Adaptive estimation method and system for braking clearance of EMB system

Abstract

The invention discloses an EMB system brake clearance adaptive estimation method and system, and relates to the technical field of automatic driving, and the method comprises the steps: receiving a motor current signal, a motor angular velocity signal and pre-calibrated system parameters, inputting the motor current signal, the motor angular velocity signal and a preset calibration parameter into a pre-established EMB system clamping force model, and outputting to obtain an EMB system clamping force value; receiving an absolute stroke signal, and performing DBSCAN data clustering processing on the absolute stroke signal in the loading stage and the clamping force value of the EMB system to obtain clustered data points; performing absolute stroke binning mean value preprocessing on the clustered data points to obtain fitting data; the method comprises the following steps: acquiring a loading stage stiffness curve model, inputting the loading stage stiffness curve model into a pre-established loading stage stiffness curve model to obtain a polynomial coefficient, generating a loading stage stiffness curve polynomial function based on the polynomial coefficient, and solving the stiffness curve polynomial function by adopting a constrained Newton iteration method to obtain an EMB system brake clearance estimated value.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to an EMB system brake gap adaptive estimation method and system. BACKGROUND

[0002] The prior art includes a detection method based on current or torque transient mutation and a brake gap adjustment method based on self-adjusting mechanical components. The current and torque method is significantly affected by temperature and motor efficiency, and the signal fluctuation is large under the same working condition, resulting in reduced reliability. At the same time, the current signal jumps abnormally in the gap elimination stage, which is incorrectly identified as a detection signal, resulting in detection failure. The detection method based on transient mutation relies on identification logic. This algorithm requires offline calibration of threshold parameters, consumes a lot of time and lacks adaptability. The adjustment method based on self-adjusting mechanical components adds mechanical components, resulting in increased complexity of the overall EMB system mechanical structure, installation difficulty and cost. At the same time, the installation and initial debugging of the self-adjusting mechanical components are complex and tedious, and the service life and reliability are severely affected by the working conditions. Once it fails or reaches the end of life, it needs to be replaced as a whole. Therefore, the method of the prior art is difficult to adapt to the complex dynamic working conditions of wear, resulting in the inability to perform online estimation quickly and at low cost in the process of adaptive estimation. SUMMARY

[0003] To solve the problems mentioned in the background art, the purpose of the present application is to provide an EMB system brake gap adaptive estimation method and system.

[0004] In a first aspect, the purpose of the present application can be achieved by the following technical solution: an EMB system brake gap adaptive estimation method, the method comprising the following steps: Receiving motor current signal, motor angular velocity signal and pre-calibrated system parameters, wherein the pre-calibrated system parameters include moment of inertia, motor torque constant, friction torque bias, clamping force related friction coefficient and torque amplification coefficient; Inputting the motor current signal, the motor angular velocity signal and the pre-set calibration parameters into a pre-established EMB system clamping force model to output the EMB system loading stage clamping force value, wherein the EMB system clamping force model is constructed based on the dynamics equation and the friction model of the EMB system; receiving the absolute stroke signal, and performing DBSCAN data clustering processing on the absolute stroke signal and the EMB system clamping force value in the loading stage to obtain the clustered data points; The absolute travel binned mean preprocessing is performed on the clustered data points to obtain fitting data; the fitting data is input into a pre-established loading stage stiffness curve model, a polynomial relationship between the absolute travel and the clamping force is fitted, polynomial coefficients are obtained, a loading stage stiffness curve polynomial function is generated based on the polynomial coefficients, a Newton iteration method with constraints is used to solve the stiffness curve polynomial function, and an EMB system brake gap estimation value is obtained.

[0005] In combination with the first aspect, in some implementations of the first aspect, the method further includes that the dynamics equation of the EMB system is described by the following formula: wherein, represents the motor current, represents the motor angular velocity, represents the moment of inertia, represents the motor torque constant, represents the friction torque, represents the load torque related to the braking force; The friction model is as follows: For the friction torque, a friction model containing load effect is used for description: wherein, represents the friction torque bias, represents the clamping force related friction coefficient, represents the clamping force, represents the viscous damping coefficient.

