An EBD fault adaptive fault-tolerant control method and system

Abstract

The present disclosure provides an EBD fault adaptive fault-tolerant control method and system, which comprises: collecting vehicle braking related parameters; judging the EBD fault type through cross verification, model prediction residual analysis and CAN communication threshold comparison of the braking related parameters respectively; calculating the fault error corresponding to the EBD fault type, judging the EBD fault level based on the fault error corresponding to the EBD fault type and the preset grade interval threshold; executing the corresponding fault disposal measures according to the EBD fault level, and determining the wheel braking force distribution coefficient; adjusting the braking pump pressure of each wheel, and executing the braking force distribution coefficient. The scheme of the present disclosure can improve the braking efficiency under different EBD faults, and guarantee the braking stability and safety.

Description

Technical Field

[0001] This invention belongs to the field of automotive braking technology, and in particular relates to an EBD fault adaptive fault-tolerant control method and system. Background Technology

[0002] Electronic Brake-force Distribution (EBD) is a core technology for active vehicle safety. It works in conjunction with Anti-lock Braking System (ABS). By collecting dynamic vehicle operating data from multiple sources such as wheel speed sensors, vehicle load sensors, and longitudinal acceleration sensors, the Electronic Control Unit (ECU) calculates the braking force distribution ratio between the front and rear axles and each wheel in real time and dynamically adjusts the brake caliper pressure to prevent excessive braking and lock-up of the rear wheels, thereby improving vehicle braking performance and driving stability.

[0003] Currently, most EBD control strategies are designed based on normal operating conditions and have basic fault failure degradation capabilities. However, when the system malfunctions, it usually adopts a single fixed ratio braking force distribution mode or directly exits the dynamic braking force distribution function, relying solely on mechanical braking to ensure basic braking needs. This fault-tolerant control method cannot adapt to fault modes, has low braking efficiency, and poses a risk of vehicle instability. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide an EBD fault-adaptive fault-tolerant control method and system to solve the problems of low braking efficiency and instability risk in current vehicle fault-tolerant control systems.

[0005] In a first aspect of the present invention, an EBD fault adaptive fault-tolerant control method is provided, comprising: Collect vehicle braking-related parameters; The EBD fault type was determined by cross-validation, model prediction residual analysis, and CAN communication threshold comparison for the braking-related parameters. Calculate the fault error corresponding to the EBD fault type, and determine the EBD fault level based on the fault error corresponding to the EBD fault type and the preset level range threshold. Based on the EBD fault level, implement corresponding fault handling measures and determine the wheel braking force distribution coefficient; Adjust the pressure of each wheel brake caliper to execute the braking force distribution coefficient.

[0006] In a second aspect of the present invention, an EBD fault adaptive fault-tolerant control system is provided, comprising: The data acquisition module is used to collect vehicle braking-related parameters; The fault type determination module is used to determine the EBD fault type by cross-validation, model prediction residual analysis and CAN communication threshold comparison of the braking-related parameters. The fault level determination module is used to calculate the fault error corresponding to the EBD fault type, and determine the EBD fault level based on the fault error corresponding to the EBD fault type and the preset level range threshold. The braking coefficient distribution module is used to execute corresponding fault handling measures according to the EBD fault level and determine the wheel braking force distribution coefficient. The braking execution module is used to adjust the pressure of the brake calipers of each wheel and execute the braking force distribution coefficient.

[0007] In a third aspect of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor executes the computer program to implement the steps of the method as described in the first aspect of the present invention.

[0008] In a fourth aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method provided in the first aspect of the present invention.

[0009] In this embodiment of the invention, the EBD fault type is determined through methods such as cross-validation, model prediction residual analysis, and communication parameter comparison. The fault level is judged based on the EBD fault error. For different fault levels, corresponding fault handling measures are taken and braking force distribution coefficients are determined, thereby improving braking performance under different fault conditions, avoiding vehicle instability risks, and effectively improving vehicle braking stability and safety. Simultaneously, the fault tolerance strategy is ensured to be adaptable to the fault state, exhibiting flexibility and good adaptability. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 A flowchart illustrating an EBD fault adaptive fault-tolerant control method according to an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the braking force distribution under different levels of faults, as provided in one embodiment of the present invention. Figure 3This is a schematic diagram of the structure of an EBD fault adaptive fault-tolerant control system according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device provided in one embodiment of the present invention. Detailed Implementation

[0012] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0013] It should be understood that the terms "comprising" and other similar expressions in the specification, claims, and accompanying drawings of this invention are intended to cover a non-exclusive inclusion, such as a process, method, system, or apparatus that includes a series of steps or units and is not limited to the listed steps or units. Furthermore, "first" and "second" are used to distinguish different objects and are not intended to describe a specific order.

