Electromechanical braking clamping force estimation method and device, medium and equipment

Abstract

The invention provides an electronic mechanical braking clamping force estimation method and device, a medium and equipment. The method comprises the steps that estimated clamping force is output through an electronic mechanical braking clamping force initial estimation model; if the deviation between the estimated clamping force and the actual clamping force does not meet the deviation range, determining a target influence factor influencing the estimated clamping force; correcting the initial estimation model of the electromechanical braking clamping force based on the target influence factor to obtain a corrected estimation model of the electromechanical braking clamping force; re-estimating the clamping force by using an electronic mechanical braking clamping force correction estimation model to obtain a target clamping force meeting the deviation range; therefore, even if the pre-estimated clamping force does not meet the precision requirement due to the influence of some scenes, the target influence factor can be determined, the initial pre-estimation model of the electronic mechanical braking clamping force is corrected again, and the clamping force is pre-estimated again by using the corrected model, so that the precision of the pre-estimated clamping force is improved, and the control precision of the vehicle braking force is improved.

Description

Technical Field

[0001] This invention relates to the field of automotive braking technology, and in particular to a method, device, medium, and equipment for estimating electromechanical braking clamping force. Background Technology

[0002] Electromechanical braking is a purely dry brake-by-wire method with advantages such as fast response, environmental friendliness, high control precision, and the ability for all four wheels to respond independently to braking requests. It is widely used in vehicle braking systems.

[0003] However, the clamping force estimation in the existing technology is inaccurate under certain conditions, which affects the accuracy of braking force control and causes the vehicle's braking force to fail to meet the requirements, resulting in a deviation in braking force.

[0004] Therefore, there is an urgent need for a method to improve the accuracy of clamping force estimation in order to meet the braking requirements of the entire vehicle. Summary of the Invention

[0005] To address the problems existing in the prior art, embodiments of the present invention provide a method, apparatus, medium, and device for estimating electromechanical braking clamping force, in order to solve or partially solve the technical problem in the prior art where the clamping force estimation is inaccurate under certain scenario conditions, affecting the accuracy of braking force control.

[0006] This invention provides a method for estimating electromechanical braking clamping force, the method comprising: The estimated clamping force is output using a pre-created initial estimation model of electromechanical braking clamping force. If the deviation between the estimated clamping force and the actual clamping force does not meet the deviation range, then the target influence factor that affects the estimated clamping force is determined. The initial prediction model of the electromechanical braking clamping force is modified based on the target influence factor to obtain the modified prediction model of the electromechanical braking clamping force. The clamping force is re-estimated using the electromechanical braking clamping force correction prediction model to obtain the target clamping force that meets the deviation range.

[0007] In the above scheme, the electromechanical braking clamping force prediction model includes multiple influencing factors that affect the clamping force. Before outputting the predicted clamping force using the pre-created electromechanical braking clamping force initial prediction model, the method further includes: During the vehicle component development phase, the first data, including clamping force, electromechanical caliper motor current, motor rotation angle, friction pad thickness, wheel edge temperature, motor temperature, and cumulative braking count of the electromechanical caliper, are obtained based on the test platform. A first electromechanical braking clamping force prediction model is then constructed. An optimization learning algorithm is used to train the first electromechanical braking clamping force prediction model to obtain the trained first electromechanical braking clamping force prediction model. During actual vehicle use, a multi-dimensional data recording platform is used to obtain second data such as clamping force, electromechanical caliper motor current, motor rotation angle, friction pad thickness, wheel edge temperature, motor temperature, cumulative braking times of the electromechanical caliper, ambient humidity, and aging time of the electromechanical caliper. The second data is used to iteratively train the first electromechanical braking clamping force prediction model to obtain the initial prediction model of the electromechanical braking clamping force.

[0008] In the above scheme, the target influencing factors that affect the estimated clamping force include: Determine the initial sample data where the deviation exceeds the standard, and perform data preprocessing on the initial sample data where the deviation exceeds the standard to obtain the corresponding target sample data where the deviation exceeds the standard; the initial sample data where the deviation exceeds the standard is the data corresponding to when the deviation between the estimated clamping force and the actual clamping force does not meet the deviation range. Based on the target sample data of each group of deviations exceeding the standard, the correlation coefficient between each influencing factor and the deviation is determined, and all influencing factors with correlation coefficients greater than a preset coefficient threshold are used as the deviation sample set. The deviation sample set is clustered using a clustering algorithm to obtain multiple deviation scenarios; The influencing factors in each deviation scenario are determined as the target influencing factors.

