An EMB-based friction plate wear estimation method and related device

Abstract

The application provides a kind of EMB-based friction plate wear estimation method and its related equipment, it is related to vehicle chassis technical field, the technical scheme obtains the real-time working current, rotation number, rotating speed and contact temperature of motor in the process of vehicle braking, and then calculates the real-time absolute stroke and real-time braking force of actuator, uses the multi-parameter dynamic correction model containing temperature, braking force, rotating speed and wear uneven correction coefficient to dynamically correct the basic wear calculation result to obtain real-time wear amount, finally combines the preset initial thickness and wear trend model to calculate the current residual thickness and residual service life of friction plate, thereby realizing high-precision wear quantification estimation and life prediction relying on original sensor data of system, effectively improving the accuracy and intelligent level of electronic mechanical brake system friction plate monitoring.

Description

Technical Field

[0001] This invention relates to the field of vehicle chassis technology, and in particular to a method for predicting friction pad wear based on EMB and related equipment. Background Technology

[0002] Electromechanical braking systems (EMBs) are gradually replacing traditional hydraulic braking systems as the mainstream configuration due to their advantages of fast response and high control precision. However, the current friction pad wear monitoring methods of EMBs in passenger vehicles mainly rely on electronic or metal wear alarms, which not only increase hardware costs and wiring difficulty but are also prone to failure. Furthermore, they can only issue warnings when the wear reaches its limit, failing to achieve quantitative prediction and early warning. Some sensorless solutions rely on relative position detection, which is susceptible to temperature changes and component vibrations, resulting in large systematic errors and making it difficult to accurately assess the absolute wear state. Moreover, existing prediction models often fail to consider dynamic operating characteristics such as motor current, speed, and braking temperature, as well as uneven wear issues, resulting in a lack of dynamic adaptability, large prediction errors, and inability to adapt to different driving conditions. In addition, existing technologies lack wear trend prediction mechanisms, making it difficult to predict the remaining service life in advance, and they do not incorporate dedicated solutions designed based on the characteristics of EMBs, resulting in poor coordination and failing to meet the requirements of precision, intelligence, and low-cost mass production. Summary of the Invention

[0003] The purpose of this invention is to provide a friction pad wear prediction method and related equipment based on EMB, in order to solve one or more technical problems existing in the prior art, and at least provide a beneficial option or create conditions that can build a multi-parameter dynamic correction model based on the original sensors of the system, and combine it with the absolute reference of the fixed end block to realize the prediction of the wear state of the friction pad, thereby effectively improving the safety, reliability and intelligence level of the braking system while reducing hardware costs.

[0004] On the one hand, this application provides a friction pad wear prediction method based on EMB, applied to the control unit of an electromechanical braking system, the method comprising the following steps: During vehicle braking, the real-time operating current, real-time number of rotations, real-time speed, and contact temperature of the motor during braking are obtained. The real-time absolute stroke of the actuator is calculated based on the real-time rotation number and the preset transmission ratio, and the real-time braking force is calculated in combination with the real-time operating current. Based on the real-time braking force, real-time absolute stroke, contact temperature, real-time rotational speed, and preset working condition weighting coefficients, the real-time wear of the friction pads is calculated through a multi-parameter dynamic correction model. The multi-parameter dynamic correction model is configured to dynamically correct the basic wear calculation results using temperature correction coefficient, braking force correction coefficient, speed correction coefficient, and wear unevenness correction coefficient. The current remaining thickness of the friction pad is calculated based on the real-time wear amount and the preset initial thickness, and the remaining service life of the friction pad is calculated based on the current remaining thickness and the preset wear trend model.

[0005] Furthermore, the method also includes an initial calibration step: When the vehicle is stationary, the control motor drives the actuator to move to a position where it is in complete contact with the fixed end block, which is a rigid limiting structure set on the actuator housing; Obtain the initial number of rotations of the motor at this time, and calculate the initial absolute stroke of the actuator based on the preset transmission ratio; Using the initial absolute travel as the starting reference point for displacement calculation, a fixed absolute benchmark for wear prediction is established to eliminate relative position benchmark errors caused by temperature drift or mechanical vibration.

[0006] Furthermore, the calculation of the real-time wear of the friction pads based on the real-time braking force, real-time absolute stroke, contact temperature, real-time rotational speed, and preset operating condition weighting coefficients through a multi-parameter dynamic correction model includes: The temperature correction coefficient is calculated based on the difference between the contact temperature and the preset initial temperature; the braking force correction coefficient is calculated based on the ratio of the real-time braking force to the preset initial braking force; and the speed correction coefficient is calculated based on the difference between the real-time speed and the preset initial speed. Substituting the real-time braking force, real-time wear time, operating condition weighting coefficient, and each correction coefficient into the wear calculation formula, the real-time wear amount is calculated.

[0007] Furthermore, the calculation of the real-time wear of the friction pads using a multi-parameter dynamic correction model based on the real-time braking force, real-time absolute stroke, contact temperature, real-time rotational speed, and preset operating condition weighting coefficients also includes: Obtain the real-time travel of the actuators of each of the four wheels, and calculate the travel difference between the wheels; If the travel difference exceeds a preset unevenness threshold, a wear unevenness correction coefficient is calculated based on the travel difference, and the wear unevenness correction coefficient is added to the multi-parameter dynamic correction model to calculate the real-time wear amount.

[0008] Furthermore, the method also includes a model self-learning optimization step: When the electromechanical braking system re-executes the initial calibration step, it obtains a new initial absolute stroke, and the difference between the new initial absolute stroke and the previously stored initial absolute stroke is taken as the actual wear amount of the friction plate. By comparing the actual wear amount with the cumulative estimated wear amount calculated by the multi-parameter dynamic correction model, the estimation error is obtained. If the estimated error exceeds the preset error threshold, the basic friction and wear coefficient is adjusted, and the multi-parameter dynamic correction model is updated using the adjusted basic friction and wear coefficient. The basic friction and wear coefficient is a basic parameter for calculating the wear amount based on the pre-calibrated materials of the friction pad and brake disc, and serves as the benchmark calculation item in the wear calculation formula.

[0009] Further, the calculation of the remaining service life of the friction pad based on the current remaining thickness and a preset wear trend model includes: When the cumulative braking parameters reach the preset trigger condition, the calculation of the remaining thickness of the friction pad is initiated; Calculate the average cumulative wear per unit time based on historical braking data; The difference between the current remaining thickness and the preset limit wear thickness is divided by the average cumulative wear amount to obtain the preliminary remaining service life; The preliminary remaining service life is substituted into the exponential decay model for correction to obtain the final remaining service life, wherein the exponential decay model is used to reduce the prediction error based on the average braking force and average braking time.

[0010] Furthermore, the method also includes a step of dynamically adjusting the braking force: Get the current remaining thickness of the four wheel friction pads; Calculate the difference in remaining thickness between any two wheels; If the thickness difference exceeds a preset unevenness threshold, then at least one of the following adjustment strategies will be executed based on the relative positional relationship of the wheels: Strategy 1: When the thickness difference between the left and right wheels on the same axle exceeds the unevenness threshold, keep the total braking force of the axle unchanged, increase the braking force distribution ratio of the wheel on the side with thicker friction pads, and decrease the braking force distribution ratio of the wheel on the side with thinner friction pads. Strategy 2: When the thickness difference between wheels on the same side of different axles exceeds the unevenness threshold, increase the braking time of the wheel with thicker friction pads and decrease the braking time of the wheel with thinner friction pads. Strategy 3: When the thickness difference between wheels on different axles and sides exceeds the unevenness threshold, the braking force distribution ratio and braking duration of each wheel are comprehensively adjusted based on the thickness difference of each wheel.

[0011] Furthermore, after calculating the real-time wear of the friction pad using a multi-parameter dynamic correction model, the method further includes: The current remaining thickness is compared with the preset limit wear thickness; If the current remaining thickness is less than or equal to the preset limit wear thickness, a secondary warning signal is generated to prompt the user to replace the friction pad immediately. If the current remaining thickness is less than or equal to the product of the preset limit wear thickness and the safety factor, a first-level warning signal is generated to prompt the user to check the wear status of the friction pads in advance and plan for replacement.

