Vehicle and control method thereof

Abstract

The invention discloses a vehicle and a control method thereof. The method comprises the steps that the temperature of an electronic parking brake caliper is determined; determining a target cooling mode according to the temperature of the electronic parking brake calipers, the vehicle running parameters, the vehicle braking parameters, the parameters of the environment where the vehicle is located and the vehicle configuration parameters; and cooling a brake execution part of the vehicle according to the target cooling mode. According to the method, the temperature of the electronic parking brake calipers is determined, the target cooling mode is selected according to the temperature of the electronic parking brake calipers and various parameters of the vehicle, the brake execution component is precisely cooled, and the problems that the brake performance is reduced and the service life of the system is shortened due to the high temperature of the calipers are effectively solved; the safety and reliability of the braking system are remarkably improved, meanwhile, the applicability and efficiency of cooling measures are optimized, and the method is particularly suitable for complex and changeable working conditions.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of vehicles, and particularly relate to a vehicle and a control method thereof. BACKGROUND

[0002] The temperature of the EPB (Electronic Parking Brake) caliper is prone to be too high when high-strength or long-time braking, which not only leads to a decline in braking performance and shortens the service life of the braking system, but also causes safety hazards. However, in the related art, the cooling method of the braking system is often single, difficult to adapt to complex working conditions, and unable to effectively solve the safety problems caused by high temperature of the caliper. SUMMARY

[0003] Embodiments of the present application provide a vehicle and a control method thereof, aiming to improve the cooling method of the braking system, which is often single, difficult to adapt to complex working conditions, and unable to effectively solve the safety problems caused by high temperature of the caliper.

[0004] To achieve the above-mentioned purpose, an embodiment of the first aspect of the present application provides a control method of a vehicle, the method comprising: determining an electronic parking brake caliper temperature; determining a target cooling mode according to the electronic parking brake caliper temperature, vehicle driving parameters, vehicle braking parameters, vehicle environment parameters and vehicle configuration parameters; and cooling the braking execution components of the vehicle according to the target cooling mode.

[0005] The present application determines the electronic parking brake caliper temperature, and selects the target cooling mode according to the electronic parking brake caliper temperature and various parameters of the vehicle to accurately cool the braking execution components, effectively solves the problems of decline in braking performance and shortening of system life caused by high temperature of the caliper, significantly improves the safety and reliability of the braking system, and optimizes the applicability and efficiency of the cooling measures, especially suitable for complex and variable working conditions.

[0006] According to an embodiment of the present application, the target cooling mode is determined according to the electronic parking brake caliper temperature, vehicle driving parameters, vehicle braking parameters, vehicle environment parameters and vehicle configuration parameters, comprising: respectively obtaining scores corresponding to the electronic parking brake caliper temperature, vehicle driving parameters, vehicle braking parameters, vehicle environment parameters and vehicle configuration parameters; determining a braking state score value based on the sum of the products of all scores and corresponding weight coefficients; and determining the target cooling mode according to the score interval in which the braking state score value is located.

[0007] According to one embodiment of the present application, the target cooling mode is determined according to the score interval in which the braking state score value is located, including: in the case that the braking state score value is less than or equal to the first braking state score threshold, determining the target cooling mode as the first cooling mode, wherein the first cooling mode is used to represent air cooling of the braking execution component of the vehicle; in the case that the braking state score value is greater than the first braking state score threshold and less than or equal to the second braking state score threshold, determining the target cooling mode as the second cooling mode, wherein the second cooling mode is used to represent liquid cooling of the braking execution component of the vehicle; in the case that the braking state score value is greater than the second braking state score threshold and less than or equal to the third braking state score threshold, determining the target cooling mode as the third cooling mode, wherein the third cooling mode is used to represent air cooling and liquid cooling of the braking execution component of the vehicle.

[0008] According to one embodiment of the present application, the above method further includes: in the case that the braking state score value is greater than the third braking state score threshold, controlling the vehicle to perform an alarm.

[0009] The present application can accurately select a cooling mode according to the actual temperature of the caliper and the working condition of the vehicle by intelligently selecting a target cooling mode according to the score interval in which the braking state score value is located, thereby avoiding excessive cooling or insufficient cooling to a certain extent, improving the safety and reliability of the braking system, and prolonging the service life of the braking system.

[0010] According to one embodiment of the present application, the target cooling mode is determined according to the electronic parking brake caliper temperature, the vehicle driving parameter, the vehicle braking parameter, the vehicle environment parameter and the vehicle configuration parameter, including: inputting the electronic parking brake caliper temperature, the vehicle driving parameter, the vehicle braking parameter, the vehicle environment parameter and the vehicle configuration parameter into a preset cooling mode determination model to output the target cooling mode.

[0011] According to one embodiment of the present application, the above method further includes: obtaining historical electronic parking brake caliper temperature, historical vehicle driving parameter, historical vehicle braking parameter, historical vehicle environment parameter, historical vehicle configuration parameter and historical cooling mode; constructing a preset cooling mode determination model training set according to the historical electronic parking brake caliper temperature, the historical vehicle driving parameter, the historical vehicle braking parameter, the historical vehicle environment parameter, the historical vehicle configuration parameter and the historical cooling mode, and training the preset cooling mode determination model by using the preset cooling mode determination model training set; The preset cooling mode determination model is trained by using the preset cooling mode determination model training set, including: inputting any input data in the preset cooling mode determination model training set into an initial preset cooling mode determination model to output a predicted cooling mode; calculating a discriminative loss based on the predicted cooling mode and a corresponding historical cooling mode in the preset cooling mode determination model training set to obtain a first calculation result; updating the model parameters of the initial preset cooling mode determination model by using the first calculation result until the updated initial preset cooling mode determination model meets a first preset convergence condition to obtain the preset cooling mode determination model.