[0009] In the above scheme, the clustering algorithm is used to cluster the deviation sample set to obtain multiple deviation scenarios, including: Randomly selected from the set of deviation samples K 1 sample is used as the initial cluster center; Determine each deviation sample to K The Euclidean distance between the initial cluster centers is used to classify each of the biased samples into the nearest cluster based on the Euclidean distance; The mean of each cluster is redefined as the new cluster center. The clustering is iterated repeatedly until the cluster centers no longer change or the upper limit of the number of iterations is reached, resulting in multiple clusters. Each cluster represents a deviation scenario.

[0010] In the above scheme, the step of correcting the initial prediction model of the electromechanical braking clamping force based on the target influence factor to obtain a corrected prediction model of the electromechanical braking clamping force includes: Determine the target compensation coefficient corresponding to the target impact factor; The compensation coefficient of the target influence factor in the electromechanical braking clamping force correction prediction model is adjusted to the target compensation coefficient to obtain the electromechanical braking clamping force correction prediction model.

[0011] In the above scheme, determining the target compensation coefficient corresponding to the target impact factor includes: Obtain the current value of the target influence factor; Based on the current value, the corresponding target compensation coefficient is searched in the pre-created compensation coefficient database; the compensation coefficient database has a pre-fitted correspondence between the target influence factor and the target compensation coefficient.

[0012] A second aspect of the present invention provides an electromechanical braking clamping force estimation device, the device comprising: The first estimation unit is used to output the estimated clamping force using a pre-created electromechanical braking clamping force initial estimation model. The determining unit is used to determine the target influence factor that affects the estimated clamping force if the deviation between the estimated clamping force and the actual clamping force does not meet the deviation range. The correction unit corrects the initial prediction model of the electromechanical braking clamping force based on the target influence factor to obtain the corrected prediction model of the electromechanical braking clamping force. The second prediction unit is used to re-predict the clamping force using the electromechanical braking clamping force correction prediction model to obtain the target clamping force that meets the deviation range.

[0013] In the above scheme, the determining unit is specifically used for: The initial sample data of deviation exceeding the standard is determined, and the data of deviation exceeding the standard is preprocessed to obtain the corresponding target sample data of deviation exceeding the standard; the initial sample data of deviation exceeding the standard is the data in which the deviation between the estimated clamping force and the actual clamping force does not meet the deviation range. Based on the target sample data of each group of deviations exceeding the standard, the correlation coefficient between each influencing factor and the deviation is determined, and all influencing factors with correlation coefficients greater than a preset coefficient threshold are used as the deviation sample set. The deviation sample set is clustered using a clustering algorithm to obtain multiple deviation scenarios; The influencing factors in each deviation scenario are determined as the target influencing factors.

[0014] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any of the first aspects.

[0015] A fourth aspect of the present invention is a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the steps of the method described in any of the first aspects.

[0016] This invention provides a method, apparatus, medium, and device for estimating electromechanical braking clamping force. The method includes: outputting an estimated clamping force using a pre-created initial estimation model of electromechanical braking clamping force. If the deviation between the estimated clamping force and the actual clamping force does not meet the deviation range, a target influence factor affecting the estimated clamping force is determined. Based on the target influence factor, the initial electromechanical braking clamping force estimation model is corrected to obtain a corrected electromechanical braking clamping force estimation model. The clamping force is re-estimated using the corrected electromechanical braking clamping force estimation model to obtain a target clamping force that meets the deviation range. In this way, even if the estimated clamping force does not meet the accuracy requirements due to the influence of certain scenarios, the target influence factor can be determined, the initial electromechanical braking clamping force estimation model can be corrected again, and the clamping force can be re-estimated using the corrected model, thereby improving the accuracy of the estimated clamping force and improving the control accuracy of the vehicle's braking force. Attached Figure Description