[0012] On the other hand, this application provides an EMB-based friction pad wear prediction system, comprising: The data acquisition module is used to acquire the motor's real-time operating current, real-time rotational count, real-time speed, and contact temperature during the braking process. The stroke and force calculation module is used to calculate the real-time absolute stroke of the actuator based on the real-time rotation number and the preset transmission ratio, and to calculate the real-time braking force in combination with the real-time operating current. The wear calculation module is used to calculate the real-time wear of the friction plate based on the real-time braking force, real-time absolute stroke, contact temperature, real-time rotation speed and preset working condition weight coefficients through a multi-parameter dynamic correction model. The multi-parameter dynamic correction model is configured to dynamically correct the basic wear calculation results using temperature correction coefficient, braking force correction coefficient, speed correction coefficient, and wear unevenness correction coefficient. The lifespan prediction module is used to calculate the current remaining thickness of the friction pad based on the real-time wear amount and the preset initial thickness, and to calculate the remaining service life of the friction pad based on the current remaining thickness and the preset wear trend model.

[0013] On the other hand, this application provides a vehicle equipped with the aforementioned EMB-based friction pad wear prediction system.

[0014] The beneficial effects of this invention are as follows: This application provides a friction pad wear prediction method based on EMB. This technical solution acquires the real-time operating current, number of rotations, speed, and contact temperature of the motor during vehicle braking, and then calculates the real-time absolute stroke and real-time braking force of the actuator. A multi-parameter dynamic correction model, including temperature, braking force, speed, and wear unevenness correction coefficients, dynamically corrects the basic wear calculation results to obtain the real-time wear amount. Finally, combining a preset initial thickness and a wear trend model, the current remaining thickness and remaining service life of the friction pad are calculated. This achieves high-precision wear quantification and life prediction based on the system's original sensor data, effectively improving the accuracy and intelligence level of friction pad monitoring in electromechanical braking systems. This application also provides related equipment for the above method; the beneficial effects of the related equipment are similar to those of the above method and will not be elaborated here.

[0015] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the description, claims and drawings. Attached Figure Description

[0016] The accompanying drawings are provided to further understand the technical solutions of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the technical solutions of the present invention, and do not constitute a limitation on the technical solutions of the present invention.

[0017] Figure 1 This is a flowchart of the EMB-based friction pad wear prediction method provided in this application; Figure 2 This is a schematic diagram of the dynamic adjustment logic of braking force provided in this application; Figure 3 This is a structural diagram of the EMB-based friction pad wear prediction system provided in this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0019] The present application will be further described below with reference to the accompanying drawings and specific embodiments. The described embodiments should not be considered as limitations on the present application, and all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of the present application.

[0020] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0022] As automobiles evolve towards electrification and intelligence, traditional hydraulic braking systems, due to their inherent drawbacks such as complex structure and slow response, are gradually being replaced by electromechanical braking systems. Electromechanical braking systems achieve braking through direct motor drive, offering advantages such as fast response, high control precision, and ease of integration with energy recovery systems. Against this backdrop, because electromechanical braking systems eliminate hydraulic redundancy, accurate monitoring and lifespan prediction of brake pad wear have become key technologies for ensuring driving safety and achieving system intelligence.

[0023] Currently, existing technologies primarily employ mechanical or electronic wear sensors for monitoring. These solutions embed sensors in the friction pads; when the friction pads wear to their limit, the sensor breaks, triggering an alarm. However, this approach is a terminal alarm, increasing hardware costs and wiring complexity. Furthermore, it is prone to failure in high-temperature and high-vibration environments, failing to provide quantitative data on the wear process or early warnings. In addition, some sensorless solutions rely on detecting changes in the relative position of the actuator to estimate wear, but the results are susceptible to zero-point drift caused by temperature variations and mechanical vibrations, resulting in significant systematic errors and hindering accurate assessment.

[0024] Meanwhile, most existing wear prediction models are quite simplified, typically considering only factors such as the number of braking cycles or mileage, lacking consideration of the dynamic characteristics of the braking process. These models fail to dynamically correct for key factors such as motor operating current, real-time speed, brake contact temperature, and uneven wear of the friction pads, resulting in large prediction errors and poor dynamic adaptability under different driving habits and operating conditions. Moreover, existing technologies generally lack a trend prediction mechanism for the remaining service life of the friction pads, and cannot make intelligent judgments based on changes in the wear rate.

[0025] Furthermore, existing technical solutions fail to fully integrate the characteristics of electromechanical braking systems into their collaborative design, lacking self-learning and self-optimization capabilities. The actual wear of friction pads is affected by various factors such as material aging, batch variations, and the operating environment, making it difficult for models with fixed parameters to maintain high accuracy over long periods. Therefore, existing technologies cannot meet the mass production requirements of electromechanical braking systems for precise, intelligent, and low-cost friction pad wear monitoring.

[0026] To address the aforementioned issues, this application proposes an EMB-based method for predicting friction pad wear. By combining multi-parameter dynamic correction with absolute reference positioning, and fully utilizing real-time data such as motor operating current, rotational number, speed, and contact temperature from the electromechanical braking system itself, a dynamic model is constructed that includes temperature, braking force, speed, and wear unevenness correction coefficients. This achieves a high-precision quantitative assessment of the friction pad wear state. Furthermore, by combining the initial thickness and wear trend model, it effectively solves the problems of inaccurate predictions and low intelligence levels in existing technologies caused by the lack of an absolute reference, neglect of the influence of dynamic operating conditions, and inability to predict remaining life.

[0027] First, the EMB-based friction pad wear prediction method provided in this application will be described in detail below with reference to the accompanying drawings.

[0028] Reference Figure 1 The friction pad wear prediction method based on EMB provided in this application embodiment is applied to the control unit of an electromechanical braking system, and its implementation includes, but is not limited to, the following steps.

[0029] Step S110: During vehicle braking, acquire the real-time operating current, real-time rotation number, real-time speed, and contact temperature of the motor during braking.

[0030] In step S110, a data-driven foundation for wear prediction is established. This is achieved by collecting the real-time operating current of the motor to reflect the braking pressure, using the real-time rotational count to characterize the actuator's displacement, leveraging the real-time rotational speed to reflect the dynamic characteristics of the braking process, and monitoring the contact temperature to quantify the impact of thermal effects on the friction material. These four parameters together constitute the core dataset describing a complete physical profile of the braking event, providing multi-dimensional basis for establishing accurate mathematical models and ensuring that wear calculations fully reflect the complexity of actual working conditions.

[0031] Step S120: Calculate the real-time absolute stroke of the actuator based on the real-time rotation number and the preset transmission ratio, and calculate the real-time braking force in combination with the real-time operating current.

[0032] In step S120, a crucial conversion is achieved from the electrical signal on the motor side to the mechanical physical quantity on the brake side. Utilizing the mathematical relationship between the number of rotations and the transmission ratio, the angular displacement of the motor is accurately converted into the linear distance the push rod moves to move the friction plate, i.e., the real-time absolute stroke. This stroke is directly related to the contact state and wear of the friction pair. Simultaneously, by analyzing the proportional relationship between the real-time operating current and the motor output torque, combined with known mechanical transmission parameters, the magnitude of the real-time braking force acting on the brake disc can be deduced, thus providing the core mechanical index determining the wear rate for the wear model.

[0033] In step S130, based on real-time braking force, real-time absolute stroke, contact temperature, real-time rotational speed, and preset working condition weighting coefficients, the real-time wear of the friction pad is calculated through a multi-parameter dynamic correction model.

[0034] Among them, the multi-parameter dynamic correction model is configured to dynamically correct the basic wear calculation results using temperature correction coefficient, braking force correction coefficient, speed correction coefficient, and wear unevenness correction coefficient.

