An EMB clamping force estimation method

Abstract

The application provides an EMB clamping force estimation method, comprising the following steps: building an EMB clamping process mechanism model; obtaining the data of the EMB clamping force, the motor rotation angle and the brake disc temperature based on an EMB test bench, and building an EMB clamping force fitting model; obtaining the data of the motor current, the motor voltage, the motor rotation speed, the motor rotation angle, the brake disc temperature, the clamping force and the driving mileage based on the EMB test bench, and building an EMB clamping force data model; calculating the first estimated value, the second estimated value and the third estimated value of the clamping force based on the real vehicle EMB data, combining the Kalman filtering algorithm to calculate the fused estimated value of the clamping force; and according to the clamping force estimation error, adaptively adjusting the weights of the first estimated value, the second estimated value and the third estimated value of the clamping force, and optimizing the clamping force estimation precision. The application can fully combine the advantages of the mechanism model and the offline data and the online data, continuously correct the fusion weight according to the estimation error, and realize the accurate estimation of the EMB clamping force without the clamping force sensor.

Description

Technical Field

[0001] This application relates to the field of vehicle braking technology, and in particular to an EMB clamping force estimation method. Background Technology

[0002] Electromechanical brake (EMB) systems are widely considered a key component for the development of drive-by-wire systems in new energy vehicle chassis due to their advantages such as fast response, small size, easy installation, and no hydraulic oil contamination. EMB clamping force is a crucial parameter affecting braking performance; however, due to cost and space constraints, clamping force sensors cannot be standard equipment in actual EMB systems. Therefore, accurately estimating the clamping force without a clamping force sensor is crucial for EMB system control and optimization. Existing methods mainly include estimation methods based on motor models, estimation methods based on brake disc stiffness models, and data-driven methods. However, each method has its limitations, and a reliable and stable EMB clamping force estimation scheme has not yet been established.

[0003] (1) Traditional motor models do not consider factors such as system temperature changes and fatigue wear, resulting in model errors;

[0004] (2) The traditional brake disc stiffness model does not consider the effect of temperature change on stiffness and is only applicable to a single temperature scenario;

[0005] (3) Data-driven methods have high requirements for the quantity and quality of data and poor reliability. Summary of the Invention

[0006] This application aims to at least partially address one of the technical problems in the related art.

[0007] Therefore, the first objective of this application is to propose an EMB clamping force estimation method to fully utilize measurable data in the absence of a clamping force sensor, thereby achieving accurate estimation of the EMB clamping force, which in turn helps to accurately control the EMB clamping force and improve vehicle braking performance.

[0008] The second objective of this application is to propose an EMB clamping force estimation system.

[0009] The third objective of this application is to propose an electronic device.

[0010] The fourth objective of this application is to provide a computer-readable storage medium.

[0011] The fifth objective of this application is to provide a computer program product.

[0012] To achieve the above objectives, a first aspect of this application provides an EMB clamping force estimation method, comprising:

[0013] A mechanism model of EMB clamping process is built. By establishing the relationship between motor speed, load torque and friction torque, and considering the influence of temperature on friction torque and transmission efficiency, as well as heat conduction, heat convection and heat radiation, the first estimated value of EMB clamping force is calculated.

[0014] Based on the data of EMB clamping force, motor rotation angle and brake disc temperature obtained by the EMB test bench, an EMB clamping force fitting model is built. By using the polynomial fitting method, the relationship between EMB clamping force and motor rotation angle under different brake disc temperatures is established, and the second estimated value of EMB clamping force is calculated.

[0015] Based on the EMB test bench, data such as motor current, motor voltage, motor speed, motor angle, brake disc temperature, clamping force, and mileage are obtained. An EMB clamping force data model is built and trained using machine learning or deep learning algorithms to calculate the third estimate of the EMB clamping force.

[0016] The first, second, and third estimates of the EMB clamping force are fused using a Kalman filter algorithm to obtain a fused estimate of the EMB clamping force.

[0017] Based on the clamping force estimation error, the weights of the first, second, and third estimates of the clamping force are adaptively adjusted to optimize the clamping force estimation accuracy.