[0017] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A schematic flowchart of an electromechanical braking clamping force estimation method according to an embodiment of the present invention is shown; Figure 2 A schematic diagram is shown when there is a deviation between the estimated clamping force and the actual clamping force according to an embodiment of the present invention; Figure 3 A schematic diagram of an electromechanical braking clamping force estimation device according to an embodiment of the present invention is shown. Detailed Implementation

[0018] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0019] Generally, the estimation of electromechanical braking clamping force is related to many factors, including environmental conditions, the surface condition of the friction pads, the temperature of the friction pads and brake disc, and the service life of the electromechanical calipers. If these influencing factors are not fully considered and the comprehensive impact of multiple factors is not sufficiently studied, it can easily lead to inaccurate clamping force estimation under certain conditions, affecting the accuracy of braking force control, resulting in the vehicle's braking force not meeting the requirements and causing braking force deviations.

[0020] Therefore, to address the issues of insufficient coverage of calibration scenarios and incomplete matching of related influencing factors in the electromechanical braking clamping force estimation model, which affect the accuracy of clamping force estimation, this invention provides a method for estimating electromechanical braking clamping force, such as... Figure 1 As shown, the method includes the following steps: S110 outputs the estimated clamping force using a pre-created electromechanical braking clamping force initial estimation model.

[0021] In one implementation, the electromechanical braking clamping force prediction model includes multiple influencing factors that affect the clamping force. Before outputting the predicted clamping force using a pre-created electromechanical braking clamping force initial prediction model, it is necessary to construct the electromechanical braking clamping force initial prediction model. Therefore, the method further includes: During the vehicle component development phase, the first data, including clamping force, electromechanical caliper motor current, motor rotation angle, friction pad thickness, wheel edge temperature, motor temperature, and cumulative braking count of the electromechanical caliper, are obtained based on the test platform. A first electromechanical braking clamping force prediction model is then constructed. An optimization learning algorithm is used to train the first electromechanical braking clamping force prediction model to obtain the trained first electromechanical braking clamping force prediction model. During actual vehicle use, a multi-dimensional data recording platform is used to obtain second data such as clamping force, electromechanical caliper motor current, motor rotation angle, friction pad thickness, wheel edge temperature, motor temperature, cumulative braking times of the electromechanical caliper, ambient humidity, and aging time of the electromechanical caliper. The second data is used to iteratively train the first electromechanical braking clamping force prediction model to obtain the initial prediction model of electromechanical braking clamping force.

[0022] Specifically, the electromechanical braking clamping force is related to multiple influencing factors, such as: electromechanical caliper current, electromechanical caliper piston displacement, friction plate thickness, friction plate usage time, ambient humidity, friction plate temperature, electromechanical caliper usage time, etc. In order to make up for the shortcomings of traditional model calibration in terms of single scenario and incomplete consideration of influencing factors, this invention obtains multiple influencing factors affecting the clamping force through a multi-dimensional data recording platform.

[0023] Several influencing factors include: electromechanical caliper motor current, motor rotation angle, friction pad thickness (reflecting the wear degree of the friction pad, thickness range from 0 to initial thickness), and wheel edge temperature (thermal state of brake disc and friction pad, -40℃ to 600℃). ), motor temperature (80~120) The parameters include the cumulative braking cycles of the electromechanical caliper (aging of components such as the ball screw, ranging from 0 to 2.2 million cycles), ambient humidity (0% to 100%), and aging time of the electromechanical caliper (0 to 30 years). These parameters cover all aspects of the electromechanical caliper, from hardware condition (friction pads, caliper) to operating parameters (current, wheel edge temperature), thus improving the coverage of the operating scenarios and factors affecting clamping force estimation for electromechanical calipers.

[0024] This invention constructs a first electromechanical braking clamping force prediction model during the component development stage, and trains the first electromechanical braking clamping force prediction model using the first data of the influencing factors during the component development stage; then, during the actual use of the vehicle, the first electromechanical braking clamping force prediction model is trained again using the data of the influencing factors collected during the actual use process, and finally obtains an electromechanical braking clamping force prediction model that conforms to the actual application scenario.

[0025] The electromechanical braking clamping force prediction model can be either a regression model or a neural network model; no restriction is imposed here.