[0014] Please see Figure 1 The present invention provides a flowchart of an EBD fault adaptive fault-tolerant control method, comprising: S101. Collect vehicle braking-related parameters; S102. The EBD fault type is determined by cross-validation, model prediction residual analysis and CAN communication threshold comparison for the braking-related parameters. S103. Calculate the fault error corresponding to the EBD fault type, and determine the EBD fault level based on the fault error corresponding to the EBD fault type and the preset level range threshold. S104. Based on the EBD fault level, implement the corresponding fault handling measures and determine the wheel braking force distribution coefficient. S105. Adjust the pressure of each wheel brake caliper to execute the braking force distribution coefficient.

[0015] After starting the vehicle, the system loads preset control parameters, fault judgment thresholds, vehicle dynamics model parameters, and initial braking force distribution coefficients, initializes all sensors, actuators, and communication modules, completes system self-test, and ensures that all components start normally. If the self-test is abnormal, a fault alarm is triggered directly.

[0016] Vehicle braking-related parameters are collected by various sensors, with a sampling frequency of, for example, 100Hz. These parameters are then transmitted to the decision-making ECU, i.e., the target ECU, via the CAN bus. The target ECU then calculates and determines the wheel braking force distribution coefficient.

[0017] The braking-related parameters include at least the wheel speeds of each wheel, the braking pressures of the front and rear axles, vehicle dynamic parameters, vehicle load, CAN bus communication parameters, and environmental operating condition parameters.

[0018] Wheel speed parameters are the real-time rotational speeds of the four wheels ω1, ω2, ω3, and ω4 (unit: rad / s); braking pressure parameters are the real-time pressures P of the front and rear axle brake calipers. f P r (Unit: MPa); Vehicle dynamic parameters include longitudinal acceleration ax, lateral acceleration ay (unit: m / s²), and vehicle yaw rate γ (unit: rad / s); Load parameters include total vehicle mass m and front and rear axle loads F. zf F zr (Unit: N); Communication parameters are CAN bus communication packet loss rate R and communication delay t (unit: ms); Operating parameters include road surface adhesion coefficient μ, ambient temperature T, and ambient humidity H.

[0019] After step S101, the Kalman filter algorithm is used to denoise the collected braking-related parameters, such as wheel speed, braking pressure, and acceleration signals, to eliminate measurement noise interference.

[0020] In step S102, cross-validation involves cross-comparing the measured values ​​of different sensors for the same physical quantity to determine the relative deviation value, and judging whether a fault exists based on the relative deviation value; model prediction residual analysis involves calculating the residual between the actual response value of the actuator and the ideal response value of the standard model, and judging whether a fault exists based on the residual; communication parameter comparison involves comparing parameters such as communication packet loss rate and delay with basic thresholds to judge whether a communication fault exists.

[0021] EBD fault types can include sensor faults, actuator faults, and communication faults. Actuator faults, also known as brake actuator faults, can be determined by residual analysis based on the real-time pressure of the brake caliper and wheel speed. Communication faults are CAN bus communication faults.

[0022] In step S103, the error corresponding to different types of faults is calculated. For example, for sensor faults, the signal deviation rate can be calculated, and for actuator faults, the control error rate can be calculated. The error is compared with the level interval threshold. When the error is in a certain interval, the current EBD fault level can be determined.

[0023] EBD fault levels can be divided into multiple categories, such as minor, moderate, and severe faults, or Level 1, Level 2, Level 3, and Level 4 faults. Each level of fault corresponds to a threshold range. For example, a packet loss rate R > 15% or a delay t > 100ms can be considered a severe fault; a packet loss rate 5% < R ≤ 15% or a delay 50ms < t ≤ 100ms can be considered a moderate fault; and a packet loss rate R ≤ 5% and a delay t ≤ 50ms can be considered a minor fault. The specific level classification and threshold range settings can be set according to the application scenario and actual needs, and no specific limitations are made here.