[0006] In combination with the first aspect, in some implementations of the first aspect, the method further includes that the calculation of the EMB system clamping force value includes: The load torque is generated by the clamping force acting on the motor through the transmission chain of the actuator : (3) wherein, represents the torque amplification coefficient, and the lead of the ball screw pair , the reduction ratio i of the speed reduction mechanism g , the transmission efficiency of the transmission chain is related to, represents the clamping force of the EMB system; The formula In combination, the clamping force model of the EMB system is as follows: The formula With the pre-calibrated system parameters, the clamping force value of the EMB system can be obtained, wherein the clamping force during the loading stage is used as the system clamping force value.

[0007] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the process of performing DBSCAN data clustering processing on the absolute travel signal and the EMB system clamping force value, comprising: Define the dataset as ; Neighborhood radius is Minimum number of neighborhood points of the core point Then for point neighborhood for: in Indicates Euclidean distance; like For the core point, if and only if the following condition is met: For unprocessed Perform DBSCAN point cluster extended classification, and define the initial point cluster as... ,Right now: In the initialization point cluster Based on this, expand the core point clusters: in, Indicates the direction of expansion of the density relationship of cluster expansion data points; Based on core point identification and point cluster expansion, DBSCAN divides the dataset into several clusters and identifies anomalous outliers, thus obtaining clustered data points.

[0008] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the process of performing absolute travel bin mean preprocessing on the clustered data points includes: The absolute travel range is divided into fixed, equal-width intervals, and the clamping force values ​​within each interval are averaged, including: Absolute travel compartment definition ; Definition and Consistent Dimension Array ; When entering absolute form correspond The closest data in the bin is indexed to find the data in... Location ; If it's the first index, then... of Replace the position value with the currently entered value. ; If it is not the first index, then for The clamping force at the position is averaged out, that is... Replace the clamping force at the position with the original value and The average value; Finally, the fitted data was obtained.

[0009] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the process of inputting the fitted data into a pre-established loading stage stiffness curve model, fitting the polynomial relationship between the absolute stroke and the clamping force, and obtaining the polynomial coefficients, including: The stiffness curve model is as follows: (9) in, This represents the estimated clamping force during the loading phase; Indicates the absolute travel distance during the loading phase; Represents the polynomial coefficients of the stiffness curve; Represents the coefficients of a polynomial containing zeros; This indicates the brake clearance value of the EMB system; The polynomial parameters are fitted using a recursive algorithm with iterative reweighting. The recursive expression is derived from the offline recursion, and the online recursive form is shown below: in, This indicates the estimated clamping force input after preprocessing; Represents the polynomial coefficient estimation vector; express Regression vector; Indicates the estimated residual; Represents the recursive weight matrix that depends on the residual; , They represent normal matrices respectively; This represents the regularization coefficient.

[0010] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the process of employing the constrained Newton iteration method includes the following steps: Let the auxiliary function be defined. : Constraints: because for The approximate polynomial of , then root converted to The derivative is 0, therefore the iterative formula is: Termination of iteration condition: in, This represents the convergence threshold.

[0011] Secondly, in order to achieve the above objectives, the present invention discloses an adaptive estimation system for braking clearance in an EMB system, comprising: The signal receiving module is used to receive motor current signals, motor angular velocity signals, and pre-calibrated system parameters, wherein the pre-calibrated system parameters include moment of inertia, motor torque constant, friction torque offset, clamping force-related friction coefficient, and torque amplification coefficient. The signal processing module is used to input the motor current signal, the motor angular velocity signal, and the preset calibration parameters into the pre-established EMB system clamping force model, and output the EMB system clamping force value. The EMB system clamping force model is constructed based on the dynamic equation and friction model of the EMB system. It also receives the absolute stroke signal and performs DBSCAN data clustering processing on the absolute stroke signal and the EMB system clamping force value to obtain the clustered data points. The brake clearance estimation module is used to preprocess the clustered data points by absolute travel bin mean to obtain fitted data. The fitted data is then input into a pre-established loading stage stiffness curve model to fit the polynomial relationship between absolute travel and clamping force, obtaining polynomial coefficients. Based on the polynomial coefficients, a loading stage stiffness curve polynomial function is generated. The constrained Newton iteration method is used to solve the stiffness curve polynomial function to obtain the brake clearance estimate of the EMB system.