[0026] During the component development stage, design of experiments (DOE) verification tests can be designed according to the influencing factors shown in Table 1 to obtain the variation law of clamping force with the influencing factors. Then, a data model between clamping force and influencing factors can be constructed based on the experimental data of each influencing factor. The deviation between the estimated clamping force calculated by the model and the actual clamping force needs to be within the deviation range (e.g., -5% to 5%).

[0027] Table 1

[0028] The first electromechanical braking clamping force prediction model can be expressed as shown in formula (1): (1) In formula (1), i This is the motor current. For the motor rotation angle, t For the thickness of the friction plate, This refers to the wheel edge temperature. For motor temperature, N This refers to the number of braking cycles of the electromechanical caliper.

[0029] Wheel-side temperatures include: -40℃, room temperature (25℃), 100℃, 200℃, 400℃, and 600℃; wheel-side temperatures can be estimated based on friction braking intensity and braking duration.

[0030] Motor temperatures include: 80℃, 100℃, and 120℃; motor temperature can be estimated based on the motor temperature as a function of motor current and duration.

[0031] The number of braking cycles for electromechanical calipers includes: 0, 22,000, 220,000, 1.1 million, and 2.2 million. Friction pad thickness: t0 (initial thickness of new pad), 70%t0, 40%t0 and 10%t0.

[0032] In actual vehicle use, environmental factors also play a role. Therefore, vehicles are equipped with sensors to collect data on various influencing factors, enabling the acquisition of data on a wider range of factors. For example, influencing factors may include ambient humidity and the aging time of electromechanical calipers. Thus, a predictive model for electromechanical braking clamping force that aligns with real-world application scenarios is needed. It can be: (2) In formula (2), For ambient humidity, This refers to the aging time.

[0033] In addition, when the vehicle enters mass production, a certain proportion of electromechanical caliper clamping force sensors need to be installed on the vehicle to collect the actual clamping force of the vehicle, so that the model training can provide sufficient sample data.

[0034] Then, the first electromechanical brake clamping force prediction model is retrained using the data of influencing factors collected during actual use. When the deviation between the actual clamping force and the predicted clamping force is less than the preset deviation threshold, the electromechanical brake clamping force prediction model that conforms to the actual application scenario is output.

[0035] For example, when the electromechanical braking clamping force prediction model is a regression model, the model can be expressed as: (3) In formula (3), This is the current compensation coefficient. This is the first compensation coefficient for the motor rotation angle. This is the second compensation coefficient for the motor rotation angle. This is the friction plate wear compensation coefficient. t This represents the current thickness of the friction pad. This is the wheel-side temperature compensation coefficient. This is the thermal compensation coefficient for motor temperature. The aging compensation coefficient is the cumulative number of braking cycles. This is the humidity compensation coefficient. This is the duration compensation coefficient for aging time. This is the preset initial clamping force.

[0036] The exponent term is used for The nonlinear gain of the quantized motor rotation angle on the clamping force has the following specific meaning: when When the value is greater than 1, the gain of the clamping force on the motor rotation angle increases with the increase of the rotation angle (e.g., in the small rotation angle stage, the force rises rapidly after overcoming the gap). when When =1, it degenerates into a linear relationship (ideal lossless scenario). when When <1: This indicates that the gain of the angle on the clamping force decreases as the angle increases (e.g., in the large angle stage, the friction plate saturates or the friction coefficient decreases). Therefore, by adjusting The value can accurately fit the nonlinear characteristics of clamping force under different working conditions.

[0037] After the above-mentioned electromechanical braking clamping force prediction model is successfully trained, the vehicle can output the predicted clamping force by collecting the above-mentioned influencing factors and combining them with the electromechanical braking clamping force prediction model during actual use.

[0038] S111, if the deviation between the estimated clamping force and the actual clamping force does not meet the deviation range, then determine the target influence factor that affects the estimated clamping force.

[0039] As mentioned above, if the above influencing factors fluctuate (for example, in a low-temperature and high-humidity environment, the ambient humidity is greater than 80% and the temperature is less than -10°C), If this happens, the estimated clamping force may deviate, resulting in the estimated clamping force not meeting the required accuracy.