[0024] In step S104, different EBD fault levels correspond to different fault handling strategies and vehicle power distribution coefficients. For example, when the fault severity is low, dynamic correction can be performed directly, while when the fault is more severe, a fixed distribution can be used to determine the power distribution coefficient.

[0025] After obtaining the braking force distribution coefficient, the vehicle's actuator layer can achieve precise distribution of braking force by adjusting the pressure of the brake calipers of each wheel. At the same time, the actuator provides real-time feedback on the execution status. If an execution anomaly occurs, it is promptly fed back to the vehicle's decision layer (i.e., the target ECU) to adjust the control strategy and form a closed-loop control. If the fault persists or escalates, a fault alarm is triggered to remind the driver to have it repaired in a timely manner.

[0026] In this embodiment, based on the real-time parameters collected by each sensor, the braking force distribution strategy is dynamically adjusted through fault type identification, fault level quantification and level strategy switching. This not only improves braking performance under different faults, but also enhances braking stability and safety. The braking force distribution is precise and the fault tolerance strategy is flexible and highly adaptable.

[0027] In one embodiment, step S102 includes: Cross-validation is used to verify the sensor measurements in the braking-related parameters to determine whether there is a sensor malfunction. The residual analysis of the model prediction is used to calculate the residual of the actual response value of the actuator in the braking-related parameters, and the presence of actuator failure is determined based on the response value residual. The presence of a cooperative communication fault is determined by comparing the CAN bus communication parameters in the braking-related parameters with a preset threshold.

[0028] Sensor faults can be determined through signal cross-checking, which involves comparing the measured values ​​of the same physical quantity from different sensors and calculating the deviation. If the deviation value is greater than the threshold, that is , If a preset deviation threshold is set and the duration exceeds 100ms, it can be determined to be a sensor malfunction. Furthermore, specific sensor malfunctions such as wheel speed sensor drift / failure and brake pressure sensor abnormality / failure can be distinguished based on the signal source.

[0029] Actuator failures can be determined using model prediction residual analysis. This involves establishing an ideal response model for the actuator and calculating the residual between the actual response value and the ideal response value output by the ideal response model. ,like ( If the residual threshold is used, it can be determined that it is an actuator fault, and further distinctions can be made between specific types such as actuator jamming, response delay, and output abnormality.

[0030] Cooperative communication failures can be determined by monitoring and comparing CAN bus communication parameters. The communication packet loss rate R and communication delay t are collected. If R > 5% or t > 50ms and the duration exceeds 500ms, it can be determined as a cooperative communication failure.

[0031] In one embodiment, step S103 includes: If the EBD fault type is sensor fault, the fault signal deviation rate is calculated and compared with the preset level range threshold to determine the EBD fault level. If the EBD fault type is actuator fault, the calculated control error rate is compared with the preset level range threshold to determine the EBD fault level. If the EBD fault type is a cooperative communication fault, the communication packet loss rate and communication delay are compared with the preset level range threshold to determine the EBD fault level.

[0032] When the fault type is sensor fault, calculate the signal deviation rate. , This is the deviation value. The nominal value of the signal is used; when the fault type is actuator fault, the control error rate is calculated. , In response to residuals, The nominal output of the actuator is used; when the fault type is a cooperative communication fault, the communication packet loss rate R and communication delay t of the CAN bus are used as evaluation indicators.

[0033] The signal deviation rate, control error rate, communication packet loss rate, and communication delay are compared with preset level range thresholds. Each level corresponds to a range threshold. When the signal deviation rate, control error rate, or communication packet loss delay falls within a certain range, the fault level can be determined. When different types of faults exist simultaneously with different fault levels, the highest level fault can be used as the current fault level. For example, if the sensor fault is minor and the communication fault is moderate, the moderate fault level is used.

[0034] For example, the fault levels are classified as follows: Minor fault: Signal deviation rate The communication packet loss rate R ≤ 5% and the communication delay t ≤ 50ms. The fault has little impact on the distribution of braking force, and some dynamic distribution functions can be retained. Moderate fault: Signal deviation rate ≤ 10% <30% or control error rate ≤15% If the communication packet loss rate is less than 40%, or the communication packet loss rate is 5% < R ≤ 15%, or the communication delay is 50ms < t ≤ 100ms, the fault will have a certain impact on the distribution of braking force, and the distribution strategy needs to be optimized. Severe Fault: Signal Deviation Rate ≥30% or control error rate If the failure rate is ≥40%, R > 15%, or communication delay t > 100ms, the fault severely affects the distribution of braking force and needs to be switched to a conservative fixed distribution mode.