[0012] According to an embodiment of the present application, the vehicle driving parameter includes at least one of a driving mode and a load, the vehicle braking parameter includes at least one of a braking frequency and a braking wear degree, and the vehicle environment parameter includes an altitude.

[0013] According to an embodiment of the present application, the electronic parking brake caliper temperature is determined by: inputting the vehicle driving parameter, the vehicle braking parameter and the vehicle environment parameter into a preset electronic parking brake caliper temperature estimation model to output the electronic parking brake caliper temperature; wherein the vehicle driving parameter includes a vehicle speed, the vehicle braking parameter includes a braking force, a braking time and a braking frequency, and the vehicle environment parameter includes an external environment temperature.

[0014] According to an embodiment of the present application, the method further includes: obtaining historical vehicle speed, historical braking force, historical braking time, historical braking frequency, historical external environment temperature and historical electronic parking brake caliper temperature; constructing a preset electronic parking brake caliper temperature estimation model training set according to the historical vehicle speed, the historical braking force, the historical braking time, the historical braking frequency, the historical external environment temperature and the historical electronic parking brake caliper temperature, and training a preset electronic parking brake caliper temperature estimation model by using the preset electronic parking brake caliper temperature estimation model training set. The preset electronic parking brake caliper temperature estimation model is trained by using the preset electronic parking brake caliper temperature estimation model training set, including: inputting any input data in the preset electronic parking brake caliper temperature estimation model training set into an initial preset electronic parking brake caliper temperature estimation model to output a predicted electronic parking brake caliper temperature; calculating a discriminative loss based on the predicted electronic parking brake caliper temperature and a corresponding historical electronic parking brake caliper temperature in the preset electronic parking brake caliper temperature estimation model training set to obtain a second calculation result; updating the model parameters of the initial preset electronic parking brake caliper temperature estimation model by using the second calculation result until the updated initial preset electronic parking brake caliper temperature estimation model meets a second preset convergence condition to obtain the preset electronic parking brake caliper temperature estimation model.

[0015] Thus, the powerful data fitting capability of the preset electronic parking brake caliper temperature estimation model is utilized to realize high-precision temperature prediction, which can significantly improve the estimation accuracy of the electronic parking brake caliper temperature. At the same time, the end-to-end learning method can effectively reduce the modeling complexity and avoid the cumbersome model establishment and parameter calibration process. In addition, the generalization ability of the model can enhance the robustness of the system to external interference, so that it can still operate stably in complex environments. Finally, by designing an efficient neural network structure and inference algorithm, the real-time performance of the system is optimized to ensure that the safety control requirements are met.

[0016] To achieve the above object, the fourth aspect of the present application provides a vehicle, comprising a memory, a processor, and a control program of the vehicle stored in the memory and executable on the processor. When the processor executes the control program of the vehicle, the control method of the vehicle is realized. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 Flowchart of the control method of the vehicle according to some embodiments of the present application; Figure 2 Structure diagram of the electronic parking brake caliper temperature estimation system according to some embodiments of the present application; Figure 3 Flowchart of the control method of the vehicle according to some embodiments of the present application; Figure 4 Block diagram of the vehicle according to some embodiments of the present application. DETAILED DESCRIPTION

[0018] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference signs represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present application, and cannot be understood as a limitation of the present application.

[0019] The vehicle and its control method according to the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0020] Figure 1 Flowchart of the control method of the vehicle according to some embodiments of the present application. Referring to Figure 1 , the control method of the vehicle according to the embodiments of the present application can comprise the following steps: S110, determining the electronic parking brake caliper temperature.

[0021] Specifically, the temperature of the electronic parking brake caliper can be acquired by a thermocouple or a resistance thermometer arranged on the electronic parking brake caliper; or the temperature of the electronic parking brake caliper can be determined by acquiring vehicle driving parameters, vehicle braking parameters and vehicle environment parameters, and determining the temperature of the electronic parking brake caliper according to the vehicle driving parameters, the vehicle braking parameters and the vehicle environment parameters, for example, by querying a two-dimensional relationship mapping table between combinations of the vehicle driving parameters, the vehicle braking parameters and the vehicle environment parameters and the temperature of the electronic parking brake caliper, wherein the two-dimensional relationship mapping table includes a plurality of combinations of the vehicle driving parameters, the vehicle braking parameters and the vehicle environment parameters and the temperature of the electronic parking brake caliper corresponding to each combination of vehicle speed, braking force, braking time, braking frequency and external environment temperature.

[0022] It should be noted that the method for determining the temperature of the electronic parking brake caliper is not specifically limited here.

[0023] S120, determining a target cooling mode according to the temperature of the electronic parking brake caliper, the vehicle driving parameters, the vehicle braking parameters, the vehicle environment parameters and the vehicle configuration parameters.