[0040] As the electromechanical caliper motor rotates, it drives the ball screw and piston to displace, gradually increasing the clamping force. A clamping force sensor measures the actual clamping force, and the deviation can be determined by comparing the actual and estimated clamping forces. If the deviation between the estimated and actual clamping forces exceeds the upper limit, it is determined that the estimated clamping force estimation is abnormal. (Reference) Figure 2 The estimated clamping force matches the actual clamping force well in the early stage, but gradually deviates from the actual clamping force in the middle and later stages, eventually exceeding the upper limit of the deviation requirement. Therefore, the estimated model needs to be corrected.

[0041] That is, when the deviation between the estimated clamping force and the actual clamping force does not meet the deviation range (greater than the upper limit of the deviation threshold or less than the lower limit of the deviation threshold, the upper limit of the deviation threshold can be 5%, and the lower limit of the deviation threshold can be -5%), it is necessary to determine the target influence factor that affects the estimated clamping force, and then the initial prediction model of the electromechanical brake clamping force can be corrected according to the target influence factor.

[0042] The actual clamping force can be obtained from a clamping force sensor. Here, the clamping force sensor only performs data acquisition and verification functions, providing a basis for model correction. For vehicles equipped with a clamping force sensor, the closed-loop control of the braking system still relies on the clamping force estimated by the model for braking control, rather than directly using the sensor's measured value. This significantly reduces the braking system's dependence on the clamping force sensor. Even if the sensor fails, the system can maintain normal operating logic based on a stable estimation model, effectively avoiding unexpected system degradation caused by sensor failure and ensuring the continuity and safety of braking function.

[0043] Deviation between estimated clamping force and actual clamping force It can be determined according to formula (4): (4) In formula (4), The actual clamping force, To estimate the clamping force.

[0044] In one implementation, determining the target influencing factors that affect the estimated clamping force includes: Determine the initial sample data where the deviation exceeds the standard, and perform data preprocessing on the initial sample data where the deviation exceeds the standard to obtain the corresponding target sample data where the deviation exceeds the standard; the initial sample data where the deviation exceeds the standard is the data corresponding to when the deviation between the estimated clamping force and the actual clamping force does not meet the deviation range. Based on the target sample data of each group of deviations exceeding the standard, the correlation coefficient between each influencing factor and the deviation is determined, and all influencing factors with correlation coefficients greater than a preset coefficient threshold are used as the deviation sample set. The deviation sample set is clustered using a clustering algorithm to obtain multiple deviation scenarios; The influencing factors in each deviation scenario are determined as the target influencing factors.

[0045] Specifically, the deviation data needs to be grouped according to the characteristics of the influencing factors. Deviation samples with similar characteristics are clustered into one class, and each class corresponds to a deviation concentration scenario, as follows: First, obtain the true value of each influencing factor when the deviation is greater than the deviation threshold; a set of true values ​​is a set of initial sample data with deviation exceeding the standard, and then multiple sets of initial sample data with deviation exceeding the standard are obtained.

[0046] For each set of initial sample data exceeding the deviation limit, data cleaning is performed to remove invalid data, resulting in target sample data exceeding the deviation limit. Invalid data includes data that is empty due to sensor malfunction or extreme outliers (e.g., ambient humidity of 200 degrees, which is significantly beyond the physical range).

[0047] Then, features with a high correlation to the deviation need to be selected from all influencing factors. All influencing factors need to be classified according to feature similarity to obtain environmental features, mechanical features, and electrical features. Among them, environmental features can include ambient humidity; mechanical features can include friction pad thickness, cumulative braking times, and aging time; electrical features can include motor current and motor temperature.

[0048] Calculate the correlation coefficient (or Pearson correlation coefficient) between each feature (which can be the mean) and the deviation, and retain features with correlation coefficients greater than a preset threshold, which can be 0.3. Taking environmental humidity as an example, multiple environmental humidity means can be determined, and then the correlation coefficient between the humidity mean and the deviation can be calculated.

[0049] For example, if the correlation coefficient between the friction plate thickness and the deviation is 0.6, then this feature is retained; if the correlation coefficient between the motor current and the deviation is 0.1, then it is discarded.

[0050] After the above screening, the cluster feature set can be obtained. The cluster feature set can also be understood as the deviation sample set that affects the estimated clamping force.