[0018] Optionally, the step of building the EMB clamping process mechanism model involves establishing the relationship between motor speed, load torque, and friction torque, and considering the influence of temperature on friction torque and transmission efficiency, as well as heat conduction, heat convection, and heat radiation, to calculate a first estimate of the EMB clamping force, including:

[0019] The relationship between the equivalent moment of inertia and the rotational speed at the EMB motor terminal is established as follows:

[0020]

[0021]

[0022]

[0023]

[0024] In the formula, This is the equivalent moment of inertia at the EMB motor end; This refers to the EMB motor speed; This provides the output torque for the EMB motor. This is the equivalent frictional torque at the EMB motor end; This refers to the load torque of the EMB motor. This is the motor torque coefficient; This refers to the q-axis current of the EMB motor. This is the critical coefficient; This is the static friction torque; This is the estimated EMB clamping force value from the previous step; This is the torque coefficient related to the clamping force; It is the coefficient of viscous friction; This is the first estimate of the EMB clamping force; For the ball screw lead; This refers to the planetary gear ratio; The transmission efficiency of the transmission mechanism;

[0025] Considering the influence of temperature on frictional torque and transmission efficiency, a corrected model for frictional torque and transmission efficiency with respect to brake disc temperature is constructed, with the following expression:

[0026]

[0027]

[0028] In the formula, The standard temperature of the brake disc; , These represent the transmission efficiency and frictional torque of the transmission mechanism at standard temperatures, respectively. , These are the correction factors for transmission efficiency and friction torque with respect to brake disc temperature, respectively.

[0029] Considering heat conduction, convection, and radiation, a brake disc temperature rise model is constructed during the braking process, expressed as follows:

[0030]

[0031]

[0032]

[0033]

[0034]

[0035] In the formula, For brake disc mass; The specific heat capacity of the brake disc; For brake disc temperature; , , , These are the frictional heat generation power, heat conduction power, heat convection power, and heat radiation power of the brake disc, respectively. The coefficient of friction of the brake disc; The relative rotational speed of the brake disc; The thermal conductivity of the brake disc; This refers to the contact area between the brake disc and adjacent components. The ambient temperature; This is the length of the heat conduction path; The convective heat transfer coefficient; The contact area between the brake disc and the air; Emissivity; is the Stefan-Boltzmann constant.

[0036] Optionally, the step of acquiring data on EMB clamping force, motor rotation angle, and brake disc temperature based on the EMB test bench, building an EMB clamping force fitting model, establishing the relationship between EMB clamping force and motor rotation angle at different brake disc temperatures using a polynomial fitting method, and calculating a second estimated value of the EMB clamping force includes:

[0037] An EMB test bench was set up, an encoder was configured on the EMB motor, a pressure sensor was installed between the EMB piston and the brake pad, and a temperature sensor was built into the brake disc; a triangular wave voltage signal of 0~maximum voltage~0 was output to the EMB motor, and this process was repeated multiple times. After filtering, the motor rotation angle, brake disc temperature and clamping force data during the EMB clamping and releasing process were obtained respectively.

[0038] Based on data on motor rotation angle, brake disc temperature, and clamping force, a polynomial fitting method was used to obtain the relationship between clamping force and motor rotation angle during EMB clamping and releasing processes at different brake disc temperatures. The expression is as follows:

[0039] EMB clamping process

[0040] EMB release process

[0041] In the formula, This is a second estimate of the EMB clamping force; , , , These are polynomial coefficients, which differ at different temperatures; This refers to the motor's rotation angle; , These are the critical values ​​of motor rotation angle during the EMB clamping and releasing processes, respectively.

[0042] Optionally, the step of acquiring data on motor current, motor voltage, motor speed, motor rotation angle, brake disc temperature, clamping force, and mileage based on the EMB test bench, building an EMB clamping force data model and training it using machine learning or deep learning algorithms, and calculating a third estimate of the EMB clamping force includes:

[0043] An EMB test bench was set up, an encoder was configured on the EMB motor, and pressure and temperature sensors were installed between the EMB piston and the brake pads. A voltage signal simulating the driver's braking torque demand was output to the EMB motor. This process was repeated several times, and after filtering, data on EMB motor current, motor voltage, motor speed, motor angle, brake disc temperature, clamping force, and mileage were obtained.

[0044] An EMB clamping force data model is constructed, which uses EMB motor current, motor voltage, motor speed, motor angle, brake disc temperature, clamping force and mileage as input variables, and clamping force as output variable.

[0045] The EMB clamping force data model is trained using machine learning or deep learning algorithms to obtain the trained clamping force data model, expressed as:

[0046]

[0047] In the formula, This is the third estimate of the EMB clamping force; This refers to the motor voltage; For the clamping force data model obtained from training; This refers to the mileage traveled.

[0048] Optionally, the step of fusing the first, second, and third estimates of the EMB clamping force using a Kalman filter algorithm to obtain a fused estimate of the EMB clamping force includes:

[0049] The first estimate of the clamping force is fused based on the Kalman filter algorithm. Second estimate Third estimate The fusion estimate of the EMB clamping force is obtained. The expression is:

[0050]

[0051] in, , , These are the weighting coefficients for the first, second, and third estimates of the clamping force, respectively.