[0024] Specifically, after determining the temperature of the electronic parking brake caliper, the vehicle driving parameters, the vehicle driving parameters, the vehicle braking parameters, the vehicle environment parameters and the vehicle configuration parameters are collected to determine the actual working condition of the vehicle, and the target cooling mode is determined according to the temperature of the electronic parking brake caliper, the vehicle driving parameters, the vehicle driving parameters, the vehicle braking parameters, the vehicle environment parameters and the vehicle configuration parameters. For example, the temperature of the electronic parking brake caliper, the vehicle driving parameters, the vehicle driving parameters, the vehicle braking parameters, the vehicle environment parameters and the vehicle configuration parameters can be input into a preset braking state scoring model to output a braking state score value, and the target cooling mode can be determined by looking up a two-dimensional relationship mapping table between the braking state score value and the cooling mode, wherein the two-dimensional relationship mapping table includes a plurality of braking state score values and a cooling mode corresponding to each braking state score value.

[0025] S130, cooling the braking execution component of the vehicle according to the target cooling mode.

[0026] Specifically, after determining the target cooling mode, the braking execution component of the vehicle, such as the brake disc and the electronic parking brake caliper of the vehicle, is cooled according to the target cooling mode.

[0027] The application determines the temperature of the electronic parking brake caliper, selects a target cooling mode according to the temperature of the electronic parking brake caliper, various parameters of the vehicle, and precisely cools the brake execution component, effectively solves the problem of brake performance decline and system life shortening caused by high caliper temperature, significantly improves the safety and reliability of the brake system, and optimizes the applicability and efficiency of the cooling measures, especially for complex and variable working conditions.

[0028] In some embodiments, the target cooling mode is determined according to the temperature of the electronic parking brake caliper, vehicle driving parameters, vehicle braking parameters, vehicle environment parameters, and vehicle configuration parameters, including: obtaining the scores corresponding to the temperature of the electronic parking brake caliper, vehicle driving parameters, vehicle braking parameters, vehicle environment parameters, and vehicle configuration parameters, respectively; determining a brake state score value based on the sum of the products of all scores and corresponding weight coefficients; determining the target cooling mode according to the score interval in which the brake state score value is located.

[0029] Specifically, after obtaining the temperature of the electronic parking brake caliper, vehicle driving parameters, vehicle braking parameters, vehicle environment parameters, and vehicle configuration parameters, the parameter intervals of the temperature of the electronic parking brake caliper, vehicle driving parameters, vehicle braking parameters, vehicle environment parameters, and vehicle configuration parameters are determined, the corresponding scores of each parameter are determined according to the parameter intervals, and the sum of the products of all scores and corresponding weight coefficients is calculated to determine the brake state score value.

[0030] After determining the brake state score value, the target cooling mode can be determined by determining the score interval in which the brake state score value is located. For example, if the brake state score value is in a lower score interval, it means that the brake execution component is in a relatively safe state and the temperature is relatively low, so it is determined that no overly complex cooling measures are needed to cool the brake execution component of the vehicle, such as air cooling; if the brake state score value is in a medium score interval, it means that the temperature of the brake execution component is relatively high, so it is determined that more effective cooling measures are needed to cool the brake execution component of the vehicle, such as liquid cooling; if the brake state score value is in a higher score interval, it means that the brake execution component is in a high-risk state and the temperature is very high, so it is determined that the strongest cooling measures are needed to cool the brake execution component of the vehicle, such as air cooling and liquid cooling.

[0031] In some embodiments, the target cooling mode is determined according to a score interval in which the braking state score value falls, including: in a case where the braking state score value is less than or equal to a first braking state score threshold, determining the target cooling mode as a first cooling mode, wherein the first cooling mode is used to represent air cooling of the braking execution component of the vehicle; in a case where the braking state score value is greater than the first braking state score threshold and less than or equal to a second braking state score threshold, determining the target cooling mode as a second cooling mode, wherein the second cooling mode is used to represent liquid cooling of the braking execution component of the vehicle; in a case where the braking state score value is greater than the second braking state score threshold and less than or equal to a third braking state score threshold, determining the target cooling mode as a third cooling mode, wherein the third cooling mode is used to represent air cooling and liquid cooling of the braking execution component of the vehicle. In a case where the braking state score value is greater than the third braking state score threshold, controlling the vehicle to perform an alarm. The first braking state score threshold, the second braking state score threshold and the third braking state score threshold can be calibrated according to actual conditions, for example, the first braking state score threshold can be 35 points, the second braking state score threshold can be 64 points, and the third braking state score threshold can be 89 points, which are not limited here.

[0032] Specifically, the target cooling mode can include a first cooling mode, a second cooling mode and a third cooling mode, the first cooling mode is used to represent air cooling, the second cooling mode is used to represent liquid cooling, and the third cooling mode is used to represent air cooling and liquid cooling. It should be noted that the cooling effect of the second cooling mode is better than that of the first cooling mode, and the cooling effect of the third cooling mode is better than that of the second cooling mode.

[0033] For example, if the braking state score value is less than or equal to the first braking state score threshold, it indicates that the braking execution component is in a relatively safe state and the temperature is relatively low, and no overly complex cooling measures are needed, so the target cooling mode is determined as the first cooling mode; if the braking state score value is greater than the first braking state score threshold and less than or equal to the second braking state score threshold, it indicates that the temperature of the braking execution component is relatively high, and more effective cooling measures are needed, so the target cooling mode is determined as the second cooling mode; if the braking state score value is greater than the second braking state score threshold and less than or equal to the third braking state score threshold, it indicates that the braking execution component is in a high-risk state and the temperature is very high, and the strongest cooling measures are needed, so the target cooling mode is determined as the third cooling mode; if the braking state score value is greater than the third braking state score threshold, it indicates that the temperature of the electronic parking brake caliper is extremely high, and the braking execution component may face serious safety hazards, so the vehicle needs to be controlled to perform an alarm, for example, a red or yellow warning light is lit on the vehicle instrument panel to clearly prompt the driver that the temperature of the braking execution component is too high.