[0035] In step S130, the traditional single-variable estimation method is abandoned in favor of a comprehensive dynamic model. This model utilizes temperature correction coefficients, braking force correction coefficients, speed correction coefficients, and wear unevenness correction coefficients to provide refined compensation for the wear amount calculated based on fundamental theory. This dynamic correction mechanism can effectively adapt to the nonlinear effects of different driving habits, ambient temperatures, and road conditions, such as material softening caused by high temperatures or severe wear caused by sudden braking, thereby significantly improving the accuracy and robustness of wear amount calculation.

[0036] Step S140: Calculate the current remaining thickness of the friction pad based on the real-time wear amount and the preset initial thickness, and calculate the remaining service life of the friction pad based on the current remaining thickness and the preset wear trend model.

[0037] In step S140, the transformation from instantaneous physical quantities to long-term health status assessment is completed. By subtracting the accumulated real-time wear from the initial thickness of the friction pad at the factory, the system can accurately determine its current remaining thickness, providing the driver with intuitive feedback on the wear status. More importantly, the system introduces a wear trend model, which combines the current wear rate with historical data to predict the future wear trajectory. Taking into account the possible acceleration phenomenon in the later stages of wear, the system scientifically calculates the remaining service life of the friction pad, achieving a leap from passive alarm to proactive predictive maintenance.

[0038] In some embodiments of this application, the method further includes the following initial calibration steps.

[0039] In step S210, with the vehicle stationary, the control motor drives the actuator to move to a position where it is in complete contact with the fixed end block. The fixed end block is a rigid limiting structure set on the actuator housing.

[0040] In step S210, a physical absolute zero point is provided for the electromechanical braking system. Since the electromechanical braking system eliminates the physical limit of the traditional hydraulic braking, the motor is prone to accumulating errors during execution. By controlling the motor to drive the actuator to abut against this rigid fixed end block, it is equivalent to forcing the mechanical structure to return to a certain physical limit position at the beginning of each calibration, thereby providing a stable physical support point for subsequent position calculations and ensuring that the system always knows the absolute boundary of the mechanical structure.

[0041] Step S220: Obtain the initial number of rotations of the motor at this time, and calculate the initial absolute stroke of the actuator in combination with the preset transmission ratio.

[0042] In step S220, the physical contact position is converted into a digital signal that the system can recognize. When the actuator contacts the fixed end block, the motor stops rotating. The number of motor rotations recorded at this time represents the total stroke from zero to the physical limit. Using a preset transmission ratio, this angular displacement data is accurately converted into linear displacement data, i.e., the initial absolute stroke. This data not only reflects the actual position of the current mechanical structure, but also implies the thickness information of the current friction plate. As the friction plate wears and becomes thinner, the motor needs to rotate more times to reach the stop, thus making this initial absolute stroke a key reference data reflecting the wear state.

[0043] Step S230: Using the initial absolute travel as the starting reference point for displacement calculation, a fixed absolute reference for wear prediction is established to eliminate relative position reference errors caused by temperature drift or mechanical vibration.

[0044] In step S230, the technical problem of reference drift during long-term operation is solved. Traditional relative position detection is easily affected by the thermal expansion and contraction of metal caused by changes in ambient temperature and the mechanical vibration during vehicle operation, which causes the zero point recorded by the system to deviate from the actual zero point, resulting in systematic errors in wear calculation. This step establishes a fixed absolute reference and forces the starting point of each calculation to be locked at the physical stop position. No matter how the ambient temperature changes or how small the mechanical structure is deformed, the system uses this absolute reference as the origin to calculate the subsequent travel, thereby completely eliminating the cumulative error caused by relative position detection and ensuring high accuracy and long-term stability of wear prediction.

[0045] In some embodiments of this application, step S130 involves calculating the real-time wear of the friction pads using a multi-parameter dynamic correction model based on real-time braking force, real-time absolute stroke, contact temperature, real-time rotational speed, and a preset working condition weighting coefficient. This specifically includes the following steps.

[0046] Step S310: Calculate the temperature correction coefficient based on the difference between the contact temperature and the preset initial temperature, calculate the braking force correction coefficient based on the ratio of the real-time braking force to the preset initial braking force, and calculate the speed correction coefficient based on the difference between the real-time speed and the preset initial speed.

[0047] In step S310, a refined compensation mechanism for the wear model is established, which transforms the dynamic physical variables in the braking process into computable correction factors, thereby overcoming the limitations of traditional linear estimation.

[0048] Specifically, the impact of thermal effects is quantified by calculating the difference between the contact temperature and the preset initial temperature, because friction materials soften or carbonize at high temperatures, leading to changes in wear characteristics. This difference directly reflects the degree of interference of temperature on the material hardness.

[0049] Simultaneously, the ratio of real-time braking force to preset initial braking force is used to characterize the change in pressure load, because the magnitude of the braking force directly determines the normal pressure between the friction pairs, thus affecting the wear rate. Furthermore, the difference between real-time rotational speed and preset initial rotational speed is used to capture the dynamic slip characteristics during braking, as changes in rotational speed are related to the shear force and energy dissipation rate of the friction interface.

[0050] The introduction of these correction factors enables the system to distinguish wear differences under different operating conditions. For example, it can identify the different degrees of wear on the friction pads caused by high-temperature emergency braking and normal-temperature slow braking, providing the necessary compensation basis for subsequent accurate calculations.

[0051] Step S320: Substitute the real-time braking force, real-time wear time, working condition weighting coefficient, and each correction coefficient into the wear calculation formula to calculate the real-time wear amount.

[0052] In step S320, the quantitative integrated calculation of wear amount is realized. Through the coupling operation of mathematical formulas, the physical quantity is transformed into the final wear data. Real-time braking force is used as the basic wear driving force, and the wear effect is accumulated by combining real-time wear time. At the same time, a working condition weighting coefficient is introduced to balance the impact of different driving habits on wear, such as the weight difference between urban congestion conditions and highway conditions.

[0053] Most importantly, the temperature correction coefficient, braking force correction coefficient, and speed correction coefficient calculated in the previous step are substituted into the formula for dynamic weighting, so that the calculation result is no longer a fixed theoretical value, but a dynamic value that can be adjusted in real time according to the actual working conditions.

[0054] This calculation method fully considers the nonlinear characteristics of friction and wear. Through the collaborative operation of multiple parameters, it effectively eliminates the deviation caused by the estimation of a single parameter, ensuring that high-precision real-time wear data can be obtained under various complex braking scenarios, providing a reliable decision-making basis for the health management of vehicle braking systems.

[0055] In some embodiments of this application, step S130 further includes the following steps.

[0056] Step S410: Obtain the real-time travel of the actuators of each of the four wheels and calculate the travel difference between the wheels.

[0057] In step S410, a dynamic sensing and quantitative analysis mechanism for differences in brake mechanical installation is established to capture the differences in working status between the brake actuators of each wheel in real time. By acquiring the real-time stroke of the actuators of each of the four wheels, the system can accurately calculate the stroke difference between each wheel. This difference directly reflects the subtle deviations in the physical installation position, mechanical resistance, or response speed of the brake.

[0058] This process is equivalent to performing a real-time synchronization check on the entire braking system. It can keenly detect whether a wheel is lagging behind or ahead of other wheels due to improper installation or mechanical wear. This provides a crucial basis for subsequent precise corrections, ensuring that the system can distinguish between normal braking behavior and abnormal wear risks caused by installation differences.

[0059] Step S420: If the travel difference exceeds the preset unevenness threshold, calculate the wear unevenness correction coefficient based on the travel difference, and add the wear unevenness correction coefficient to the multi-parameter dynamic correction model to calculate the real-time wear amount.