[0051] Next, the K-means clustering algorithm can be used to iteratively optimize the clustering feature set, and the biased samples can be clustered into multiple biased scenarios.

[0052] Since the training logic of K-means iteratively updates cluster centers and minimizes intra-cluster differences, one implementation uses the K-means clustering algorithm to iteratively optimize the clustering feature set, clustering the biased samples into multiple bias scenarios, including: Randomly select from the biased sample set K 1 sample is used as the initial cluster center; Calculate each deviation sample to K The Euclidean distance between the centers is used to classify the biased samples into the nearest cluster; the mean of each cluster is recalculated as the new cluster center. Repeatedly iterate the clustering process until the cluster centers no longer change or the upper limit of the number of iterations is reached (e.g., 100 times), thus obtaining multiple clusters. Each cluster represents a deviation scenario, and each cluster has corresponding typical features (key influencing factors).

[0053] For example, suppose K= 2. The centers of the two obtained clusters are shown in Table 2: Table 2

[0054] As can be seen, the bias of cluster 2 meets the standard, therefore cluster 1 is retained: Cluster 1 represents the deviation scenario of late-stage friction pad wear and high aging. The influencing factors in this deviation scenario are friction pad thickness and cumulative braking count. Therefore, the final target influencing factors are friction pad thickness and cumulative braking count.

[0055] S112, Based on the target influence factor, the initial prediction model of the electromechanical braking clamping force is modified to obtain the modified prediction model of the electromechanical braking clamping force.

[0056] Once the target impact factor is determined, the initial prediction model of the electromechanical braking clamping force can be modified based on the target impact factor to obtain the modified prediction model of the electromechanical braking clamping force.

[0057] In one implementation, the initial prediction model of the electromechanical braking clamping force is modified based on the target influence factor to obtain a modified prediction model of the electromechanical braking clamping force, including: Determine the target compensation coefficient corresponding to the target impact factor; The compensation coefficient of the target influence factor in the electromechanical braking clamping force correction prediction model is adjusted to the target compensation coefficient to obtain the electromechanical braking clamping force correction prediction model.

[0058] In one implementation, determining the target compensation coefficient corresponding to the target impact factor includes: Obtain the current value of the target impact factor; The system searches for the corresponding target compensation coefficient in a pre-created compensation coefficient database based on the current value. The compensation coefficient database contains a pre-fitted correspondence between the target influence factor and the target compensation coefficient.

[0059] That is, if the target influencing factor is the friction plate thickness, the wear compensation coefficient in the electromechanical braking clamping force correction prediction model is adjusted, and the electromechanical braking clamping force correction prediction model is output.

[0060] If the target influencing factor is wheel edge temperature, adjust the wheel edge temperature compensation coefficient in the electromechanical brake clamping force correction prediction model and output the electromechanical brake clamping force correction prediction model. If the target influencing factor is environmental humidity, adjust the humidity compensation coefficient in the electromechanical brake clamping force correction prediction model to output the electromechanical brake clamping force correction prediction model.

[0061] If the target influencing factor is the aging time, the friction compensation coefficient in the electromechanical braking clamping force correction prediction model is adjusted until the accuracy of the initial prediction model of the electromechanical braking clamping force meets the preset requirements, and the electromechanical braking clamping force correction prediction model is output.

[0062] S113, the clamping force is re-estimated using the electromechanical braking clamping force correction prediction model to obtain the target clamping force that meets the deviation range.

[0063] After the electromechanical braking clamping force correction prediction model is output, the clamping force can be re-predicted using the electromechanical braking clamping force correction prediction model to obtain the target clamping force that meets the deviation range, thereby improving the estimation accuracy of the clamping force.

[0064] Based on the same inventive concept as in the foregoing embodiments, this embodiment also provides an electromechanical braking clamping force estimation device, such as... Figure 3 As shown, the device includes: The first estimation unit 31 is used to output the estimated clamping force using a pre-created electromechanical braking clamping force initial estimation model. The determining unit 32 is used to determine the target influence factor that affects the estimated clamping force if the deviation between the estimated clamping force and the actual clamping force does not meet the deviation range. Correction unit 33 corrects the initial prediction model of electromechanical braking clamping force based on the target influence factor to obtain the corrected prediction model of electromechanical braking clamping force. The second prediction unit 34 is used to re-predict the clamping force using the electromechanical braking clamping force correction prediction model to obtain the target clamping force that meets the deviation range.