[0034] The application can intelligently select a target cooling mode according to a score interval of a braking state score value, accurately select a cooling mode according to an actual temperature of a caliper and a vehicle working condition, avoid excessive cooling or insufficient cooling to a certain extent, improve safety and reliability of a braking system, and prolong a service life of the braking system.

[0035] In some embodiments, determining the target cooling mode according to the electronic parking brake caliper temperature, the vehicle driving parameter, the vehicle braking parameter, the vehicle environment parameter and the vehicle configuration parameter includes: inputting the electronic parking brake caliper temperature, the vehicle driving parameter, the vehicle braking parameter, the vehicle environment parameter and the vehicle configuration parameter into a preset cooling mode determination model to output the target cooling mode.

[0036] Specifically, after obtaining the electronic parking brake caliper temperature, the vehicle driving parameter, the vehicle braking parameter, the vehicle environment parameter and the vehicle configuration parameter, the electronic parking brake caliper temperature, the vehicle driving parameter, the vehicle braking parameter, the vehicle environment parameter and the vehicle configuration parameter can be input into a preset cooling mode determination model to output the target cooling mode.

[0037] In some embodiments, the above method further includes: obtaining historical electronic parking brake caliper temperature, historical vehicle driving parameter, historical vehicle braking parameter, historical vehicle environment parameter, historical vehicle configuration parameter and historical cooling mode; constructing a preset cooling mode determination model training set according to the historical electronic parking brake caliper temperature, the historical vehicle driving parameter, the historical vehicle braking parameter, the historical vehicle environment parameter, the historical vehicle configuration parameter and the historical cooling mode, and training the preset cooling mode determination model using the preset cooling mode determination model training set. Training the preset cooling mode determination model using the preset cooling mode determination model training set includes: inputting any input data in the preset cooling mode determination model training set into an initial preset cooling mode determination model to output a predicted cooling mode; calculating a discriminative loss based on the predicted cooling mode and a corresponding historical cooling mode in the preset cooling mode determination model training set to obtain a first calculation result; updating model parameters of the initial preset cooling mode determination model using the first calculation result until the updated initial preset cooling mode determination model meets a first preset convergence condition to obtain the preset cooling mode determination model.

[0038] Specifically, the historical vehicle driving parameter includes at least one of a historical driving mode and a historical load, the historical vehicle braking parameter includes at least one of a historical braking frequency and a historical braking wear degree, the historical vehicle environment parameter includes a historical altitude, and the historical vehicle configuration parameter includes at least one of a historical vehicle type, a historical caliper material and a historical number of brake discs.

[0039] For example, when the historical vehicle driving parameter includes a historical driving mode, the historical vehicle braking parameter includes a historical braking frequency, the historical environment parameter includes a historical altitude, and the historical vehicle configuration parameter includes a historical vehicle type, the historical driving mode, the historical braking frequency, the historical altitude, the historical vehicle type, and a corresponding historical cooling mode are preprocessed, for example, to perform outlier cleaning, noise processing, and normalization processing. Then, a preset cooling mode determination model training set is constructed according to the preprocessed data, and a preset cooling mode determination model is trained using the preset cooling mode determination model training set. Specifically, any input data in the preset cooling mode determination model training set is input into an initial preset cooling mode determination model for forward propagation to obtain a corresponding predicted cooling mode. Then, the predicted cooling mode and the historical cooling mode corresponding to the input data are used to calculate a discriminative loss to obtain a first calculation result. Then, the gradient of each parameter of the loss function is calculated by back propagation, and the model parameters of the initial preset cooling mode determination model are updated according to the gradient using a preset optimization algorithm (such as Adam). The above steps are repeated until the updated preset cooling mode determination model satisfies a first preset convergence condition, for example, the first calculation result reaches a preset loss threshold or the number of iterations reaches a preset iteration number threshold, to obtain a cooling mode determination model for determining a cooling mode.

[0040] For example, when the historical vehicle driving parameter includes a historical driving mode and a historical load, the historical vehicle braking parameter includes a historical braking frequency and a historical braking wear degree, the historical environment parameter includes a historical altitude, the historical vehicle configuration parameter includes a historical vehicle type, a historical caliper material, and a historical number of brake discs, and the historical cooling mode is preprocessed, for example, to perform outlier cleaning, noise processing, and normalization processing. Then, a preset cooling mode determination model training set is constructed according to the preprocessed data, and a preset cooling mode determination model is trained using the preset cooling mode determination model training set. The specific training process has been described in detail in the above embodiment, and will not be repeated here.

[0041] In some embodiments, the vehicle driving parameter includes at least one of a driving mode and a load, the vehicle braking parameter includes at least one of a braking frequency and a braking wear degree, the vehicle environment parameter includes an altitude, and the vehicle configuration parameter includes at least one of a vehicle type, a caliper material, and a number of brake discs.