[0060] In step S420, intelligent compensation for mechanical installation deviations and dynamic optimization of the wear model are implemented. Abnormal wear caused by stroke differences is eliminated by introducing a wear unevenness correction coefficient. When the system detects that the stroke difference between each wheel exceeds the preset unevenness threshold, it indicates that the installation state of the brake has deviated from the ideal synchronization range. At this time, the system will calculate a special wear unevenness correction coefficient based on the difference and add it to the multi-parameter dynamic correction model.

[0061] This correction factor acts like a balancer in the wear calculation formula, automatically adjusting the wear calculation weights for each wheel based on the actual degree of mechanical deviation. This counteracts the negative impact of physical installation differences at the mathematical model level. In this way, the system can maintain accurate predictions of friction pad wear throughout long-term vehicle use, effectively preventing excessive wear on one side of the wheel or decreased braking performance due to installation deviations, significantly improving the reliability and lifespan of the braking system.

[0062] In some embodiments of this application, the method further includes the following model self-learning optimization steps.

[0063] Step S510: When the electromechanical braking system re-executes the initial calibration step, a new initial absolute stroke is obtained, and the difference between the new initial absolute stroke and the previously stored initial absolute stroke is taken as the actual wear amount of the friction plate.

[0064] In step S510, a physical benchmark verification mechanism for the wear model is established, utilizing the physical characteristics of the braking system hardware to calibrate the actual wear data. When the electromechanical braking system re-executes the initial calibration step, the system can obtain a completely new initial absolute stroke and calculate the difference between it and the previously stored initial absolute stroke to determine the actual physical wear of the friction pads during actual use.

[0065] This process is equivalent to providing the system with a physical check-up opportunity during vehicle maintenance or under specific operating conditions. By directly measuring the mechanical displacement changes of the brake, the wear level of the friction pads can be inferred, effectively avoiding the drift error that may be caused by relying solely on the accumulation of sensor data. This provides the most reliable physical factual basis for subsequent model error analysis.

[0066] Step S520: Compare the actual wear amount with the cumulative estimated wear amount calculated by the multi-parameter dynamic correction model to obtain the estimation error.

[0067] In step S520, a quantitative assessment and deviation diagnosis of the model's calculation accuracy are achieved, revealing the gap between the algorithm's prediction and physical reality through data comparison. The system directly compares the actual wear amount obtained through physical measurement in the previous step with the cumulative estimated wear amount calculated by the multi-parameter dynamic correction model within the same time period. This cross-sectional data verification enables the accurate calculation of the prediction error between the two.

[0068] This comparison mechanism is not only a comprehensive check-up of the model's computational logic, but also a key means of identifying whether the model has systematic deviations under specific working conditions. It enables the system to clearly determine whether the current wear prediction is within a reasonable range or whether parameter correction is needed, providing a clear direction for the model's self-evolution.

[0069] Step S530: If the estimated error exceeds the preset error threshold, the basic friction and wear coefficient is adjusted, and the multi-parameter dynamic correction model is updated using the adjusted basic friction and wear coefficient; wherein, the basic friction and wear coefficient is a basic parameter for calculating the wear amount based on the pre-calibrated materials of the friction pad and brake disc, and is used as a benchmark calculation item in the wear calculation formula.

[0070] In step S530, the parameters of the wear model are optimized and dynamically evolved, and the model's computational accuracy and adaptability are continuously improved through a feedback mechanism. When the system detects that the estimated error exceeds the preset error threshold, it indicates that the current model parameters can no longer accurately reflect the actual wear situation. At this time, the system will adjust the basic friction and wear coefficients accordingly and update the multi-parameter dynamic correction model using the adjusted parameters.

[0071] Since the basic friction and wear coefficient is a pre-calibrated wear calculation parameter based on the materials of the friction pads and brake discs, and serves as the benchmark calculation term in the wear formula, adjusting it is equivalent to reshaping the model's calculation benchmark, enabling the model to self-calibrate according to the actual material wear characteristics. This parameter update mechanism based on error feedback endows the model with self-learning capabilities, allowing it to adapt to the performance differences of different batches of friction materials and the evolution of material properties during long-term use, thereby ensuring the long-term accuracy of wear prediction.

[0072] In some embodiments of this application, step S140 involves calculating the remaining service life of the friction pad based on the current remaining thickness and a preset wear trend model, including the following steps.

[0073] Step S610: When the cumulative braking parameters reach the preset trigger condition, start the calculation of the remaining thickness of the friction pad.

[0074] In step S610, the timing control logic for calculating the remaining service life is established. A reasonable triggering mechanism is set to balance system resource consumption and the timeliness of data updates. By monitoring whether the cumulative braking parameters reach the preset triggering conditions, the system can intelligently determine when to start the calculation process for the remaining thickness of the friction pad. This avoids excessive processor load due to overly frequent calculations and also prevents missing critical wear warning opportunities due to slow data updates.

[0075] This event- or parameter threshold-based triggering method allows the system to perform calculations only when braking behavior accumulates to a certain extent and has a significant impact on the friction pad thickness. This ensures the validity and representativeness of the calculation results and provides an accurate starting point for subsequent life prediction based on the latest thickness data.

[0076] Step S620: Calculate the average cumulative wear per unit time based on historical braking data.

[0077] In step S620, the wear rate of the friction pads is quantified, transforming historical braking data into a key indicator reflecting the rate of wear. By analyzing historical braking data to calculate the average cumulative wear per unit time, the system can objectively assess the actual wear rate of the vehicle under current usage habits and operating conditions. This indicator comprehensively reflects the impact of the driver's driving style, road conditions, and environmental factors on the friction pads.

[0078] This average cumulative wear serves as a bridge connecting the current state with future predictions, providing a dynamic rate benchmark for calculating remaining service life. This makes service life prediction no longer a static estimate based on fixed empirical values, but a dynamic assessment that can change with the actual use of the vehicle, significantly improving the realism of the prediction results.

[0079] Step S630: Divide the difference between the current remaining thickness and the preset limit wear thickness by the average cumulative wear amount to obtain the preliminary remaining service life.

[0080] In step S630, a basic estimation framework for the remaining service life is constructed, and a preliminary model for service life prediction is established through simple mathematical calculations. The difference between the current remaining thickness and the preset limit wear thickness, i.e., the maximum wear that the friction plate can still withstand, is divided by the average cumulative wear per unit time to directly obtain the time that the friction plate can continue to be used at the current wear rate, i.e., the preliminary remaining service life.

[0081] This calculation method is logically clear and computationally efficient, providing an intuitive and easy-to-understand quantitative result for remaining lifetime. As the basis for subsequent fine-tuning, it ensures the scientific nature and interpretability of lifetime prediction, enabling the system to quickly provide a rough lifetime range.

[0082] Step S640: Substitute the preliminary remaining service life into the exponential decay model for correction to obtain the final remaining service life. The exponential decay model is used to reduce the prediction error based on the average braking force and average braking time.

[0083] In step S640, the preliminary estimation results are refined by introducing a more complex mathematical model to eliminate the bias caused by linear estimation and improve prediction accuracy. Substituting the preliminary remaining service life into the exponential decay model for correction takes into account the impact of factors such as the decrease in heat capacity and heat dissipation performance as the friction pad thickness decreases, and the possible changes in braking force distribution on the wear rate. These factors usually lead to a non-linear accelerating trend in the wear rate.

[0084] The exponential decay model introduces parameters such as average braking force and average braking time to make nonlinear adjustments to the preliminary results, effectively reducing the prediction error caused by ignoring the wear acceleration effect. This makes the final remaining service life closer to the actual wear law of the friction pads, providing users with more reliable replacement warnings.

[0085] In some embodiments of this application, the method further includes the following dynamic adjustment step of braking force.

[0086] Step S710: Obtain the current remaining thickness of the four wheel friction pads.

[0087] Step S710 forms the foundational sensing element for dynamic adjustment of braking force, enabling real-time monitoring of the physical state of the friction pads on all four wheels. By accurately acquiring the current remaining thickness of each wheel's friction pad, the system establishes a global view of the wear status of key consumable materials in the braking system. This data not only serves as the basis for assessing the braking performance potential of individual wheels but also as a prerequisite for subsequent inter-wheel comparative analysis. This step ensures that the system can accurately identify which wheels have severely worn friction pads and which wheels are still in relatively new condition, thus providing the most fundamental decision-making basis for achieving intelligent braking force distribution based on physical state and avoiding blind braking due to missing information.