[0012] In another aspect of the present invention, in order to achieve the above-mentioned objective, a terminal device is disclosed, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. The memory stores the computer program capable of running on the processor, and when the processor loads and executes the computer program, it employs an EMB system braking gap adaptive estimation method as described above.

[0013] In another aspect of the present invention, in order to achieve the above-mentioned objective, a computer-readable storage medium is disclosed, wherein a computer program is stored in the computer program, and when the computer program is loaded and executed by a processor, an adaptive estimation method for braking gap of an EMB system as described above is employed.

[0014] The beneficial effects of this invention are: This invention avoids establishing a stiffness curve model with complex hysteresis effects by estimating the applied braking force alone. Compared with the current detection method, it uses the braking force to estimate the braking gap, taking into account the dynamic characteristics of the mechanical system, and the physical meaning of the estimation model is clear. Based on clustering and mean preprocessing, it achieves adaptive outlier handling of data density and enhances the concentration of data points for stiffness curve fitting. At the same time, it combines the Polynomial Regression algorithm to increase the robustness of the estimation model to outlier data points and the fitting accuracy, thereby improving the estimation stability. Finally, it uses the constrained Newton iteration method to ensure that the zero-point solution results are within a reasonable range, satisfying the actual physical constraints while quickly and accurately estimating the braking zero-point value of the EMB system. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Figure 1 This is a schematic diagram of the method flow of the present invention; Figure 2 This is a schematic diagram of the technical route of the present invention; Figure 3 This is a schematic diagram showing the estimated clamping force under SIN unpolished working conditions according to the present invention. Figure 4 This is a schematic diagram of the preprocessing results of SIN unpolished working condition data in this invention; Figure 5 This is a schematic diagram of the braking gap estimation results based on the SIN unworn data of the present invention; Figure 6 This is a schematic diagram of the braking gap estimation results of the SIN semi-grind data of the present invention; Figure 7 This is a schematic diagram of the braking gap estimation results of the SIN full-grind data of the present invention; Figure 8 This is a schematic diagram of the braking clearance estimation results under the SIN amplitude condition of the present invention; Figure 9 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Example 1: like Figure 1 As shown, an adaptive estimation method for braking clearance in an EMB system includes the following steps: S101: Receives motor current signal, motor angular velocity signal and pre-calibrated system parameters, wherein the pre-calibrated system parameters include moment of inertia, motor torque constant, friction torque offset, clamping force related friction coefficient and torque amplification coefficient; S102: Input the motor current signal, motor angular velocity signal, and preset calibration parameters into the pre-established EMB system clamping force model, and output the EMB system clamping force value. The EMB system clamping force model is constructed based on the dynamic equation and friction model of the EMB system. Receive the absolute stroke signal, and perform DBSCAN data clustering processing on the absolute stroke signal and the EMB system clamping force value to obtain clustered data points. The dynamic equations of the EMB-based system are described by the following formula: in, Indicates motor current. Indicates the angular velocity of the motor. Represents the moment of inertia. This represents the motor torque constant. Represents frictional torque. This represents the load torque associated with braking force; The friction model is as follows: For frictional torque, a friction model incorporating load effects is used to describe it: in, This indicates a bias in the frictional torque. This represents the friction coefficient related to the clamping force. Indicates clamping force. This represents the viscous damping coefficient.