[0052] Optionally, the step of adaptively adjusting the weights of the first, second, and third estimates of the clamping force based on the clamping force estimation error to optimize the clamping force estimation accuracy includes:

[0053] The variance of the estimation error of the EMB clamping process mechanism model, the EMB clamping force fitting model, and the EMB clamping force data model within the sliding window is calculated using the following expression:

[0054]

[0055]

[0056]

[0057] In the formula, The number of data items within the sliding window. , , These represent the variances of the estimation errors for the EMB clamping process mechanism model, the EMB clamping force fitting model, and the EMB clamping force data model within the sliding window, respectively.

[0058] Based on the variance of the clamping force estimation error, the weighting coefficients of the first, second, and third estimates of the clamping force are adaptively adjusted, as expressed by:

[0059]

[0060]

[0061]

[0062] in, , , These are the weighting coefficients for the first, second, and third estimates of the clamping force, respectively.

[0063] To achieve the above objectives, a second aspect of this application provides an EMB clamping force estimation system, comprising:

[0064] The information acquisition module is used to collect real-time data related to clamping force in the EMB system, including motor current, motor voltage, motor speed, motor angle, brake disc temperature, clamping force, and mileage.

[0065] The EMB clamping process mechanism model calculation module is used to establish the relationship between motor speed, load torque, and friction torque, and to calculate the first estimate of EMB clamping force, taking into account the influence of temperature on friction torque and transmission efficiency, as well as heat conduction, heat convection, and heat radiation.

[0066] The EMB clamping force fitting model calculation module is used to build an EMB clamping force fitting model based on data of EMB clamping force, motor rotation angle, and brake disc temperature. By using a polynomial fitting method, the relationship between EMB clamping force and motor rotation angle under different brake disc temperatures is established, and the second estimated value of EMB clamping force is calculated.

[0067] The EMB clamping force data model calculation module is used to build an EMB clamping force data model based on data such as motor current, motor voltage, motor speed, motor rotation angle, brake disc temperature, clamping force, and mileage, and train it using machine learning or deep learning algorithms to calculate the third estimate of the EMB clamping force.

[0068] The online fusion estimation module for EMB clamping force is used to fuse the first, second, and third estimates of the EMB clamping force using a Kalman filter algorithm to obtain a fused estimate of the EMB clamping force. The module also adaptively adjusts the weights of each estimate based on the clamping force estimation error to optimize the accuracy of the clamping force estimation.

[0069] To achieve the above objectives, a third aspect of this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0070] The memory stores computer-executed instructions;

[0071] The processor executes computer execution instructions stored in the memory to implement the method as described in any one of the first aspects above.

[0072] To achieve the above objectives, a fourth aspect of this application provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, are used to implement the method as described in any one of the first aspects above.

[0073] To achieve the above objectives, a fifth aspect of this application provides a computer program product including a computer program that, when executed by a processor, implements the method as described in any one of the first aspects above.

[0074] The technical solutions provided by the embodiments of this application bring at least the following beneficial effects:

[0075] It can fully combine the advantages of mechanism models with offline and online data, and continuously adjust the fusion weights according to the estimation error to achieve accurate estimation of EMB clamping force without clamping force sensor. It has higher estimation accuracy and stability, and can adapt to complex working conditions for a long time. At the same time, since this application does not use clamping force sensor, the cost is reduced, which is conducive to improving the economic benefits of mass-produced vehicles.

[0076] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0077] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0078] Figure 1 A flowchart illustrating an EMB clamping force estimation method provided in an embodiment of this application;

[0079] Figure 2 This is a schematic diagram of the structure of an EMB clamping force estimation system provided in an embodiment of this application. Detailed Implementation

[0080] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0081] To address the problems existing in the prior art, this application provides an EMB clamping force estimation method. Figure 1 This is a flowchart illustrating an EMB clamping force estimation method provided in an embodiment of this application. Figure 1 As shown, the method includes the following steps:

[0082] Step S1: Build an EMB clamping process mechanism model. By establishing the relationship between motor speed, load torque, and friction torque, and considering the influence of temperature on friction torque and transmission efficiency, as well as heat conduction, heat convection, and heat radiation, calculate the first estimated value of EMB clamping force.

[0083] The first step in this application is to build a mechanism model of the EMB clamping process. The key to this step is to establish the relationship between motor speed, load torque, and friction torque, comprehensively consider the influence of temperature on friction torque and transmission efficiency, and also consider factors such as heat conduction, heat convection, and heat radiation, so as to calculate the first estimate of the EMB clamping force.