[0035] In another embodiment, step S103 further includes: using the analytic hierarchy process to determine the weight of each fault type, calculating a comprehensive evaluation index based on the fault error and weight corresponding to the fault type, and determining the fault level according to the level threshold range in which the comprehensive evaluation index is located.

[0036] In one embodiment, such as Figure 2 As shown, step S104 further includes: If the EBD fault level is Level 1, a fixed allocation mode is adopted, which sets a fixed allocation ratio between the front and rear axles of the vehicle based on the baseline parameters of the vehicle under no-load or full-load conditions. If the EBD fault level is Level 2, the faulty component is restricted from participating in braking force distribution, and the control model is reconstructed based on the vehicle health actuator evaluation data to increase the wheel braking force distribution coefficient of the healthy actuator. If the EBD fault level is level three, a fault signal correction algorithm is used to filter, compensate and correct the signals of the faulty sensor or actuator, and dynamically adjust the braking force distribution ratio of the front and rear axle wheels within a predetermined range.

[0037] For Level 1 faults (severe faults), immediately switch to conservative fixed load distribution mode. Based on the vehicle's unloaded / fully loaded reference parameters, set a fixed front-to-rear axle load distribution ratio, for example, λ=0.6~0.7 when unloaded and λ=0.5~0.6 when fully loaded, to ensure basic braking safety. The fixed load distribution formula is as follows:

[0038]

[0039] In the formula, , For braking force on the front and rear axles, For fixed allocation coefficients, For total braking force.

[0040] For Level 2 faults (moderate faults), the faulty component is restricted from participating in braking force distribution. The control model is reconstructed using healthy component evaluation data, and the braking force distribution coefficient is optimized to prioritize the braking performance of the healthy axle. The optimized distribution formula is as follows:

[0041] In the formula, To optimize the allocation coefficients, This is the allocation coefficient under normal operating conditions. The sum of evaluation indicators for healthy components. This is the sum of all evaluation metrics for all components.

[0042] For Level 3 faults (minor faults), the core dynamic allocation function of EBD is retained. A fault signal correction algorithm is used to filter and compensate the signals of the faulty sensor or actuator to maintain the dynamic adjustment capability of braking force. The braking force allocation coefficient formula is as follows:

[0043] In the formula, λ is the front and rear axle braking force distribution coefficient. , The front and rear axle loads are denoted by α, which is a correction factor with a value of 0.1 to 0.3, and η is the fault evaluation index value.

[0044] This embodiment achieves differentiated fault tolerance based on fault level, with mild dynamic allocation retention, moderate optimized allocation, and severe basic safety protection, maximizing the retention of braking performance under fault conditions, improving braking efficiency, and avoiding instability risks.

[0045] In one embodiment, adjusting the brake caliper pressure of each wheel in step S105 and implementing the braking force distribution coefficient further includes: A seven-degree-of-freedom vehicle dynamics model is constructed. Using a model predictive control algorithm, the vehicle's yaw rate and lateral acceleration are taken as control targets. Combined with the vehicle's real-time state and current environmental parameters, the target braking force of each wheel corresponding to the braking force distribution coefficient is corrected in real time.

[0046] A seven-DOF model was established, including longitudinal, lateral, yaw, and four-wheel rotation. Model predictive control (MPC) algorithm was adopted, with the vehicle's yaw rate and lateral acceleration as control targets. Combining the vehicle's real-time state with the current environmental conditions, the target braking force for each wheel was corrected in real time. The compensation formula is as follows:

[0047] In the formula, This is the braking force compensation amount for the i-th wheel. , , For PID control parameters, The target dynamic parameters (yaw rate, lateral acceleration). These are the actual dynamic parameters.

[0048] This embodiment is based on a seven-degree-of-freedom vehicle dynamics model and MPC algorithm to accurately compensate for braking force deviation, effectively suppress vehicle instability, shorten braking distance and reduce deviation.

[0049] In one embodiment, adjusting the brake caliper pressure of each wheel in step S105 and implementing the braking force distribution coefficient further includes: Using vehicle braking safety parameters and driving stability parameters as reward functions, the wheel braking force distribution coefficient is optimized through a reinforcement learning algorithm.