[0018] The calculation of the clamping force value of the EMB system includes: The load torque is generated by the clamping force acting on the motor through the transmission chain of the actuator. : (3) in, This represents the torque amplification factor, which is related to the lead of the ball screw pair. The reduction ratio i of the reduction mechanism g Transmission efficiency of the transmission chain related, Indicates the clamping force of the EMB system; Formula Combining these, the clamping force model of the EMB system can be obtained as follows: Using formula With the pre-calibrated system parameters, the clamping force value of the EMB system can be obtained, wherein the clamping force during the loading stage is used as the system clamping force value.

[0019] The process of performing DBSCAN data clustering on the absolute stroke signal and EMB system clamping force value during the loading phase includes: To address the transient nature of measured data such as current and angular velocity, it is necessary to process outliers in the data points composed of applied braking force and absolute stroke. Therefore, the DBSCAN data clustering method is proposed, which achieves data classification based on data density and core point clustering. The principle is as follows: Define the dataset as ; Neighborhood radius is Minimum number of neighborhood points of the core point Then for point neighborhood for: in Indicates Euclidean distance; like For the core point, if and only if the following condition is met: For unprocessed Perform DBSCAN point cluster extended classification, and define the initial point cluster as... ,Right now: In the initialization point cluster Based on this, expand the core point clusters: in, Indicates the direction of expansion of the density relationship of cluster expansion data points; Based on core point identification and point cluster expansion, DBSCAN divides the dataset into several clusters and identifies anomalous outliers, thus obtaining clustered data points.

[0020] S103: Perform absolute stroke bin mean preprocessing on the clustered data points to obtain fitted data; input the fitted data into the pre-established loading stage stiffness curve model, fit the polynomial relationship between absolute stroke and clamping force to obtain polynomial coefficients, generate the loading stage stiffness curve polynomial function based on the polynomial coefficients, and solve the stiffness curve polynomial function using the constrained Newton iteration method to obtain the estimated value of the braking clearance of the EMB system.

[0021] The process of performing absolute travel binning mean preprocessing on the clustered data points includes: To address the issue of significant interference from current noise in the clamping force estimation during the loading phase, leading to numerous scattered points on the estimated clamping force versus absolute stroke stiffness curve, a bin-averaging preprocessing method is proposed to reduce data bandwidth. The core principle of this method is to divide the absolute stroke range into fixed, equally wide intervals and, leveraging the property that clamping force values ​​are similar for close absolute strokes, average the clamping force estimates near similar absolute strokes. The specific implementation steps are as follows: Absolute travel compartment definition ; Definition and Consistent Dimension Array .

[0022] When entering absolute form correspond If the bin contains the closest data, index that data in [the bin]. Location ; If it's the first index, then... of Replace the position value with the currently entered value. ; If it is not the first index, then for The clamping force at the position is averaged out, that is... Replace the clamping force at the position with the original value and The average value; Repeated indexing can yield fitted data with narrower bandwidth and more concentrated data, thus improving the data quality of polynomial fitting.

[0023] The process of inputting the fitted data into a pre-established stiffness curve model for the loading stage, fitting the polynomial relationship between the absolute stroke and the clamping force, and obtaining the polynomial coefficients includes: The core idea of ​​adaptive brake clearance estimation is to use the stiffness curve during the loading stage to fit the polynomial relationship between the absolute stroke and the clamping force, and then use the fact that the brake clearance value equals the polynomial root to achieve online estimation of the brake clearance. The expression is as follows: (9) in, This represents the estimated clamping force during the loading phase; Indicates the absolute travel distance during the loading phase; Represents the polynomial coefficients of the stiffness curve; Represents the coefficients of a polynomial containing zeros; This indicates the brake clearance value of the EMB system; To reduce the impact of outliers and noise on the fitted polynomial coefficients To address the issue of accuracy, this invention proposes a Polynomial Regression recursive algorithm with iterative reweighting to fit polynomial parameters. Its recursive expression is derived from offline recursion, and the online recursive form is shown below: in, This indicates the estimated clamping force input after preprocessing; Represents the polynomial coefficient estimation vector; express Regression vector; Indicates the estimated residual; Represents the recursive weight matrix that depends on the residual; , They represent normal matrices respectively; This represents the regularization coefficient.