[0088] Step S720: Calculate the remaining thickness difference between any two wheels.

[0089] In step S720, mathematical calculations reveal the wear differences between wheels. By calculating the difference in remaining thickness between any two wheels, the system can accurately detect unbalanced wear phenomena that occur in the brakes during long-term use. This difference calculation not only reflects the wear differences between the left and right wheels on the same axle, but also reveals the wear gradient between the front and rear axles caused by different braking force distribution strategies or load distributions. By comparing the actual difference with a preset unevenness threshold, the system can determine whether the current wear state is within the allowable tolerance range, thereby deciding whether intervention and adjustment are necessary. This process is equivalent to setting up an early warning defense for the health status of the braking system.

[0090] In step S730, if the thickness difference exceeds the preset unevenness threshold, the braking force distribution ratio and braking duration of each wheel are adjusted according to the relative position relationship of the wheels.

[0091] In step S730, uneven wear and optimized braking performance are eliminated through dynamic adjustment. When the system detects that the thickness difference exceeds a preset unevenness threshold, it indicates that the wear state of the braking system is unbalanced. At this time, the system will make targeted adjustments to the braking force distribution ratio and braking duration of each wheel according to the relative position of the wheels. This adjustment strategy can guide more braking force to the wheels with larger remaining thickness, while reducing the burden on the severely worn wheels, thereby promoting a more uniform wear rate among the wheels while ensuring braking safety. In this way, the system can not only extend the service life of the entire braking system, but also maintain the braking stability and handling balance of the vehicle, effectively avoiding safety hazards caused by unilateral braking failure or uneven braking force attenuation.

[0092] In some embodiments of this application, in step S730, at least one of the following adjustment strategies is executed.

[0093] Strategy 1: When the thickness difference between the left and right wheels on the same axle exceeds the unevenness threshold, keep the total braking force of the axle unchanged, increase the braking force distribution ratio of the wheel on the side with thicker friction pads, and decrease the braking force distribution ratio of the wheel on the side with thinner friction pads.

[0094] Specifically, Strategy 1 achieves wear balance on both sides of the wheels on a single axle by lateral transfer of braking force. It makes full use of the physical symmetry and relatively uniform load distribution of coaxial wheels. By intelligently adjusting the braking torque on both sides, the less worn wheel undertakes more braking tasks. This ensures the lateral braking stability of the vehicle while effectively suppressing further excessive wear on the more worn wheel, gradually reducing the wear difference between the two wheels and maintaining axial braking balance.

[0095] Strategy 2: When the thickness difference between wheels on the same side of different axles exceeds the unevenness threshold, increase the braking time of the wheel with thicker friction pads and decrease the braking time of the wheel with thinner friction pads.

[0096] Specifically, Strategy Two balances longitudinal wear distribution by adjusting the timing of braking engagement. It focuses on using time differences to allocate braking tasks, allowing less worn wheels to engage earlier or disengage later during braking, thus absorbing more braking energy. Since wheels on the same side of opposite axles experience inherent differences in load and operating conditions during vehicle operation, simply adjusting the braking force may affect the vehicle's longitudinal stability and handling characteristics. However, adjusting the braking duration can effectively balance the long-term wear trends of wheels on the same side of the front and rear axles without significantly altering the instantaneous braking force distribution.

[0097] Strategy 3: When the thickness difference between wheels on different axles and sides exceeds the unevenness threshold, the braking force distribution ratio and braking duration of each wheel are comprehensively adjusted based on the thickness difference of each wheel.

[0098] Specifically, Strategy 3 addresses the asymmetric wear of wheels on opposite axles and sides through the coupled adjustment of multi-dimensional parameters. It simultaneously optimizes the vehicle's lateral and longitudinal braking performance. By precisely calculating the wear state of each wheel, it intelligently allocates braking tasks to each wheel, ensuring optimal braking force not only in magnitude but also in timing. This comprehensive adjustment effectively addresses complex wear patterns caused by driving habits, road inclination, or uneven load distribution, ensuring the elimination of uneven wear while maintaining the stability and safety of the entire vehicle's braking system, achieving global optimization of braking performance and friction pad life.

[0099] In some embodiments of this application, reference is made to Figure 2The core of the dynamic braking force adjustment logic lies in achieving wear balance by monitoring the remaining thickness (H1-H4) of the four wheel friction pads. The system first determines whether the thickness difference between any two wheels exceeds a threshold of 0.1mm. If it does not, the current state is maintained; if it does, a differentiated adjustment strategy is adopted based on the wheel position (coaxial, opposite axles on the same side, opposite axles on opposite sides). For coaxial wheels, the braking force is increased by 10% on the thickened side and decreased by 10% on the thinned side, with a 5% increase in braking duration. For opposite axles on the same side, the same applies: the braking force is increased by 10% on the thickened side and decreased by 10% on the thinned side, with a 5% increase in braking duration. For opposite axles on opposite sides, the braking force is increased by 10% on the thickened side and decreased by 10% on the thinned side, with a 5% increase in braking duration. After all adjustments are completed, the system returns to re-detect the thickness difference, forming a continuously optimizing closed loop until the wear of each wheel reaches a balanced state.

[0100] In some embodiments of this application, after calculating the real-time wear of the friction pad using a multi-parameter dynamic correction model, the method further includes the following early warning step.

[0101] Step S810: Compare the current remaining thickness with the preset limit wear thickness.

[0102] In step S810, the physical state of the friction pad is assessed in real time to determine whether it is within a safe boundary through numerical comparison. The system precisely compares the current remaining thickness calculated by a multi-parameter dynamic correction model with the pre-set physical safety baseline of the ultimate wear thickness. This process is equivalent to performing a critical "life-or-death check" on the friction pad's condition. Through this direct numerical comparison, the system can quickly identify whether the friction pad has worn to a dangerous level that necessitates immediate discontinuation, providing the most fundamental basis for subsequent graded early warning decisions and ensuring the timeliness and accuracy of the early warning mechanism.

[0103] In step S820, if the current remaining thickness is less than or equal to the preset limit wear thickness, a secondary warning signal is generated to prompt the user to replace the friction pad immediately.

[0104] In step S820, the user is forced to pay close attention when the wear of the friction pads reaches a dangerous limit. When the system detects that the current remaining thickness is less than or equal to the preset limit wear thickness, it indicates that the wear of the friction pads has reached the physical safety red line. Continued use will directly threaten the vehicle's braking performance or even lead to brake failure. At this time, the system will immediately generate a level two warning signal.

[0105] This warning signal, as the highest level of alert, aims to force users to immediately stop using the vehicle and replace the friction pads as soon as possible, in order to avoid serious safety accidents caused by locking up, scratching the brake disc, or completely losing braking force. It is the last electronic line of defense to ensure the safe operation of the vehicle.

[0106] In step S830, if the current remaining thickness is less than or equal to the product of the preset limit wear thickness and the safety factor, a first-level warning signal is generated to prompt the user to check the wear status of the friction pads in advance and plan for replacement.

[0107] In step S830, ample buffer time and planning space are provided to the user to cope with the upcoming component replacement needs. When the system determines that the current remaining thickness is less than or equal to the product of the preset limit wear thickness and the safety factor, it means that although the friction plate has not yet reached the scrap standard, it has entered a critical area that requires close attention. At this time, the system will generate a first-level warning signal.

[0108] This warning signal serves as a primary alert, aiming to prompt users to check the wear condition of the friction pads in advance and begin planning for replacement. This allows users to proactively schedule maintenance according to their own timetable, avoiding passive breakdowns or emergency repairs caused by sudden excessive wear, thereby improving the convenience of vehicle use and the initiative in maintenance.