[0050] Employing a Q-learning reinforcement learning algorithm, with braking safety parameters and driving stability parameters as reward functions, and based on historical data from a cloud-based fault database and real-time local operating condition data, this embodiment automatically optimizes the braking force distribution coefficient, compensation parameters, and fault determination threshold. This implementation achieves self-updating of the strategy through road condition recognition and reinforcement learning, automatically adapting to complex operating conditions and enhancing its adaptability.

[0051] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0052] Figure 3 This is a schematic diagram of the structure of an EBD fault-adaptive fault-tolerant control system provided in an embodiment of the present invention. The system includes: Data acquisition module 310 is used to collect vehicle braking-related parameters; The braking-related parameters include wheel speeds, front and rear axle braking pressures, vehicle dynamic parameters, vehicle load, CAN bus communication parameters, and environmental operating condition parameters.

[0053] The fault type determination module 320 is used to determine the EBD fault type by cross-validation, model prediction residual analysis and CAN communication threshold comparison of the braking-related parameters. The fault level determination module 330 is used to calculate the fault error corresponding to the EBD fault type and determine the EBD fault level based on the fault error corresponding to the EBD fault type and the preset level range threshold. The braking coefficient distribution module 340 is used to execute corresponding fault handling measures according to the EBD fault level and determine the wheel braking force distribution coefficient. The braking execution module 350 is used to adjust the pressure of the brake calipers of each wheel and execute the braking force distribution coefficient.

[0054] In one embodiment, the fault type determination module 320 includes: The first judgment unit is used to verify the sensor measurement values ​​in the braking-related parameters through cross-validation to determine whether there is a sensor malfunction. The second judgment unit is used to perform residual calculation on the actual response value of the actuator in the braking-related parameters through model prediction residual analysis, and to determine whether there is an actuator fault based on the response value residual. The third judgment unit is used to determine whether there is a cooperative communication failure by comparing the CAN bus communication parameters in the braking-related parameters with a preset threshold.

[0055] In one embodiment, determining the EBD fault level based on the fault error corresponding to the EBD fault type and a preset level range threshold includes: If the EBD fault type is sensor fault, the fault signal deviation rate is calculated and compared with the preset level range threshold to determine the EBD fault level. If the EBD fault type is actuator fault, the calculated control error rate is compared with the preset level range threshold to determine the EBD fault level. If the EBD fault type is a cooperative communication fault, the communication packet loss rate and communication delay are compared with the preset level range threshold to determine the EBD fault level.

[0056] In one embodiment, the braking coefficient allocation module 340 includes: The first allocation unit is used to adopt a fixed allocation mode if the EBD fault level is the first level, and to set a fixed allocation ratio between the front and rear axles of the vehicle based on the reference parameters under the vehicle's unloaded or fully loaded state. The second allocation unit is used to restrict the participation of the faulty component in braking force distribution if the EBD fault level is the second level, and to reconstruct the braking control model based on the vehicle health execution component evaluation data to increase the wheel braking force distribution coefficient of the health execution component. The third distribution unit is used to filter, compensate and correct the signals of faulty sensors or actuators by adopting a fault signal correction algorithm if the EBD fault level is level three, and dynamically adjust the braking force distribution ratio of the front and rear axle wheels within a predetermined range.

[0057] In one embodiment, the braking execution module 350 further includes: The execution correction module is used to construct a seven-degree-of-freedom vehicle dynamics model. Through the model predictive control algorithm, the vehicle's yaw rate and lateral acceleration are used as control targets. Combined with the vehicle's real-time state and current environmental operating conditions, the target braking force of each wheel corresponding to the braking force distribution coefficient is corrected in real time.

[0058] In one embodiment, the EBD fault-adaptive fault-tolerant control system further includes: The braking optimization module uses vehicle braking safety parameters and driving stability parameters as reward functions, and optimizes the wheel braking force distribution coefficients through a reinforcement learning algorithm.

[0059] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the system and modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0060] Figure 4 This is a schematic diagram of an electronic device according to an embodiment of the present invention. The electronic device is used for vehicle braking fault-tolerant control. Figure 4 As shown, the electronic device 40 of this embodiment includes: a memory 410, a processor 420, and a system bus 430. The memory 410 includes an executable program 4101 stored thereon. As those skilled in the art will understand, Figure 4 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0061] The following is combined with Figure 4 A detailed description of each component of the electronic device 40 is provided below: The memory 410 can be used to store software programs and modules. The processor 420 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 410. The memory 410 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device (such as cached data), etc. In addition, the memory 410 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0062] The memory 410 contains an executable program 4101 for a vehicle braking control method. This executable program 4101 can be divided into one or more modules / units, which are stored in the memory 410 and executed by the processor 420 to implement vehicle braking fault-tolerant control, etc. Each module / unit can be a series of computer program instruction segments capable of performing a specific function, describing the execution process of the executable program 4101 in the electronic device 40. For example, the executable program 4101 can be divided into functional modules such as a data acquisition module, a fault type judgment module, a fault level judgment module, a braking coefficient allocation module, and a braking execution module.