[0042] Specifically, the vehicle driving parameter includes at least one of a driving mode and a load, wherein the driving mode can be read by an electronic control unit of the vehicle, and the load can be acquired by a pressure sensor arranged in a suspension system or a tire of the vehicle; the vehicle braking parameter includes at least one of a braking frequency and a braking wear degree, wherein the braking frequency can be calculated by analyzing a braking operation timestamp or a brake pedal sensor data recorded by the electronic control unit, and the braking wear degree includes a brake disc wear degree and a caliper wear degree, which can be acquired according to an embedded resistance sensor or a capacitive sensor; the vehicle environment parameter includes an altitude, which can be acquired by a vehicle positioning system; and the vehicle configuration parameter includes at least one of a vehicle type, a caliper material and a number of brake discs, which can be read by the electronic control unit of the vehicle.

[0043] The scores corresponding to the electronic parking brake caliper temperature, the vehicle driving parameter (for example, at least one of the driving mode and the load), the vehicle braking parameter (for example, at least one of the braking frequency and the braking wear degree), the vehicle environment parameter (for example, the altitude) and the vehicle configuration parameter (at least one of the vehicle type, the caliper material and the number of brake discs) are respectively acquired, and the sum of the products of all the scores and the corresponding weight coefficients is calculated to determine the braking state score value.

[0044] In the case of acquiring the electronic parking brake caliper temperature, the load, the braking wear degree, the altitude and the number of brake discs, the scores corresponding to the electronic parking brake caliper temperature, the load, the braking wear degree, the altitude and the number of brake discs are determined according to the parameter intervals of the electronic parking brake caliper temperature, the load, the braking wear degree, the altitude and the number of brake discs, and the sum of the products of all the scores and the corresponding weight coefficients is calculated to determine the braking state score value.

[0045] For example, the scores and the weight coefficients corresponding to the parameter intervals of the electronic parking brake caliper temperature, the load, the braking wear degree, the altitude and the number of brake discs are shown in Table 1: Table 1

[0046] In the case of the electronic parking brake caliper temperature being 110°C, the altitude being 1500m, the braking wear degree being good, the vehicle load being full load and the number of brake discs being 2, the braking state score value is braking state score value = 50x30% + 50x20% + 20x20% + 100x20% + 20x10% = 51 points. The braking state score value is greater than the first braking state score threshold (for example, 35 points) and less than or equal to the second braking state score threshold (for example, 64 points), so the target cooling mode can be determined as the second cooling mode.

[0047] In the case of acquiring the electronic parking brake caliper temperature, the driving mode, the load, the brake frequency, the brake wear degree, the altitude, the vehicle type, the caliper material and the number of brake discs, according to the parameter interval of the electronic parking brake caliper temperature, the driving mode, the load, the brake frequency, the brake wear degree, the altitude, the vehicle type, the caliper material and the number of brake discs, the corresponding scores of each parameter are determined, and the sum of the products of all scores and corresponding weight coefficients is calculated to determine the brake state score value.

[0048] For example, the corresponding scores of the parameter intervals of the electronic parking brake caliper temperature, the driving mode, the load, the brake frequency, the brake wear degree, the altitude, the vehicle type, the caliper material and the number of brake discs and the weight coefficients are shown in Table 2: Table 2

[0049] In the case of the electronic parking brake caliper temperature being 110℃, the altitude being 1500m, the caliper material being aluminum alloy, the brake wear degree being good, the vehicle type being heavy truck, the vehicle load being full load, the number of brake discs being 2, the driving mode being comfortable and the brake frequency being moderate, the brake state score value is brake state score value = 50x30% + 50x8% + 100x8% + 20x10% + 100x8% + 100x8% + 20x4% + 10x12% + 50x12% = 53 points. The brake state score value is greater than the first brake state score threshold (e.g. 35 points) and less than or equal to the second brake state score threshold (e.g. 64 points), so the target cooling mode can be determined as the second cooling mode.

[0050] In the related art, the measurement and estimation methods of the electronic parking brake caliper temperature mainly include direct measurement method, model estimation method, signal correlation method and hybrid method. The direct measurement method obtains the temperature by installing a thermocouple or a resistance thermometer on the caliper, which has high accuracy, but has problems such as high cost, sensors susceptible to environmental interference, complex wiring, etc.; the model estimation method estimates the temperature based on the thermal model of the caliper and parameters such as motor current and voltage, without additional sensors, but the model accuracy depends on parameter calibration, and it is difficult to establish and calibrate, and it is difficult to accurately reflect the dynamic temperature change of the caliper; the signal correlation method estimates by analyzing the relationship between motor winding temperature, brake torque, brake frequency and caliper temperature, but the accuracy is low, and it is difficult to cope with complex braking conditions; the hybrid method combines multiple methods to improve estimation accuracy and reliability, but still faces challenges in model complexity, parameter calibration, real-time performance, etc. These methods generally have limited accuracy, high model complexity, poor robustness and insufficient real-time performance, making it difficult to achieve high-precision estimation of the caliper temperature, accurately reflect its dynamic changes, and be susceptible to external environmental interference and parameter drift. Most methods have poor real-time performance, making it difficult to meet the requirements of safety control.

[0051] Based on this, the application trains a preset electronic parking brake caliper temperature estimation model by collecting historical vehicle speed, historical braking force, historical braking time, historical braking frequency, historical external environment temperature and historical electronic parking brake caliper temperature, and determines the electronic parking brake caliper temperature by using the preset electronic parking brake caliper temperature estimation model.

