mechanism. Calculate the fitness function of the individual bitter fish in the initialized population, and update the position of each individual bitter fish according to the behavior strategy to obtain population one; The fitness value of each individual in the population is calculated. If the output fitness value is higher than the preset fitness threshold, the optimal hyperparameter is output. Otherwise, the iteration is continued until the fitness value is higher than the preset fitness threshold or the maximum number of iterations is reached to obtain the optimal hyperparameter.

10. The method for detecting wear of automobile brake pads according to claim 9, characterized in that: The behavioral strategies include: The individual bitter fish compares its own fitness with the average fitness value of the individual bitter fish within the sensing range. If it is better than the average fitness value of the individual bitter fish within the sensing range, the position of the individual bitter fish is updated according to local foraging; If the number of hungry steps of the bitter fish individual reaches the threshold of hungry steps, the bitter fish individual updates its position according to random migration; If the bitter fish individual does not meet the conditions of local foraging and random migration, the bitter fish individual will update its individual position through group collaboration. When the positions of all bitter fish individuals are updated, population one is obtained.

Images