[0109] In some embodiments of this application, a method for predicting friction pad wear, encompassing the entire process from initial calibration, dynamic data acquisition, parameter correction, wear prediction, trend forecasting, to self-learning optimization, is demonstrated. This method relies on existing sensor data from the EMB system, requiring no additional hardware, and incorporates a dynamic braking force adjustment mechanism to achieve accurate prediction and intelligent early warning. The specific implementation steps are as follows: 1. Initial System Calibration After the EMB system in the passenger vehicle is assembled, the system first performs an initial calibration procedure to establish a precise baseline. The control unit drives the motor to move the actuator element to a position where it is in full contact with the rigid end stop fixed on the housing, thus serving as an absolutely fixed baseline unaffected by temperature and vibration. Subsequently, the motor drives the actuator to move towards the brake disc until the friction pad just contacts the brake disc. At this point, the number of motor rotations is collected by the rotation angle sensor, and the initial absolute stroke of the actuator is calculated by combining it with the transmission ratio. And record the initial current. and ambient temperature .

[0110] At the same time, the system presets the initial thickness of the friction pad. (e.g., 10mm), limit wear thickness (e.g., 3mm), friction plate density and initial friction coefficient Parameters such as friction and wear coefficients were determined based on bench tests. And initial correction factors for temperature, braking force, and speed ( , , ), and set weighting coefficients for different operating conditions (such as emergency, ramp, normal braking). Complete the system initialization settings.

[0111] 2. Real-time data acquisition During vehicle operation, the EMB system control unit utilizes existing sensor hardware to collect multi-dimensional data in real time, eliminating the need for additional hardware. The system collects real-time operating current via a motor current sensor. To reflect the magnitude of braking force, and to collect the real-time number of rotations via an angle sensor. and speed To calculate the real-time absolute travel of the actuator Simultaneously, an integrated temperature sensor is used to collect the real-time contact temperature during the braking process. The vehicle speed is obtained through the vehicle control unit (VCU). and brake pedal travel .

[0112] In addition, the system also records the duration of each braking action. Braking frequency It automatically identifies the current operating condition (normal, emergency, or ramp braking) by combining data from the VCU and slope sensors, and matches the corresponding weighting coefficient. At the same time, the above parameters of the four wheels are recorded separately to provide data support for subsequent judgment of uneven wear and adjustment of braking force.

[0113] 3. Correction coefficients are dynamically updated. Based on the collected real-time data, the system dynamically updates various correction coefficients to eliminate the influence of environmental and operating conditions on the prediction accuracy. The system also adjusts the system based on real-time braking temperature. With initial temperature The difference is calculated using the temperature correction factor. ,when hour Take 1.0; Braking force calculated based on real-time current. With initial braking force The ratio is used to calculate the braking force correction coefficient. According to real-time rotation speed With initial rotational speed The difference is used to calculate the speed correction coefficient. ,when hour Take 1.0.

[0114] In addition, the system also calculates a wear unevenness correction coefficient based on the difference in real-time stroke of the four wheel actuators. When the difference in travel between a certain wheel and other wheels Correction is initiated when the error exceeds 0.1mm. This compensates for errors caused by differences in mechanical installation or excessive wear on one side, ensuring the system's adaptability under different dynamic operating conditions.

[0115] 4. Estimation of friction plate wear The system calculates the real-time and cumulative wear of the friction pads based on initial data, real-time acquired data, and dynamic correction coefficients. During each braking process, the real-time wear is calculated using the following friction and wear mechanism formula. : , The contact area is used; the cumulative wear amount is obtained by integrating the results. At the same time, combined with the absolute stroke difference of the actuator Perform calibration (calibration deviation) The system is based on Calculate the current remaining thickness .

[0116] In addition, the system has an automatic component replacement identification function: when the absolute stroke of the actuator is detected... Sudden decrease (difference exceeds) 50% of the real-time current Restore to initial current When the brake disc or friction pads are nearby, the system automatically determines that they have been replaced and then resets the accumulated wear level. It can then be recalibrated, thereby achieving intelligent management without human intervention.

[0117] 5. Wear Trend Prediction and Remaining Life Estimation Based on cumulative wear and braking frequency The system constructs a trend model to predict remaining service life. This is achieved by statistically analyzing the average cumulative wear per unit time. , For usage time; combined with the current remaining thickness Calculate the preliminary remaining life And adopt an exponential decay model The results were corrected, among which For average braking force, The average braking time per cycle is used to reduce errors under continuous braking conditions.

[0118] The system updates the wear trend curve in real time and dynamically adjusts the prediction results based on increased braking frequency, rising temperature, or frequent occurrences of peak braking force. Finally, it transmits the remaining service life (displayed in days or mileage) and current thickness to the instrument panel, and then... Is it less than or Trigger a Level 1 (remind to check) or Level 2 (force replacement) warning.

[0119] 6. Dynamic adjustment of braking force To reduce uneven wear and extend service life, the system dynamically adjusts the braking force distribution based on the difference in the remaining thickness of the friction pads on the four wheels. If the thickness difference between any two wheels exceeds a threshold (e.g., 0.1mm), the system will initiate adjustment logic: For wheels on the same axle (e.g., left and right front wheels), during straight-line or small-angle steering braking, the braking force distribution ratio (e.g., +10%) and duration of the wheel with the thicker friction pad are increased, while the ratio of the wheel with the thinner friction pad is decreased (e.g., -10%). For wheels on different axles but on the same side, the braking force distribution ratio and duration of the axle corresponding to the thicker wheel are increased, while the ratio and duration of the axle corresponding to the thinner wheel are decreased. For wheels on different axles and on different sides, the same applies: the braking force distribution ratio and duration of the axle corresponding to the thicker wheel are increased, while the ratio and duration of the axle corresponding to the thinner wheel are decreased. Through this strategy, the system promotes more even wear on each wheel by dynamically transferring braking force while ensuring braking safety.

[0120] 7. Model self-learning optimization To ensure long-term accuracy and stability, the model possesses a self-learning optimization function. Every preset operating cycle (e.g., 30 days) or when the total number of braking cycles reaches a preset value (e.g., 1000), the model automatically performs self-learning optimization. The system compares the actual wear of the friction pads (detected through disassembly or calculated using travel difference) with the model's estimated wear, calculates the prediction error, and adjusts the friction wear coefficient $K$ and the calibration values ​​of various correction coefficients when the error exceeds 5%. Simultaneously, it optimizes the condition weighting coefficients by incorporating wear data from different driving conditions (urban, highway, mountainous). The optimized parameters will be stored and updated in the model database, enabling adaptive iteration of the model. This allows the prediction model to evolve adaptively with changes in the vehicle's operating environment and the properties of friction materials, maintaining high-precision prediction capabilities at all times.

[0121] In some embodiments of this application, taking the EMB system of a new energy passenger vehicle as a specific application scenario, the friction pads are set to be made of ceramic material with an initial thickness of... Limit wear thickness Current-braking force conversion factor coefficient of friction and wear Friction plate density Initial value of friction coefficient Contact area Initial braking speed initial current initial temperature The estimated trigger threshold for braking is set at $100 times. The specific implementation process is as follows: 1. Initial System Calibration After the EMB system is assembled, the control motor drives the actuator element to move to the initial calibration position where it contacts the fixed end stop. Then, the drive motor moves the actuator element towards the brake disc until the friction pads just contact the brake disc. The number of motor rotations at this point is collected by the motor rotation angle sensor. The given EMB system transmission ratio is... The initial absolute stroke of the actuator is calculated. (Right now Simultaneously record the initial current of the motor. and initial braking temperature The system defaults to an initial value of 1.0 for all correction coefficients (i.e., ...). , , , All values ​​are 1.0), and the operating condition weighting coefficient is preset. For example, emergency braking The value is 1.2, corresponding to ramp braking. The value is 1.1, corresponding to normal braking. If the value is 1.0, the above parameters are stored in the EMB control unit to complete the initial calibration process.