[0052] In some embodiments, the electronic parking brake caliper temperature is determined by inputting the vehicle driving parameters, vehicle braking parameters and vehicle environment parameters into the preset electronic parking brake caliper temperature estimation model to output the electronic parking brake caliper temperature; wherein the vehicle driving parameters include vehicle speed, the vehicle braking parameters include braking force, braking time and braking frequency, and the vehicle environment parameters include external environment temperature.

[0053] Specifically, the vehicle driving parameters include vehicle speed, which can be acquired by a speed sensor arranged at the wheel; the vehicle braking parameters include braking force, braking time and braking frequency, wherein the braking force can be calculated by an electronic control unit of the vehicle, a brake pressure sensor or a wheel speed sensor, the braking time can be determined by means of a brake operation time stamp recorded by the electronic control unit, a brake pedal sensor or a wheel speed sensor monitoring wheel speed change, and the braking frequency can be calculated by analyzing brake operation time stamp recorded by the electronic control unit or brake pedal sensor data; and the vehicle environment parameters include external environment temperature, which can be acquired by a temperature sensor arranged outside the vehicle.

[0054] After the vehicle speed, braking force, braking time, braking frequency and external environment temperature are acquired, the vehicle speed, braking force, braking time, braking frequency and external environment temperature can be input into the preset electronic parking brake caliper temperature estimation model to output the electronic parking brake caliper temperature.

[0055] In some embodiments, the above method further comprises: acquiring historical vehicle speed, historical braking force, historical braking time, historical braking frequency, historical external environment temperature and historical electronic parking brake caliper temperature; constructing a preset electronic parking brake caliper temperature estimation model training set according to the historical vehicle speed, historical braking force, historical braking time, historical braking frequency, historical external environment temperature and historical electronic parking brake caliper temperature, and training the preset electronic parking brake caliper temperature estimation model by using the preset electronic parking brake caliper temperature estimation model training set; The preset electronic parking brake caliper temperature estimation model is trained by using a preset electronic parking brake caliper temperature estimation model training set, including: inputting any input data in the preset electronic parking brake caliper temperature estimation model training set into an initial preset electronic parking brake caliper temperature estimation model to output a predicted electronic parking brake caliper temperature; calculating a discriminant loss based on the predicted electronic parking brake caliper temperature and a corresponding historical electronic parking brake caliper temperature in the preset electronic parking brake caliper temperature estimation model training set to obtain a second calculation result; updating the model parameters of the initial preset electronic parking brake caliper temperature estimation model by using the second calculation result until the updated initial preset electronic parking brake caliper temperature estimation model meets a second preset convergence condition, and obtaining the preset electronic parking brake caliper temperature estimation model.

[0056] For example, historical vehicle speeds, historical braking forces, historical braking times, historical braking frequencies, historical external environment temperatures, and historical electronic parking brake caliper temperatures are collected and obtained, these data are preprocessed, such as abnormal value cleaning, noise processing, and normalization processing, and then a model training set is built according to the preprocessed data.

[0057] An initial preset electronic parking brake caliper temperature estimation model (for example, a Transformer model) is constructed, and the hyperparameters of the model are set, such as the number of layers, the input dimension, the hidden dimension, the number of heads, etc. The Transformer model includes an input layer, an encoder layer, a decoder layer, and an output layer, wherein the encoder layer includes a multi-head self-attention mechanism layer, residual connection and layer normalization, a feedforward neural network, and residual connection and layer normalization, respectively, and the decoder layer includes a masked multi-head self-attention mechanism layer, residual connection and layer normalization, an encoder-decoder attention mechanism layer, residual connection and layer normalization, a feedforward neural network, and residual connection and layer normalization.

[0058] Any input data in the model training set is input into the input layer of the initial preset electronic parking brake caliper temperature estimation model (Transformer model), the input layer converts the input data into a fixed-dimensional vector representation, and adds position information for each element in the input sequence; then, the encoder layer processes the input sequence in parallel through multiple attention heads, captures long-distance dependencies in the sequence through a feedforward neural network, performs residual connection processing on the features of each position to increase the nonlinear ability of the model, and performs layer normalization processing on the features of each position to increase the nonlinear ability of the model; then, the decoder layer processes the input sequence of the decoder itself through a masked multi-head self-attention mechanism layer, and prevents "seeing" future information through a masking mechanism, the encoder-decoder attention mechanism layer combines the output information of the encoder with the intermediate result of the decoder, so that the decoder can use the context information extracted by the encoder, uses a feedforward neural network to further process the features of each position to increase the nonlinear ability of the model, directly transmits the input to the next layer through a residual connection to avoid the problem of gradient disappearance, and normalizes the features of each sample through layer normalization to stabilize the training process; then, the output layer converts the output of the decoder layer into a target format to generate the final predicted electronic parking brake caliper temperature; then, based on the predicted electronic parking brake caliper temperature and the corresponding historical electronic parking brake caliper temperature in the model training set, the calculation of the discriminative loss is performed, for example, the calculation of the mean square error or the average absolute error, the gradient is calculated using backpropagation and the model parameters are updated. Repeat the above steps until the preset convergence condition is met, for example, the loss value no longer decreases significantly, the performance of the validation set no longer improves, or the preset number of training times is reached, to obtain the preset electronic parking brake caliper temperature estimation model.