[0024] The process of using the constrained Newton iteration method includes the following steps: By fitting the polynomial parameter coefficients of the high-quality stiffness model, the root of the stiffness curve of the EMB system is solved, thus realizing the zero point of the stiffness model. It is estimated that this patent uses the Newton-Raphson iteration method to achieve a fast solution. Considering that the traditional Newton-Raphson iteration method heavily relies on the initial iteration point, leading to anomalies in the solution values ​​and failing to meet the actual physical state of the motor, a constrained Newton-Raphson iteration method is proposed to ensure that the solution is within the feasible region and stable. Its principle is detailed below: Let the auxiliary function be defined. : Constraints: because for The approximate polynomial of , then root to The derivative is 0, therefore the iterative formula is: Termination of iteration condition: in, This represents the convergence threshold.

[0025] The specific steps of the above-mentioned real-time braking zero-point estimation method are summarized in Table 1 below: Table 1. Online Estimation Steps for Braking Zero Point of EMB System Specifically, the present invention will be further illustrated below through embodiments: Figure 3 The results show that the loading clamping force estimation based on the physical mechanism can accurately match the dynamically changing real clamping force, with a maximum estimation error of 700N, which is within the expected allowable range. Moreover, this maximum error is caused by the abnormal current measurement value, and the other estimation errors are within 300N. The overall accuracy is high, providing reliable clamping force data for subsequent braking zero-point estimation.

[0026] Figure 4 The results show that after clustering and bin mean preprocessing, outlier values ​​were eliminated from the overall absolute travel and estimated clamping force data points. At the same time, this method can obtain high-quality fitting data with concentrated data and narrow bandwidth when there are many original estimated clamping force scatter points.

[0027] Figure 5 The results show that red data represents the original measurement data, blue points are stiffness curve data points after clustering and binning mean preprocessing, and the green line represents the polynomial fitted curve obtained through Polynomial Regression recursive fitting. The fitting results indicate that the actual braking clearance is close to 155.2 rad, the estimated braking clearance is 155.168 rad, and the error is -0.032 rad (2.1). The result (%) proves that the method of the present invention can achieve high-precision online estimation of braking clearance in EMB systems.

[0028] To demonstrate the reliability and accuracy of the method under other operating conditions, data from different wear states were used for verification, and the results are as follows: Figure 6-8 As shown, the estimation results are summarized in Table 2. These results demonstrate that under different operating conditions, the braking clearance estimation error is within 0.1 rad (0.064%). The method of this invention achieves low-cost, online, accurate, and high-precision estimation of the braking clearance in EMB systems based on existing signal data, without requiring calibration of the clearance identification logic.

[0029] Table 2. Braking clearance estimation results under different operating conditions Example 2: To achieve the above objective, such as Figure 9 As shown, based on Embodiment 1, this invention discloses an adaptive estimation system for braking clearance in an EMB system, comprising: The signal receiving module 11 is used to receive motor current signals, motor angular velocity signals, and pre-calibrated system parameters, wherein the pre-calibrated system parameters include moment of inertia, motor torque constant, friction torque offset, clamping force-related friction coefficient, and torque amplification coefficient. The signal processing module 12 is used to input the motor current signal, the motor angular velocity signal, and the preset calibration parameters into the pre-established EMB system clamping force model, and output the clamping force value of the EMB system during the loading stage. The EMB system clamping force model is constructed based on the dynamic equation and friction model of the EMB system. It also receives the absolute stroke signal and performs DBSCAN data clustering processing on the absolute stroke signal and the EMB system clamping force value during the loading stage to obtain the clustered data points. The brake clearance estimation module 13 is used to preprocess the clustered data points by absolute travel bin mean to obtain fitted data; the fitted data is input into the pre-established loading stage stiffness curve model to fit the polynomial relationship between absolute travel and clamping force to obtain polynomial coefficients; a loading stage stiffness curve polynomial function is generated based on the polynomial coefficients; and the stiffness curve polynomial function is solved using the constrained Newton iteration method to obtain the brake clearance estimate of the EMB system.