[0122] 2. Real-time data acquisition and wear prediction When driving a passenger vehicle on urban roads (under normal braking conditions), During the process of (1.0), the EMB system collects data in real time: real-time motor current. motor speed Braking temperature Braking duration speed Number of motor rotations Circle. Calculate the real-time absolute travel of the actuator. (Right now ).

[0123] Then, the correction coefficients are dynamically updated: Temperature correction factor ; Braking force correction coefficient ; Speed ​​correction factor ; Because the difference in travel between each wheel is (Not exceeding the threshold), therefore the wear unevenness correction coefficient is... ; Substitute the above data into the formula to calculate the real-time wear amount: .

[0124] When the cumulative number of braking cycles reaches a preset threshold of 100, wear estimation is initiated, and the cumulative wear amount is calculated. Combined with travel difference calibration ( The calibration deviation is Corrected cumulative wear Current remaining thickness Greater than the first-level warning threshold Therefore, no warning was triggered.

[0125] Then, the remaining service life is estimated, and the average cumulative wear per unit time is calculated. .

[0126] Calculate the preliminary remaining life After correction by the exponential decay model The real-time data transmitted to the vehicle's instrument panel displays "452 days remaining / approximately..." .

[0127] 3. Dynamic adjustment of braking force During system monitoring, if the remaining thickness of the left front wheel friction pad is detected to be... The right front wheel is The calculated thickness difference is Exceeding the preset threshold And it is determined to be a wheel on the same axle. At this time, when the vehicle brakes straight, the system automatically activates the dynamic adjustment logic, appropriately increases the braking force distribution ratio of the right front wheel (the side with thinner friction pads) by 10% and shortens the braking time by 5%. By reducing the amount of wear on the thinner side wheel in a single operation, the thickness difference between the left and right wheels is gradually reduced, and wear balance control is achieved.

[0128] 4. Model self-learning optimization and component replacement recognition After the model runs for 30 days, a self-learning optimization process is implemented. The actual cumulative wear of the friction pads is obtained through disassembly and testing. Compare the wear amount predicted by the model. The calculation error was 4.4%, which did not exceed the set threshold of 5%, therefore no adjustment of the friction and wear coefficient was required. If the error exceeds 5%, then... The value was adjusted to 0.000105 for compensation.

[0129] Regarding component identification, when the user replaces the friction pads with new ones, the EMB system detects the absolute stroke of the actuator. from sudden drop And the motor current recovered to The system automatically identifies the left and right positions as friction pad replacement operations and then resets the accumulated wear level. Then re-execute the initial calibration procedure.

[0130] Furthermore, taking into account the characteristics of urban road braking data (high braking frequency and moderate braking intensity), the model further optimizes the weighting coefficients for different operating conditions. The city's congestion conditions The value was adjusted to 1.05, thereby improving the accuracy of wear prediction under this specific working condition.

[0131] In some embodiments of this application, the temperature correction factor Alternatively, a calculation method with lower linearity can be used, specifically, it can be replaced with... Meanwhile, the speed correction coefficient It can be replaced with a more sensitive calculation method. By adjusting the coefficient parameters to dynamically correct the influence of temperature and rotational speed on the wear of the friction plates, the invention's objective of accurately predicting wear can be achieved.

[0132] In some embodiments of this application, the braking frequency trigger threshold can be adaptively adjusted according to the vehicle's usage frequency, specifically replacing it with a range of 50 to 200 times; simultaneously, the cumulative braking duration trigger threshold can be calibrated and adjusted according to the braking habits of different vehicle models. As long as a reasonable trigger threshold is set to avoid wasting system computing power and to achieve accurate prediction of wear, it can be used as an effective alternative to this application.

[0133] In some embodiments of this application, the trend prediction model for remaining service life can also employ linear regression analysis. Specifically, the original exponential decay model can be replaced with a linear regression model based on historical wear data. As long as accurate prediction of remaining service life is achieved by fitting the wear trend, the inventive objective of this application can be achieved regardless of the mathematical model used.

[0134] In some embodiments of this application, the dynamic adjustment logic of braking force distribution can also adopt a graded correction strategy. Specifically, different adjustment ranges can be set according to the size of the wear difference between the wheels. For example, when the wear difference is between 0.1 and 0.2 mm, the braking force distribution ratio can be adjusted by 10%, and when the wear difference is greater than 0.2 mm, it can be adjusted by 15%. As long as the uneven wear of the coaxial wheels is effectively corrected through graded control, the invention objective of balanced wear can be achieved.

[0135] In some embodiments of this application, the optimization period for model self-learning can be flexibly adjusted according to the vehicle driving environment, specifically within a range of 15 to 60 days; simultaneously, the preset value for the number of braking cycles to trigger self-learning can be replaced with 500 to 2000 cycles. As long as the prediction accuracy is ensured through periodic optimization of model parameters, dynamic calibration and optimization of the friction and wear coefficient can be achieved regardless of the specific period length.

[0136] Secondly, refer to Figure 3This application provides an EMB-based friction pad wear prediction system, comprising: The data acquisition module is used to acquire the motor's real-time operating current, real-time rotational count, real-time speed, and contact temperature during the braking process.

[0137] The stroke and force calculation module is used to calculate the real-time absolute stroke of the actuator based on the real-time rotation number and the preset transmission ratio, and to calculate the real-time braking force in combination with the real-time operating current.

[0138] The wear calculation module is used to calculate the real-time wear of the friction pads based on real-time braking force, real-time absolute stroke, contact temperature, real-time rotational speed, and preset working condition weighting coefficients through a multi-parameter dynamic correction model.

[0139] Among them, the multi-parameter dynamic correction model is configured to dynamically correct the basic wear calculation results using temperature correction coefficient, braking force correction coefficient, speed correction coefficient, and wear unevenness correction coefficient.

[0140] The lifespan prediction module is used to calculate the current remaining thickness of the friction pad based on the real-time wear amount and the preset initial thickness, and to calculate the remaining service life of the friction pad based on the current remaining thickness and the preset wear trend model.

[0141] Furthermore, embodiments of this application provide a vehicle equipped with the aforementioned EMB-based friction pad wear prediction system.

[0142] In summary, the EMB-based friction pad wear prediction method, system, and vehicle provided in this application have the following technical effects.

[0143] First, by combining real-time braking parameters with a multi-parameter dynamic correction model, high-precision online prediction of friction pad wear is achieved, overcoming the limitations of traditional empirical estimation and direct measurement by physical sensors, and significantly improving the accuracy and reliability of wear condition monitoring. Second, a model self-learning optimization mechanism is introduced, using the actual travel difference during the calibration phase to correct the basic friction and wear coefficient. This allows the model to dynamically adapt to the actual working characteristics of friction pads made of different materials, effectively reducing accumulated errors during long-term operation and enhancing the system's adaptability and stability throughout its lifespan.

[0144] Furthermore, based on a combination of remaining thickness and wear trend models, the remaining service life is predicted in stages and levels. An exponential decay model is used to nonlinearly correct the preliminary results, making the life prediction closer to the actual wear evolution and improving the engineering applicability of the prediction. In addition, by implementing a dynamic braking force distribution strategy, the braking force ratio and braking duration of each wheel are actively adjusted according to the thickness differences of the friction pads between different wheels. This not only effectively balances the wear distribution of the entire vehicle's braking system and extends the overall maintenance cycle, but also avoids the risk of brake eccentricity, vibration, or failure caused by excessive wear on one side, improving driving safety and braking smoothness.

[0145] Finally, a tiered early warning mechanism is set up to trigger a first-level cautionary warning and a second-level emergency warning at different wear stages, providing users with a reasonable inspection planning window and emergency response guidance. This achieves closed-loop management from condition monitoring and life prediction to fault warning and control optimization, significantly improving the intelligence level, safety redundancy capability, and user experience of the electromechanical braking system.

[0146] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards of the relevant countries and regions. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirects to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data for the proper functioning of the embodiments of this application obtained.