[0084] In this process, the embodiments of this application first express the operating characteristics of the motor by establishing the relationship between the equivalent moment of inertia and the rotational speed at the EMB motor end. The relationship is as follows:

[0085]

[0086]

[0087]

[0088]

[0089] In the formula, This is the equivalent moment of inertia at the EMB motor end; This refers to the EMB motor speed; This provides the output torque for the EMB motor. This is the equivalent frictional torque at the EMB motor end; This refers to the load torque of the EMB motor. This is the motor torque coefficient; This refers to the q-axis current of the EMB motor. This is the critical coefficient; This is the static friction torque; This is the estimated EMB clamping force value from the previous step; This is the torque coefficient related to the clamping force; It is the coefficient of viscous friction; This is the first estimate of the EMB clamping force; For the ball screw lead; This refers to the planetary gear ratio; The transmission efficiency of the transmission mechanism.

[0090] To account for the influence of temperature on frictional torque and transmission efficiency, this application embodiment constructs a corrected model for frictional torque and transmission efficiency with respect to brake disc temperature, as shown in the following formula:

[0091]

[0092]

[0093] In the formula, The standard temperature of the brake disc; , These represent the transmission efficiency and frictional torque of the transmission mechanism at standard temperatures, respectively. , These are the correction factors for transmission efficiency and friction torque with respect to brake disc temperature, respectively.

[0094] Furthermore, this application embodiment further considers the influence of heat conduction, heat convection, and heat radiation on the temperature rise of the brake disc. Using the heat conduction equation and the formula for calculating heat power, a model for the temperature rise of the brake disc is established, expressed as follows:

[0095]

[0096]

[0097]

[0098]

[0099]

[0100] In the formula, For brake disc mass; The specific heat capacity of the brake disc; For brake disc temperature; , , , These are the frictional heat generation power, heat conduction power, heat convection power, and heat radiation power of the brake disc, respectively. The coefficient of friction of the brake disc; The relative rotational speed of the brake disc; The thermal conductivity of the brake disc; This refers to the contact area between the brake disc and adjacent components. The ambient temperature; This is the length of the heat conduction path; The convective heat transfer coefficient; The contact area between the brake disc and the air; Emissivity; is the Stefan-Boltzmann constant.

[0101] These formulas take into account the effects of frictional heat generation, heat conduction, heat convection, and heat radiation, thereby helping this application to more accurately assess the temperature of the brake disc, and further adjust the frictional torque and transmission efficiency.

[0102] Taking all the above factors into account, a first estimate of the EMB clamping force can be obtained based on the model. This estimate provides the foundation for subsequent steps and can be further optimized by combining other data and models.

[0103] In practical applications, the first estimate of the EMB clamping force can be obtained through real vehicle data. By monitoring parameters such as motor current, motor speed, temperature, and load torque in real time, and combining the calculation process of the aforementioned mechanism model, the EMB clamping force can be accurately estimated based on the actual vehicle operating status.

[0104] Step S2: Based on the EMB test bench, data on EMB clamping force, motor rotation angle, and brake disc temperature are obtained. An EMB clamping force fitting model is built. By using a polynomial fitting method, the relationship between EMB clamping force and motor rotation angle under different brake disc temperatures is established, and the second estimated value of EMB clamping force is calculated.

[0105] The second step of this application mainly involves acquiring data such as motor rotation angle, brake disc temperature and clamping force based on the EMB test bench, and building a fitting model of EMB clamping force based on these data. By using a polynomial fitting method, the relationship between EMB clamping force and motor rotation angle under different brake disc temperatures is established, and then the second estimated value of EMB clamping force is calculated.

[0106] In this process, the embodiments of this application first construct an EMB test bench and configure relevant sensors and devices to collect necessary data. The main configuration of the EMB test bench includes:

[0107] Motor encoder: Used to accurately measure the rotation angle of a motor;

[0108] Pressure sensor: Installed between the EMB piston and the brake pads to monitor clamping force;

[0109] Temperature sensor: Installed in the brake disc to monitor the temperature of the brake disc in real time.

[0110] By controlling the EMB motor, this application outputs a triangular wave voltage signal that rises from 0 to its maximum voltage and then returns to 0, repeating this process multiple times. These input signals cause the EMB motor to operate during clamping and releasing. After the signal output, data under different conditions is obtained through filtering. This data mainly includes motor rotation angle, brake disc temperature, and clamping force data during the EMB clamping and releasing process. This data reflects the dynamic behavior of the EMB during clamping and releasing, serving as the basis for subsequent fitting and modeling.

[0111] Based on the collected data on motor rotation angle, brake disc temperature, and clamping force, this embodiment employs a polynomial fitting method to establish the relationship between clamping force and motor rotation angle. Specifically, the relationship between clamping force and motor rotation angle varies under different brake disc temperatures; therefore, the polynomial coefficients need to be fitted for different temperature conditions. The expression is as follows:

[0112] EMB clamping process

[0113] EMB release process

[0114] In the formula, This is a second estimate of the EMB clamping force; , , , These are polynomial coefficients, which differ at different temperatures; This refers to the motor's rotation angle; , These are the critical values ​​of motor rotation angle during the EMB clamping and releasing processes, respectively.