[0065] In one embodiment, the determining unit 32 is specifically used for: The initial sample data of deviation exceeding the standard is determined, and the data of deviation exceeding the standard is preprocessed to obtain the corresponding target sample data of deviation exceeding the standard; the initial sample data of deviation exceeding the standard is the data in which the deviation between the estimated clamping force and the actual clamping force does not meet the deviation range. Based on the target sample data of each group of deviations exceeding the standard, the correlation coefficient between each influencing factor and the deviation is determined, and all influencing factors with correlation coefficients greater than a preset coefficient threshold are used as the deviation sample set. The deviation sample set is clustered using a clustering algorithm to obtain multiple deviation scenarios; The influencing factors in each deviation scenario are determined as the target influencing factors.

[0066] Since the apparatus described in the embodiments of this invention is used for implementing the electromechanical braking clamping force estimation method of the embodiments of this invention, those skilled in the art can understand the specific structure and variations of the apparatus based on the method described in the embodiments of this invention, and therefore will not be described in detail here. All apparatuses used in the methods of the embodiments of this invention fall within the scope of protection of this invention.

[0067] Based on the same inventive concept, this embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any step of the method described above.

[0068] Based on the same inventive concept, this embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0069] Through one or more embodiments of the present invention, the present invention has the following beneficial effects or advantages: This invention provides a method, apparatus, medium, and device for estimating electromechanical braking clamping force. The method includes: outputting an estimated clamping force using a pre-created initial estimation model of electromechanical braking clamping force. If the deviation between the estimated clamping force and the actual clamping force does not meet the deviation range, a target influence factor affecting the estimated clamping force is determined. Based on the target influence factor, the initial electromechanical braking clamping force estimation model is corrected to obtain a corrected electromechanical braking clamping force estimation model. The clamping force is re-estimated using the corrected electromechanical braking clamping force estimation model to obtain a target clamping force that meets the deviation range. In this way, even if the estimated clamping force does not meet the accuracy requirements due to the influence of certain scenarios, the target influence factor can be determined, the initial electromechanical braking clamping force estimation model can be corrected again, and the clamping force can be re-estimated using the corrected model, thereby improving the accuracy of the estimated clamping force and improving the control accuracy of the vehicle's braking force.

[0070] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, this invention is not directed to any particular programming language. It should be understood that the contents of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the invention.

[0071] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0072] Similarly, it should be understood that, in order to simplify this disclosure and aid in understanding one or more of the various aspects of the invention, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof. However, this method of disclosure should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into this detailed description, wherein each claim itself is a separate embodiment of the invention.

[0073] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0074] Furthermore, those skilled in the art will understand that although some embodiments herein include certain features included in other embodiments but not others, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0075] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components of the gateway, proxy server, or system according to embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such programs implementing the present invention can be stored on a computer-readable medium or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0076] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0077] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0078] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for estimating the clamping force of an electromechanical brake, characterized in that, The method includes: The estimated clamping force is output using a pre-created initial estimation model of electromechanical braking clamping force. If the deviation between the estimated clamping force and the actual clamping force does not meet the deviation range, then the target influence factor that affects the estimated clamping force is determined. The initial prediction model of the electromechanical braking clamping force is modified based on the target influence factor to obtain the modified prediction model of the electromechanical braking clamping force. The clamping force is re-estimated using the electromechanical braking clamping force correction prediction model to obtain the target clamping force that meets the deviation range.

2. The method as described in claim 1, characterized in that, The electromechanical braking clamping force prediction model includes multiple influencing factors that affect the clamping force. Before outputting the predicted clamping force using the pre-created electromechanical braking clamping force initial prediction model, the method further includes: During the vehicle component development phase, the first data, including clamping force, electromechanical caliper motor current, motor rotation angle, friction pad thickness, wheel edge temperature, motor temperature, and cumulative braking count of the electromechanical caliper, are obtained based on the test platform. A first electromechanical braking clamping force prediction model is then constructed. An optimization learning algorithm is used to train the first electromechanical braking clamping force prediction model to obtain the trained first electromechanical braking clamping force prediction model. During actual vehicle use, a multi-dimensional data recording platform is used to obtain second data such as clamping force, electromechanical caliper motor current, motor rotation angle, friction pad thickness, wheel edge temperature, motor temperature, cumulative braking times of the electromechanical caliper, ambient humidity, and aging time of the electromechanical caliper. The second data is used to iteratively train the first electromechanical braking clamping force prediction model to obtain the initial prediction model of the electromechanical braking clamping force.