[0030] Based on the same inventive concept, this invention also provides a computer device, comprising: one or more processors, and a memory for storing one or more computer programs; the programs include program instructions, and the processor executes the program instructions stored in the memory. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, used to implement one or more instructions, specifically for loading and executing one or more instructions stored in a computer storage medium to implement the above-described method.

[0031] It should be further explained that, based on the same inventive concept, the present invention also provides a computer storage medium storing a computer program, which, when executed by a processor, performs the above-described method. This storage medium can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0032] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. 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.

[0033] The foregoing has shown and described the basic principles, main features, and advantages of this disclosure. Those skilled in the art should understand that this disclosure is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of this disclosure. Various changes and modifications can be made to this disclosure without departing from its spirit and scope, and all such changes and modifications fall within the scope of this disclosure as claimed.

Claims

1. An adaptive estimation method for braking clearance in an EMB system, characterized in that, The method includes the following steps: The system receives motor current signals, motor angular velocity signals, and pre-calibrated system parameters, including moment of inertia, motor torque constant, friction torque offset, clamping force-related friction coefficient, and torque amplification factor. The motor current signal, motor angular velocity signal, and preset calibration parameters are input into the pre-established EMB system clamping force model, and the clamping force value of the EMB system during the loading stage is output. The EMB system clamping force model is constructed based on the dynamic equation and friction model of the EMB system. The absolute stroke signal is received, and the absolute stroke signal and the clamping force value of the EMB system during the loading stage are subjected to DBSCAN data clustering processing to obtain the clustered data points. The clustered data points are preprocessed with absolute travel bin mean to obtain fitted data. The fitted data is then input into a pre-established loading stage stiffness curve model to fit the polynomial relationship between absolute travel and clamping force, obtaining polynomial coefficients. Based on the polynomial coefficients, a loading stage stiffness curve polynomial function is generated. The stiffness curve polynomial function is solved using the constrained Newton iteration method to obtain the estimated value of the braking clearance of the EMB system.

2. The adaptive estimation method for braking clearance in an EMB system according to claim 1, characterized in that, The dynamic equations of the EMB-based system are described by the following formula: in, Indicates motor current. Indicates the angular velocity of the motor. Represents the moment of inertia. This represents the motor torque constant. Represents frictional torque. This represents the load torque associated with braking force; The friction model is as follows: For frictional torque, a friction model incorporating load effects is used to describe it: in, This indicates a bias in the frictional torque. This represents the friction coefficient related to the clamping force. Indicates clamping force. This represents the viscous damping coefficient.

3. The adaptive estimation method for braking clearance in an EMB system according to claim 1, characterized in that, The calculation of the clamping force value of the EMB system includes: The load torque is generated by the clamping force acting on the motor through the transmission chain of the actuator. : （3） in, This represents the torque amplification factor, which is related to the lead of the ball screw pair. The reduction ratio i of the reduction mechanism g Transmission efficiency of the transmission chain related, Indicates the clamping force of the EMB system; Formula Combining these, the clamping force model of the EMB system can be obtained as follows: Using formula With the pre-calibrated system parameters, the clamping force value of the EMB system can be obtained, wherein the clamping force during the loading stage is used as the system clamping force value.

4. The adaptive estimation method for braking clearance in an EMB system according to claim 1, characterized in that, The process of performing DBSCAN data clustering on the absolute travel signal and EMB system clamping force value during the loading phase includes: Define the dataset as ; Neighborhood radius is Minimum number of neighborhood points of the core point Then for point neighborhood for: in Indicates Euclidean distance; like For the core point, if and only if the following condition is met: For unprocessed Perform DBSCAN point cluster extended classification, and define the initial point cluster as... ,Right now: In the initialization point cluster Based on this, expand the core point clusters: in, Indicates the direction of expansion of the density relationship of cluster expansion data points; Based on core point identification and point cluster expansion, DBSCAN divides the dataset into several clusters and identifies anomalous outliers, thus obtaining clustered data points.