[0115] It should be noted that when fitting the relationship between clamping force and motor rotation angle, the polynomial fitting methods used include, but are not limited to, the following commonly used methods: Least squares polynomial fitting method: the optimal polynomial coefficients are obtained by minimizing the sum of squared errors between the fitted curve and the actual data; Lagrange interpolation polynomial fitting method: based on interpolation theory, a polynomial is calculated using multiple known data points, which can accurately pass through all given points; Newton interpolation polynomial fitting method: based on a type of interpolation method, the polynomial is obtained by recursively calculating the difference quotient, which can adapt to different numbers of data points.

[0116] It should be noted that this application does not limit the fitting method. The above polynomial fitting methods are applicable to different situations. The most suitable fitting method can be selected according to the actual data characteristics. The polynomial coefficients obtained by these methods will change with the different brake disc temperatures. Therefore, fitting needs to be performed according to different temperature conditions.

[0117] Through step S2, this application establishes a relationship between the EMB clamping force and the motor rotation angle based on actual data collected from the EMB test bench using a polynomial fitting method. This step not only considers the influence of brake disc temperature but also introduces several commonly used polynomial fitting methods, including least squares, Lagrange interpolation, and Newton interpolation, thereby optimizing the estimated value of the EMB clamping force.

[0118] In practical applications, a second estimate of the EMB clamping force can be obtained from real vehicle data. Combined with the calculation process of the aforementioned clamping force fitting model, the EMB clamping force can be accurately estimated based on the actual vehicle operating status.

[0119] Step S3: Based on the EMB test bench, acquire data on motor current, motor voltage, motor speed, motor angle, brake disc temperature, clamping force, and mileage, build an EMB clamping force data model, and train it using machine learning or deep learning algorithms to calculate the third estimate of the EMB clamping force.

[0120] The third step of this application mainly involves acquiring data such as motor current, motor voltage, motor speed, motor rotation angle, brake disc temperature, clamping force, and mileage based on an EMB test bench, and building a data model of the EMB clamping force. Then, machine learning or deep learning algorithms are used to train the data model to calculate a third estimate of the EMB clamping force.

[0121] In this step, the embodiment of this application first sets up an EMB test bench and configures relevant sensors and devices to collect necessary data. The main configuration of the EMB test bench includes:

[0122] Motor encoder: Used to accurately measure the rotation angle of a motor;

[0123] Pressure sensor: Installed between the EMB piston and the brake pads to monitor clamping force;

[0124] Temperature sensor: Installed in the brake disc to monitor the temperature of the brake disc in real time;

[0125] Mileage sensor: records the mileage traveled by the vehicle.

[0126] Next, in this embodiment, a voltage signal simulating the driver's braking torque demand is output to the EMB motor, causing the EMB motor to operate under different conditions, and this process is repeated multiple times. After the signal is output, the following data is obtained through filtering: EMB motor current, motor voltage, motor speed, motor angle, brake disc temperature, clamping force, and mileage. These data represent the operating state of the EMB motor and braking system, providing rich input information for subsequent data modeling and training.

[0127] Based on the acquired data, this application embodiment further establishes an EMB clamping force data model. This model uses EMB motor current, motor voltage, motor speed, motor rotation angle, brake disc temperature, clamping force, and mileage as input variables, and clamping force as the output variable.

[0128] In this embodiment, machine learning or deep learning algorithms are used to train the EMB clamping force data model. Commonly used machine learning algorithms include, but are not limited to, gradient boosting trees, support vector regression, and random forests; while deep learning algorithms may include long short-term memory networks (LSTM), convolutional neural networks (CNN), and Transformers. Through these algorithms, the model can automatically learn the variation pattern of clamping force from the data, thereby achieving the estimation of EMB clamping force.

[0129] The trained model can be expressed by the following formula:

[0130]

[0131] In the formula, This is the third estimate of the EMB clamping force; This refers to the motor voltage; For the clamping force data model obtained from training; This refers to the mileage traveled.

[0132] Finally, the trained EMB clamping force data model can predict the third estimate of the clamping force in real time. This model can handle complex nonlinear relationships and provides accurate clamping force estimates for practical applications by analyzing various parameters of the motor and braking system. This estimate will help to better control and optimize the operating state of the EMB system, improving its stability and reliability.

[0133] In practical applications, a third estimate of the EMB clamping force can be obtained from real vehicle data. Combined with the calculation process of the aforementioned clamping force data model, the EMB clamping force can be accurately estimated based on the actual vehicle operating status.

[0134] Step S4: The first, second, and third estimates of the EMB clamping force are fused using the Kalman filter algorithm to obtain the fused estimate of the EMB clamping force.