3. The method as described in claim 1, characterized in that, Identify the target influencing factors that affect the estimated clamping force, including: Determine the initial sample data where the deviation exceeds the standard, and perform data preprocessing on the initial sample data where the deviation exceeds the standard to obtain the corresponding target sample data where the deviation exceeds the standard; the initial sample data where the deviation exceeds the standard is the data corresponding to when the deviation between the estimated clamping force and the actual clamping force does not meet the deviation range. Based on the target sample data of each group of deviations exceeding the standard, the correlation coefficient between each influencing factor and the deviation is determined, and all influencing factors with correlation coefficients greater than a preset coefficient threshold are used as the deviation sample set. The deviation sample set is clustered using a clustering algorithm to obtain multiple deviation scenarios; The influencing factors in each deviation scenario are determined as the target influencing factors.

4. The method as described in claim 3, characterized in that, The clustering algorithm is used to cluster the deviation sample set to obtain multiple deviation scenarios, including: Randomly selected from the set of deviation samples K 1 sample is used as the initial cluster center; Determine each deviation sample to K The Euclidean distance between the initial cluster centers is used to classify each of the biased samples into the nearest cluster based on the Euclidean distance; The mean of each cluster is redefined as the new cluster center. The clustering is iterated repeatedly until the cluster centers no longer change or the upper limit of the number of iterations is reached, resulting in multiple clusters. Each cluster represents a deviation scenario.

5. The method as described in claim 1, characterized in that, The process of revising the initial prediction model of the electromechanical braking clamping force based on the target influence factor to obtain a revised prediction model of the electromechanical braking clamping force includes: Determine the target compensation coefficient corresponding to the target impact factor; The compensation coefficient of the target influence factor in the electromechanical braking clamping force correction prediction model is adjusted to the target compensation coefficient to obtain the electromechanical braking clamping force correction prediction model.

6. The method as described in claim 1, characterized in that, Determining the target compensation coefficient corresponding to the target impact factor includes: Obtain the current value of the target influence factor; Based on the current value, the corresponding target compensation coefficient is searched in the pre-created compensation coefficient database; the compensation coefficient database has a pre-fitted correspondence between the target influence factor and the target compensation coefficient.

7. A device for estimating electromechanical braking clamping force, characterized in that, The device includes: The first estimation unit is used to output the estimated clamping force using a pre-created electromechanical braking clamping force initial estimation model. The determining unit is used to determine the target influence factor that affects the estimated clamping force if the deviation between the estimated clamping force and the actual clamping force does not meet the deviation range. The correction unit corrects the initial prediction model of the electromechanical braking clamping force based on the target influence factor to obtain the corrected prediction model of the electromechanical braking clamping force. The second prediction unit is used to re-predict the clamping force using the electromechanical braking clamping force correction prediction model to obtain the target clamping force that meets the deviation range.

8. The apparatus as claimed in claim 7, characterized in that, The determining unit is specifically used for: The initial sample data of deviation exceeding the standard is determined, and the data of deviation exceeding the standard is preprocessed to obtain the corresponding target sample data of deviation exceeding the standard; the initial sample data of deviation exceeding the standard is the data in which the deviation between the estimated clamping force and the actual clamping force does not meet the deviation range. Based on the target sample data of each group of deviations exceeding the standard, the correlation coefficient between each influencing factor and the deviation is determined, and all influencing factors with correlation coefficients greater than a preset coefficient threshold are used as the deviation sample set. The deviation sample set is clustered using a clustering algorithm to obtain multiple deviation scenarios; The influencing factors in each deviation scenario are determined as the target influencing factors.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method according to any one of claims 1-7.

10. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method according to any one of claims 1-7.

Images