5. The adaptive estimation method for braking clearance in an EMB system according to claim 1, characterized in that, The process of performing absolute travel binning mean preprocessing on the clustered data points includes: The absolute travel range is divided into fixed, equal-width intervals, and the clamping force values ​​within each interval are averaged, including: Absolute travel compartment definition ; Definition and Consistent Dimension Array ; When entering absolute form correspond The closest data in the bin is indexed to find the data in... Location ; If it's the first index, then... of Replace the position value with the currently entered value. ; If it is not the first index, then for The clamping force at the position is averaged out, that is... Replace the clamping force at the position with the original value and The average value; Finally, the fitted data was obtained.

6. The adaptive estimation method for braking clearance in an EMB system according to claim 1, characterized in that, The process of inputting the fitted data into a pre-established loading stage stiffness curve model, fitting the polynomial relationship between the absolute stroke and the clamping force, and obtaining the polynomial coefficients includes: The stiffness curve model is as follows: （9） in, This represents the estimated clamping force during the loading phase; Indicates the absolute travel distance during the loading phase; Represents the polynomial coefficients of the stiffness curve; Represents the coefficients of a polynomial containing zeros; This indicates the brake clearance value of the EMB system; The polynomial parameters are fitted using a recursive algorithm with iterative reweighting. The recursive expression is derived from the offline recursion, and the online recursive form is shown below: in, This indicates the estimated clamping force input after preprocessing; Represents the polynomial coefficient estimation vector; express Regression vector; Indicates the estimated residual; Represents the recursive weight matrix that depends on the residual; , They represent normal matrices respectively; This represents the regularization coefficient.

7. The adaptive estimation method for braking clearance in an EMB system according to claim 1, characterized in that, The process of using the constrained Newton iteration method includes the following steps: Let the auxiliary function be defined. : Constraints: because for The approximate polynomial of , then root to The derivative is 0, therefore the iterative formula is: Termination of iteration condition: in, This represents the convergence threshold.

8. An adaptive braking clearance estimation system for an EMB system, employing the adaptive braking clearance estimation method for an EMB system as described in any one of claims 1 to 7, characterized in that, include: The signal receiving module is used to receive motor current signals, motor angular velocity signals, and pre-calibrated system parameters, wherein the pre-calibrated system parameters include moment of inertia, motor torque constant, friction torque offset, clamping force-related friction coefficient, and torque amplification coefficient. The signal processing module is used to input the motor current signal, motor angular velocity signal, and preset calibration parameters into the pre-established EMB system clamping force model, and output the clamping force value of the EMB system during the loading stage. The EMB system clamping force model is constructed based on the dynamic equation and friction model of the EMB system. It receives the absolute stroke signal and performs DBSCAN data clustering processing on the absolute stroke signal and the EMB system clamping force value during the loading stage to obtain the clustered data points. The brake clearance estimation module is used to preprocess the clustered data points by absolute travel bin mean to obtain fitted data. The fitted data is then input into a pre-established loading stage stiffness curve model to fit the polynomial relationship between absolute travel and clamping force, obtaining polynomial coefficients. Based on the polynomial coefficients, a loading stage stiffness curve polynomial function is generated. The constrained Newton iteration method is used to solve the stiffness curve polynomial function to obtain the brake clearance estimate of the EMB system.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, The memory stores a computer program that can run on a processor. When the processor loads and executes the computer program, it employs an adaptive estimation method for braking gap of an EMB system according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is loaded and executed by the processor, it employs an adaptive estimation method for braking gap of an EMB system as described in any one of claims 1 to 7.

Images