[0135] In this embodiment of the application, the fourth step involves fusing the first, second, and third estimates of the EMB clamping force using a Kalman filter algorithm to obtain a fused estimate of the EMB clamping force.

[0136] Kalman filtering is a recursive algorithm that uses a system dynamic model and observation data to make optimal estimates. It is widely used in multi-sensor data fusion and dynamic system state estimation. In this step, the Kalman filtering algorithm is used to fuse different estimates of the EMB clamping force to obtain a more accurate fused estimate. Through the weighted averaging mechanism of Kalman filtering, the embodiments of this application can automatically adjust the weight coefficient of each estimate and dynamically optimize the clamping force estimation result.

[0137] In this embodiment, based on the Kalman filter algorithm, three different estimates of the EMB clamping force are fused to calculate the final fused clamping force estimate. Assuming that the first, second, and third estimates of the clamping force have been obtained based on actual vehicle data, the combined estimate of the clamping force is calculated using the following weighted sum formula:

[0138]

[0139] in, , , These are the weighting coefficients for the first, second, and third estimates of the clamping force, respectively. These weighting coefficients are adaptively adjusted using the Kalman filter algorithm, dynamically allocated based on the accuracy and reliability of each estimate, ultimately yielding the optimal fused estimate of the clamping force.

[0140] Step S5: Based on the clamping force estimation error, adaptively adjust the weights of the first, second, and third estimated values ​​of the clamping force to optimize the clamping force estimation accuracy.

[0141] In order to dynamically adjust the weighting coefficients based on the clamping force estimation error, the embodiments of this application first need to calculate the error of each estimate. By using historical data within a sliding window, the variance of the estimation errors of the EMB clamping process mechanism model, the EMB clamping force fitting model, and the EMB clamping force data model can be calculated. The variance of the error reflects the magnitude of the deviation of each estimate from the actual value, thereby helping to assess the reliability of the estimates.

[0142] The specific formula for calculating the error variance is as follows:

[0143]

[0144]

[0145]

[0146] In the formula, The number of data items within the sliding window. , , These represent the variances of the estimation errors for the EMB clamping process mechanism model, the EMB clamping force fitting model, and the EMB clamping force data model within the sliding window, respectively.

[0147] After calculating the error variance of each estimate, this embodiment further dynamically adjusts the weight coefficient of each estimate based on the magnitude of the error. A smaller estimation error corresponds to a higher weight, thereby enhancing the influence of that estimate in the fusion result. Conversely, a larger estimation error leads to a lower weight, thereby reducing its impact on the final result.

[0148] The adaptive adjustment formula for the weighting coefficients is as follows:

[0149]

[0150]

[0151]

[0152] in, , , These are the weighting coefficients for the first, second, and third estimates of the clamping force, respectively.

[0153] Understandably, in practical applications, the estimation error of the clamping force will fluctuate with changes in different working conditions. The Kalman filtering algorithm and adaptive adjustment mechanism allow this application to correct the estimation error and adjust the weighting coefficients in real time based on new data. In this way, the estimation accuracy of the EMB clamping force will continuously improve over time and with the collection of more data.

[0154] By implementing step S5, this application utilizes the Kalman filter algorithm combined with the estimation error variance to adaptively adjust the weighting coefficients of the EMB clamping force estimate, thereby optimizing the estimation accuracy of the clamping force. This method can provide high-precision EMB clamping force estimation in practical applications, helping to improve the control accuracy and stability of the EMB system.

[0155] To achieve the above embodiments, this application also proposes an EMB clamping force estimation system. Figure 2 This is a schematic diagram of the structure of an EMB clamping force estimation system provided in an embodiment of this application. Figure 2 As shown, the system includes:

[0156] The information acquisition module is used to collect real-time data related to clamping force in the EMB system, including motor current, motor voltage, motor speed, motor angle, brake disc temperature, clamping force, and mileage.

[0157] The EMB clamping process mechanism model calculation module is used to establish the relationship between motor speed, load torque, and friction torque, and to calculate the first estimate of EMB clamping force, taking into account the influence of temperature on friction torque and transmission efficiency, as well as heat conduction, heat convection, and heat radiation.

[0158] The EMB clamping force fitting model calculation module is used to build an EMB clamping force fitting model based on data of EMB clamping force, motor rotation angle, and brake disc temperature. By using a polynomial fitting method, the relationship between EMB clamping force and motor rotation angle under different brake disc temperatures is established, and the second estimated value of EMB clamping force is calculated.

[0159] The EMB clamping force data model calculation module is used to build an EMB clamping force data model based on data such as motor current, motor voltage, motor speed, motor rotation angle, brake disc temperature, clamping force, and mileage, and train it using machine learning or deep learning algorithms to calculate the third estimate of the EMB clamping force.