[0147] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this application are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0148] Furthermore, although this application is described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding this application. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of ordinary skill of an engineer. Therefore, those skilled in the art can implement the application set forth in the claims using ordinary skill. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of this application, which is determined by the full scope of the appended claims and their equivalents.

[0149] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several programs to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0150] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequential list of executable programs for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, a program execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can retrieve and execute a program from or in conjunction with such a program execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit a program for use by or in conjunction with a program execution system, apparatus, or device.

[0151] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or, if necessary, processing in a suitable manner, and then stored in computer memory.

[0152] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable program execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0153] In the foregoing description of this specification, the reference to terms such as "one embodiment / implementation," "another embodiment / implementation," or "certain embodiments / implementations," etc., indicates that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in an embodiment or example of the present invention. 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.

[0154] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0155] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A method for predicting friction pad wear based on EMB, characterized in that, A control unit applied to an electromechanical braking system, the method comprising the following steps: During vehicle braking, the real-time operating current, real-time number of rotations, real-time speed, and contact temperature of the motor during braking are obtained. The real-time absolute stroke of the actuator is calculated based on the real-time rotation number and the preset transmission ratio, and the real-time braking force is calculated in combination with the real-time operating current. Based on the real-time braking force, real-time absolute stroke, contact temperature, real-time rotational speed, and preset working condition weighting coefficients, the real-time wear of the friction pads is calculated through a multi-parameter dynamic correction model. The multi-parameter dynamic correction model is configured to dynamically correct the basic wear calculation results using temperature correction coefficient, braking force correction coefficient, speed correction coefficient, and wear unevenness correction coefficient. The current remaining thickness of the friction pad is calculated based on the real-time wear amount and the preset initial thickness, and the remaining service life of the friction pad is calculated based on the current remaining thickness and the preset wear trend model.

2. The method for predicting friction pad wear based on EMB according to claim 1, characterized in that, The method also includes an initial calibration step: When the vehicle is stationary, the control motor drives the actuator to move to a position where it is in complete contact with the fixed end block, which is a rigid limiting structure set on the actuator housing; Obtain the initial number of rotations of the motor at this time, and calculate the initial absolute stroke of the actuator based on the preset transmission ratio; Using the initial absolute travel as the starting reference point for displacement calculation, a fixed absolute benchmark for wear prediction is established to eliminate relative position benchmark errors caused by temperature drift or mechanical vibration.

3. The method for predicting friction pad wear based on EMB according to claim 1, characterized in that, The real-time wear of the friction pads is calculated using a multi-parameter dynamic correction model based on the real-time braking force, real-time absolute stroke, contact temperature, real-time rotational speed, and preset operating condition weighting coefficients. This includes: The temperature correction coefficient is calculated based on the difference between the contact temperature and the preset initial temperature; the braking force correction coefficient is calculated based on the ratio of the real-time braking force to the preset initial braking force; and the speed correction coefficient is calculated based on the difference between the real-time speed and the preset initial speed. Substituting the real-time braking force, real-time wear time, operating condition weighting coefficient, and each correction coefficient into the wear calculation formula, the real-time wear amount is calculated.

4. The method for predicting friction pad wear based on EMB according to claim 3, characterized in that, The method of calculating the real-time wear of the friction pads using a multi-parameter dynamic correction model based on the real-time braking force, real-time absolute stroke, contact temperature, real-time rotational speed, and preset operating condition weighting coefficients also includes: Obtain the real-time travel of the actuators of each of the four wheels, and calculate the travel difference between the wheels; If the travel difference exceeds a preset unevenness threshold, a wear unevenness correction coefficient is calculated based on the travel difference, and the wear unevenness correction coefficient is added to the multi-parameter dynamic correction model to calculate the real-time wear amount.

5. The method for predicting friction pad wear based on EMB according to claim 1, characterized in that, The method also includes a model self-learning optimization step: When the electromechanical braking system re-executes the initial calibration step, it obtains a new initial absolute stroke, and the difference between the new initial absolute stroke and the previously stored initial absolute stroke is taken as the actual wear amount of the friction plate. By comparing the actual wear amount with the cumulative estimated wear amount calculated by the multi-parameter dynamic correction model, the estimation error is obtained. If the estimated error exceeds the preset error threshold, the basic friction and wear coefficient is adjusted, and the multi-parameter dynamic correction model is updated using the adjusted basic friction and wear coefficient. The basic friction and wear coefficient is a basic parameter for calculating the wear amount based on the pre-calibrated materials of the friction pad and brake disc, and serves as the benchmark calculation item in the wear calculation formula.

6. The method for predicting friction pad wear based on EMB according to claim 1, characterized in that, The calculation of the remaining service life of the friction pad based on the current remaining thickness and a preset wear trend model includes: When the cumulative braking parameters reach the preset trigger condition, the calculation of the remaining thickness of the friction pad is initiated; Calculate the average cumulative wear per unit time based on historical braking data; The difference between the current remaining thickness and the preset limit wear thickness is divided by the average cumulative wear amount to obtain the preliminary remaining service life; The preliminary remaining service life is substituted into the exponential decay model for correction to obtain the final remaining service life, wherein the exponential decay model is used to reduce the prediction error based on the average braking force and average braking time.

7. The method for predicting friction pad wear based on EMB according to claim 1, characterized in that, The method also includes a dynamic adjustment step for braking force: Get the current remaining thickness of the four wheel friction pads; Calculate the difference in remaining thickness between any two wheels; If the thickness difference exceeds a preset unevenness threshold, then at least one of the following adjustment strategies will be executed based on the relative positional relationship of the wheels: Strategy 1: When the thickness difference between the left and right wheels on the same axle exceeds the unevenness threshold, keep the total braking force of the axle unchanged, increase the braking force distribution ratio of the wheel on the side with thicker friction pads, and decrease the braking force distribution ratio of the wheel on the side with thinner friction pads. Strategy 2: When the thickness difference between wheels on the same side of different axles exceeds the unevenness threshold, increase the braking time of the wheel with thicker friction pads and decrease the braking time of the wheel with thinner friction pads. Strategy 3: When the thickness difference between wheels on different axles and sides exceeds the unevenness threshold, the braking force distribution ratio and braking duration of each wheel are comprehensively adjusted based on the thickness difference of each wheel.

8. The method for predicting friction pad wear based on EMB according to claim 1, characterized in that, After calculating the real-time wear of the friction pad using a multi-parameter dynamic correction model, the method further includes: The current remaining thickness is compared with the preset limit wear thickness; If the current remaining thickness is less than or equal to the preset limit wear thickness, a secondary warning signal is generated to prompt the user to replace the friction pad immediately. If the current remaining thickness is less than or equal to the product of the preset limit wear thickness and the safety factor, a first-level warning signal is generated to prompt the user to check the wear status of the friction pads in advance and plan for replacement.

9. A friction pad wear prediction system based on EMB, characterized in that, include: The data acquisition module is used to acquire the motor's real-time operating current, real-time rotational count, real-time speed, and contact temperature during the braking process. The stroke and force calculation module is used to calculate the real-time absolute stroke of the actuator based on the real-time rotation number and the preset transmission ratio, and to calculate the real-time braking force in combination with the real-time operating current. The wear calculation module is used to calculate the real-time wear of the friction plate based on the real-time braking force, real-time absolute stroke, contact temperature, real-time rotation speed and preset working condition weight coefficients through a multi-parameter dynamic correction model. The multi-parameter dynamic correction model is configured to dynamically correct the basic wear calculation results using temperature correction coefficient, braking force correction coefficient, speed correction coefficient, and wear unevenness correction coefficient. The lifespan prediction module is used to calculate the current remaining thickness of the friction pad based on the real-time wear amount and the preset initial thickness, and to calculate the remaining service life of the friction pad based on the current remaining thickness and the preset wear trend model.

10. A vehicle, characterized in that, It is equipped with the EMB-based friction pad wear prediction system as described in claim 9.

Images