[0059] As a specific example, refer to Figure 2The electronic parking brake caliper temperature estimation system 500 of the embodiment of the application comprises a data acquisition module 510, a preprocessing module 520, a feature extraction module 530, an AI model module 540 and a post-processing module 550. The data acquisition module 510 is configured to collect historical vehicle speed, historical braking force, historical braking time, historical braking frequency, historical external environment temperature and historical electronic parking brake caliper temperature. The preprocessing module 520 is configured to perform cleaning, filtering, normalization and other processing on the collected data, reduce noise interference and improve data quality. The feature extraction module 530 is configured to automatically extract and select features by an AI large model, extract feature data closely related to the caliper temperature, and can use a self-attention mechanism and a time convolution network. The AI model module 540 is configured to construct a preset electronic parking brake caliper temperature estimation model based on a deep neural network and a Transformer, train the model using a large amount of historical data, learn the mapping relationship between the input data and the electronic parking brake caliper temperature, and consider the real-time performance of the model, and can use a MobileNet compression model. The post-processing module 550 is configured to calibrate and filter the output of the AI model, eliminate abnormal values and improve estimation accuracy.

[0060] In this way, the powerful data fitting capability of the preset electronic parking brake caliper temperature estimation model is used to realize high-precision temperature prediction, which can significantly improve the estimation accuracy of the electronic parking brake caliper temperature. At the same time, the end-to-end learning method can effectively reduce the modeling complexity and avoid the cumbersome model establishment and parameter calibration process. In addition, the generalization ability of the model can enhance the robustness of the system to external interference, so that it can still operate stably in complex environments. Finally, by designing an efficient neural network structure and inference algorithm, the real-time performance of the system is optimized to ensure that the safety control requirements are met.

[0061] As a specific example, refer to Figure 3 The control method of the vehicle of the embodiment of the application can further comprise the following steps: S201, obtaining vehicle driving parameters, vehicle braking parameters, vehicle environment parameters and vehicle configuration parameters.

[0062] S202, inputting the vehicle driving parameters, the vehicle braking parameters and the vehicle environment parameters into a preset electronic parking brake caliper temperature estimation model to output an electronic parking brake caliper temperature.

[0063] S203, determining a braking state score value according to the electronic parking brake caliper temperature, the vehicle driving parameters, the vehicle braking parameters, the vehicle environment parameters and the vehicle configuration parameters and corresponding weight coefficients.

[0064] S204, determining a target cooling mode according to the score interval in which the braking state score value is located.

[0065] S205, air cooling the brake executing component of the vehicle.

[0066] S206, liquid cooling the brake executing component of the vehicle.

[0067] S207, air cooling and liquid cooling the brake executing component of the vehicle.

[0068] To sum up, the application trains a preset electronic parking brake caliper temperature estimation model by collecting historical vehicle speed, historical braking force, historical braking time, historical braking frequency, historical external environment temperature and historical electronic parking brake caliper temperature, and determines the electronic parking brake caliper temperature by using the preset electronic parking brake caliper temperature estimation model, so that the estimation accuracy of the electronic parking brake caliper temperature can be significantly improved. Further, the target cooling mode is intelligently selected according to the weight coefficients corresponding to the electronic parking brake caliper temperature and various parameters of the vehicle, and the brake executing component is precisely cooled, so that the problems of brake performance decline and system service life shortening caused by high caliper temperature are effectively solved, the safety and reliability of the brake system are significantly improved, the applicability and efficiency of the cooling measures are optimized, the braking distance is reduced, and the application is especially suitable for complex and variable actual working conditions, thereby improving the vehicle driving experience and increasing user satisfaction.

[0069] Referring to Figure 4 As shown in the figure, the vehicle 400 of the application comprises a memory 410, a processor 420, and a vehicle control program stored in the memory 410 and executable on the processor 420. When the processor executes the vehicle control program, the vehicle control method described above is realized.

[0070] It should be pointed out that the above explanations and descriptions of the embodiments and beneficial effects of the vehicle control method are also applicable to the vehicle of the application. To avoid redundancy, they will not be described in detail here.

[0071] In the present application, a plurality of refers to two or more than two.

[0072] In the present application, unless otherwise explicitly limited, the terms "mounting", "connecting", "connecting" should be understood broadly, for example, it can be fixed connection, or detachable connection, or integral connection; it can be mechanical connection, or electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or the internal communication of two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0073] The terms "first", "second", "third", "fourth" and the like (if any) in the present application are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.

[0074] The term "and / or", within the present application, merely describes an associated relationship with the associated objects (may exist in three kinds of relationship, for example, A and / or B, can represent: A alone, A and B exist simultaneously, B alone, three cases). In addition, the character " / " in the present application generally indicates that the front and rear associated objects are a kind of "or" relationship.

[0075] If there is no special description, all the steps of the present application can be carried out in sequence, or randomly. For example, the method comprises steps A and B, which means that the method can comprise sequentially performed steps A and B, or sequentially performed steps B and A. For example, the method also comprises step C, which means that step C can be added to the method in any order, for example, the method can comprise steps A, B and C, or steps A, C and B, or steps C, A and B, etc.

[0076] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for controlling a vehicle, characterized in that, The method includes: Determine the temperature of the electronic parking brake caliper; The target cooling mode is determined based on the electronic parking brake caliper temperature, vehicle driving parameters, vehicle braking parameters, vehicle environmental parameters, and vehicle configuration parameters. The braking actuators of the vehicle are cooled according to the target cooling mode.