[0160] The online fusion estimation module for EMB clamping force is used to fuse the first, second, and third estimates of EMB clamping force using a Kalman filter algorithm to obtain a fusion estimate of the EMB clamping force. The module also adaptively adjusts the weights of each estimate based on the clamping force estimation error to optimize the accuracy of the clamping force estimation.

[0161] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0162] To implement the above embodiments, this application also proposes an electronic device, including: a processor and a memory communicatively connected to the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method provided in the foregoing embodiments.

[0163] To implement the above embodiments, this application also proposes a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided in the foregoing embodiments.

[0164] To implement the above embodiments, this application also proposes a computer program product, including a computer program that, when executed by a processor, implements the methods provided in the foregoing embodiments.

[0165] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0166] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0167] This application is intended to provide an implementation scheme for users to selectively prevent the use or access to their personal information data. Specifically, this disclosure is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information is de-identified to protect user privacy.

[0168] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0169] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0170] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0171] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0172] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0173] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0174] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0175] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

[0176] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved, and this is not limited herein.

[0177] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for estimating EMB clamping force, characterized in that, include: A mechanism model of EMB clamping process is established. By establishing the relationship between motor speed, load torque and friction torque, and considering the influence of temperature on friction torque and transmission efficiency as well as heat conduction, heat convection and heat radiation, the first estimate of EMB clamping force is calculated. Correction models of friction torque and transmission efficiency with respect to brake disc temperature and brake disc temperature rise model during braking process are constructed. Based on the data of EMB clamping force, motor rotation angle and brake disc temperature obtained by the EMB test bench, an EMB clamping force fitting model is built. By using the polynomial fitting method, the relationship between EMB clamping force and motor rotation angle under different brake disc temperatures is established, and the second estimated value of EMB clamping force is calculated. Based on the EMB test bench, data such as motor current, motor voltage, motor speed, motor angle, brake disc temperature, clamping force, and mileage are obtained. An EMB clamping force data model is built and trained using machine learning or deep learning algorithms to calculate the third estimate of the EMB clamping force. The first, second, and third estimates of the EMB clamping force are fused using a Kalman filter algorithm to obtain a fused estimate of the EMB clamping force. Based on the clamping force estimation error, the weights of the first, second, and third estimates of the clamping force are adaptively adjusted to optimize the clamping force estimation accuracy.

2. The method according to claim 1, characterized in that, The aforementioned model of the EMB clamping process mechanism establishes the relationship between motor speed, load torque, and friction torque, and considers the influence of temperature on friction torque and transmission efficiency, as well as heat conduction, heat convection, and heat radiation. It then calculates a first estimate of the EMB clamping force, including: The relationship between the equivalent moment of inertia and the rotational speed at the EMB motor terminal is established as follows: In the formula, This is the equivalent moment of inertia at the EMB motor end; This refers to the EMB motor speed; This provides the output torque for the EMB motor. This is the equivalent frictional torque at the EMB motor end; This refers to the load torque of the EMB motor. This is the motor torque coefficient; This refers to the q-axis current of the EMB motor. This is the critical coefficient; This is the static friction torque; This is the estimated EMB clamping force value from the previous step; This is the torque coefficient related to the clamping force; It is the coefficient of viscous friction; This is the first estimate of the EMB clamping force; For the ball screw lead; This refers to the planetary gear ratio; The transmission efficiency of the transmission mechanism; Considering the effect of temperature on frictional torque and transmission efficiency, the expression is: In the formula, The standard temperature of the brake disc; , These represent the transmission efficiency and frictional torque of the transmission mechanism at standard temperatures, respectively. , These are the correction factors for transmission efficiency and friction torque with respect to brake disc temperature, respectively. Considering heat conduction, heat convection, and heat radiation, the expression is: In the formula, For brake disc mass; The specific heat capacity of the brake disc; For brake disc temperature; , , , These are the frictional heat generation power, heat conduction power, heat convection power, and heat radiation power of the brake disc, respectively. The coefficient of friction of the brake disc; The relative rotational speed of the brake disc; The thermal conductivity of the brake disc; This refers to the contact area between the brake disc and adjacent components. The ambient temperature; This is the length of the heat conduction path; The convective heat transfer coefficient; The contact area between the brake disc and the air; Emissivity; is the Stefan-Boltzmann constant.