2. The vehicle control method according to claim 1, characterized in that, The target cooling mode is determined based on the electronic parking brake caliper temperature, vehicle driving parameters, vehicle braking parameters, environmental parameters, and vehicle configuration parameters, including: The scores corresponding to the electronic parking brake caliper temperature, vehicle driving parameters, vehicle braking parameters, vehicle environmental parameters, and vehicle configuration parameters are obtained respectively. The braking status score is determined by the sum of the products of all scores and their corresponding weighting coefficients. The target cooling mode is determined based on the scoring range in which the braking state score value falls.

3. The vehicle control method according to claim 2, characterized in that, The target cooling mode is determined based on the scoring range in which the braking state score falls, including: If the braking state score is less than or equal to the first braking state score threshold, the target cooling mode is determined to be the first cooling mode, wherein the first cooling mode is used to characterize the air cooling of the braking actuator of the vehicle. If the braking state score is greater than the first braking state score threshold and less than or equal to the second braking state score threshold, the target cooling mode is determined to be the second cooling mode, wherein the second cooling mode is used to characterize liquid cooling of the braking actuator of the vehicle. If the braking state score is greater than the second braking state score threshold and less than or equal to the third braking state score threshold, the target cooling mode is determined to be the third cooling mode, wherein the third cooling mode is used to characterize the air cooling and liquid cooling of the braking actuator of the vehicle.

4. The vehicle control method according to claim 3, characterized in that, The method further includes: If the braking status score is greater than the third braking status score threshold, the vehicle is controlled to issue an alarm.

5. The vehicle control method according to claim 1, characterized in that, The target cooling mode is determined based on the electronic parking brake caliper temperature, vehicle driving parameters, vehicle braking parameters, environmental parameters, and vehicle configuration parameters, including: The electronic parking brake caliper temperature, vehicle driving parameters, vehicle braking parameters, vehicle environmental parameters, and vehicle configuration parameters are input into a preset cooling mode determination model to output the target cooling mode.

6. The vehicle control method according to claim 5, characterized in that, The method further includes: It acquires historical electronic parking brake caliper temperature, historical vehicle driving parameters, historical vehicle braking parameters, historical vehicle environmental parameters, historical vehicle configuration parameters, and historical cooling modes. Based on the historical electronic parking brake caliper temperature, the historical vehicle driving parameters, the historical vehicle braking parameters, the historical vehicle environmental parameters, the historical vehicle configuration parameters, and the historical cooling mode, a preset cooling mode determination model training set is constructed, and the preset cooling mode determination model is trained using the preset cooling mode determination model training set. Training the preset cooling mode determination model using the preset cooling mode determination model training set includes: Input any input data from the training set of the preset cooling mode determination model into the initial preset cooling mode determination model to output the predicted cooling mode; Based on the predicted cooling mode and the preset cooling mode, the historical cooling mode corresponding to the model training set is determined and the discrimination loss is calculated to obtain the first calculation result; The model parameters of the initial preset cooling mode determination model are updated using the first calculation result until the updated initial preset cooling mode determination model satisfies the first preset convergence condition, thus obtaining the preset cooling mode determination model.

7. The vehicle control method according to claim 1, characterized in that, The vehicle driving parameters include at least one of driving mode and load; the vehicle braking parameters include at least one of braking frequency and brake wear degree; the vehicle environment parameters include altitude; and the vehicle configuration parameters include at least one of vehicle type, caliper material, and number of brake discs.

8. The vehicle control method according to claim 1, characterized in that, Determining the temperature of the electronic parking brake caliper includes: The vehicle driving parameters, the vehicle braking parameters, and the environmental parameters of the vehicle are input into a preset electronic parking brake caliper temperature estimation model to output the electronic parking brake caliper temperature. The vehicle driving parameters include vehicle speed, the vehicle braking parameters include braking force, braking time, and braking frequency, and the vehicle's environmental parameters include external ambient temperature.

9. The vehicle control method according to claim 8, characterized in that, The method further includes: It acquires historical vehicle speed, historical braking force, historical braking time, historical braking frequency, historical ambient temperature, and historical electronic parking brake caliper temperature. Based on the historical vehicle speed, historical braking force, historical braking time, historical braking frequency, historical ambient temperature, and historical electronic parking brake caliper temperature, a preset electronic parking brake caliper temperature estimation model training set is constructed, and the preset electronic parking brake caliper temperature estimation model is trained using the preset electronic parking brake caliper temperature estimation model training set. Training the preset electronic parking brake caliper temperature estimation model using the preset electronic parking brake caliper temperature estimation model training set includes: Input any input data from the training set of the preset electronic parking brake caliper temperature estimation model into the initial preset electronic parking brake caliper temperature estimation model to output the predicted electronic parking brake caliper temperature. The discrimination loss is calculated based on the predicted electronic parking brake caliper temperature and the historical electronic parking brake caliper temperatures corresponding to the training set of the preset electronic parking brake caliper temperature estimation model, so as to obtain the second calculation result. The model parameters of the initial preset electronic parking brake caliper temperature estimation model are updated using the second calculation result until the updated initial preset electronic parking brake caliper temperature estimation model meets the second preset convergence condition, thus obtaining the preset electronic parking brake caliper temperature estimation model.

10. A vehicle, characterized in that, The system includes a memory, a processor, and a vehicle control program stored in the memory and executable on the processor. When the processor executes the vehicle control program, it implements the vehicle control method according to any one of claims 1-9.

Images