3. The method according to claim 2, characterized in that, The method involves acquiring data on EMB clamping force, motor rotation angle, and brake disc temperature using an EMB test bench, building an EMB clamping force fitting model, and establishing a relationship between EMB clamping force and motor rotation angle under different brake disc temperatures using a polynomial fitting method. A second estimated value of the EMB clamping force is then calculated, including: An EMB test bench was set up, an encoder was configured on the EMB motor, a pressure sensor was installed between the EMB piston and the brake pad, and a temperature sensor was built into the brake disc; a triangular wave voltage signal of 0~maximum voltage~0 was output to the EMB motor, and this process was repeated multiple times. After filtering, the motor rotation angle, brake disc temperature and clamping force data during the EMB clamping and releasing process were obtained respectively. Based on data on motor rotation angle, brake disc temperature, and clamping force, a polynomial fitting method was used to obtain the relationship between clamping force and motor rotation angle during EMB clamping and releasing processes at different brake disc temperatures. The expression is as follows: EMB clamping process EMB release process In the formula, This is a second estimate of the EMB clamping force; , , , These are polynomial coefficients, which differ at different temperatures; This refers to the motor's rotation angle; , These are the critical values ​​of motor rotation angle during the EMB clamping and releasing processes, respectively.

4. The method according to claim 3, characterized in that, The method involves acquiring data on motor current, motor voltage, motor speed, motor rotation angle, brake disc temperature, clamping force, and mileage based on an EMB test bench. An EMB clamping force data model is then built and trained using machine learning or deep learning algorithms to calculate a third estimate of the EMB clamping force, including: An EMB test bench was set up, an encoder was configured on the EMB motor, and pressure and temperature sensors were installed between the EMB piston and the brake pads. A voltage signal simulating the driver's braking torque demand was output to the EMB motor. This process was repeated several times, and after filtering, data on EMB motor current, motor voltage, motor speed, motor angle, brake disc temperature, clamping force, and mileage were obtained. An EMB clamping force data model is constructed, which uses EMB motor current, motor voltage, motor speed, motor angle, brake disc temperature, clamping force and mileage as input variables, and clamping force as output variable. The EMB clamping force data model is trained using machine learning or deep learning algorithms to obtain the trained clamping force data model, expressed as: In the formula, This is the third estimate of the EMB clamping force; This refers to the motor voltage; For the clamping force data model obtained from training; This refers to the mileage traveled.

5. The method according to claim 4, characterized in that, The process of fusing the first, second, and third estimates of the EMB clamping force using a Kalman filter algorithm to obtain a fused estimate of the EMB clamping force includes: The first estimate of the clamping force is fused based on the Kalman filter algorithm. Second estimate Third estimate The fused estimate of the EMB clamping force is obtained. The expression is: in, , , These are the weighting coefficients for the first, second, and third estimates of the clamping force, respectively.

6. The method according to claim 5, characterized in that, The step of adaptively adjusting the weights of the first, second, and third estimates of the clamping force based on the clamping force estimation error to optimize the clamping force estimation accuracy includes: The variance of the estimation error of the EMB clamping process mechanism model, the EMB clamping force fitting model, and the EMB clamping force data model within the sliding window is calculated using the following expression: In the formula, The number of data items within the sliding window. , , These represent the variances of the estimation errors for the EMB clamping process mechanism model, the EMB clamping force fitting model, and the EMB clamping force data model within the sliding window, respectively. Based on the variance of the clamping force estimation error, the weighting coefficients of the first, second, and third estimates of the clamping force are adaptively adjusted, as expressed by: in, , , These are the weighting coefficients for the first, second, and third estimates of the clamping force, respectively.

7. An EMB clamping force estimation system, characterized in that, include: The information acquisition module is used to collect real-time data related to clamping force in the EMB system, including motor current, motor voltage, motor speed, motor angle, brake disc temperature, clamping force, and mileage. The EMB clamping process mechanism model calculation module is used to establish the relationship between motor speed, load torque, and friction torque, and to consider the influence of temperature on friction torque and transmission efficiency, as well as heat conduction, heat convection, and heat radiation. It calculates the first estimate of the EMB clamping force, and constructs a corrected model of friction torque and transmission efficiency with respect to brake disc temperature, as well as a brake disc temperature rise model during the braking process. The EMB clamping force fitting model calculation module is used to build an EMB clamping force fitting model based on data of EMB clamping force, motor rotation angle, and brake disc temperature. By using a polynomial fitting method, the relationship between EMB clamping force and motor rotation angle under different brake disc temperatures is established, and the second estimated value of EMB clamping force is calculated. The EMB clamping force data model calculation module is used to build an EMB clamping force data model based on data such as motor current, motor voltage, motor speed, motor rotation angle, brake disc temperature, clamping force, and mileage, and train it using machine learning or deep learning algorithms to calculate the third estimate of the EMB clamping force. The online fusion estimation module for EMB clamping force is used to fuse the first, second, and third estimates of the EMB clamping force using a Kalman filter algorithm to obtain a fused estimate of the EMB clamping force. The module also adaptively adjusts the weights of each estimate based on the clamping force estimation error to optimize the accuracy of the clamping force estimation.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-6.

Images