[0063] The processor 420 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 410, and by calling data stored in the memory 410, it performs various functions and processes data, thereby monitoring the overall status of the electronic device. Optionally, the processor 420 may include one or more processing units; preferably, the processor 420 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, application programs, etc., and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into the processor 420.

[0064] The system bus 430 is used to connect various functional components inside the computer, transmitting data, address, and control information. Its type can be, for example, a PCI bus, an ISA bus, or a CAN bus. Instructions from the processor 420 are transmitted to the memory 410 via the bus, and the memory 410 sends data back to the processor 420. The system bus 430 is responsible for data and instruction exchange between the processor 420 and the memory 410. Of course, the system bus 430 can also connect to other devices, such as network interfaces and display devices.

[0065] In this embodiment of the invention, the executable program executed by the processor 420 included in the electronic device includes: Collect vehicle braking-related parameters; The EBD fault type was determined by cross-validation, model prediction residual analysis, and CAN communication threshold comparison for the braking-related parameters. The fault level determination module is used to calculate the fault error corresponding to the EBD fault type, and determine the EBD fault level based on the fault error corresponding to the EBD fault type and the preset level range threshold. The braking coefficient distribution module is used to execute corresponding fault handling measures according to the EBD fault level and determine the wheel braking force distribution coefficient. The braking execution module is used to adjust the pressure of the brake calipers of each wheel and execute the braking force distribution coefficient.

[0066] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0067] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0068] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An EBD fault-adaptive fault-tolerant control method, characterized in that, include: Collect vehicle braking-related parameters; The EBD fault type was determined by cross-validation, model prediction residual analysis, and CAN communication threshold comparison for the braking-related parameters. Calculate the fault error corresponding to the EBD fault type, and determine the EBD fault level based on the fault error corresponding to the EBD fault type and the preset level range threshold. Based on the EBD fault level, implement corresponding fault handling measures and determine the wheel braking force distribution coefficient; Adjust the pressure of each wheel brake caliper to execute the braking force distribution coefficient.

2. The method according to claim 1, characterized in that, The braking-related parameters include at least the wheel speeds of each wheel, the braking pressures of the front and rear axles, vehicle dynamic parameters, vehicle load, CAN bus communication parameters, and environmental operating condition parameters.

3. The method according to claim 1, characterized in that, The determination of EBD fault type by cross-validation, model prediction residual analysis, and CAN communication threshold comparison of the braking-related parameters includes: Cross-validation is used to verify the sensor measurements in the braking-related parameters to determine whether there is a sensor malfunction. The residual analysis of the model prediction is used to calculate the residual of the actual response value of the actuator in the braking-related parameters, and the presence of actuator failure is determined based on the response value residual. The presence of a cooperative communication fault is determined by comparing the CAN bus communication parameters in the braking-related parameters with a preset threshold.

4. The method according to claim 1, characterized in that, The calculation of the fault error corresponding to the EBD fault type, and the determination of the EBD fault level based on the fault error corresponding to the EBD fault type and the preset level range threshold, include: If the EBD fault type is sensor fault, the fault signal deviation rate is calculated and compared with the preset level range threshold to determine the EBD fault level. If the EBD fault type is actuator fault, the calculated control error rate is compared with the preset level range threshold to determine the EBD fault level. If the EBD fault type is a cooperative communication fault, the communication packet loss rate and communication delay are compared with the preset level range threshold to determine the EBD fault level.

5. The method according to claim 1, characterized in that, The step of implementing corresponding fault handling measures based on the EBD fault level and determining the wheel braking force distribution coefficient includes: If the EBD fault level is Level 1, a fixed allocation mode is adopted, which sets a fixed allocation ratio between the front and rear axles of the vehicle based on the baseline parameters of the vehicle under no-load or full-load conditions. If the EBD fault level is Level 2, the faulty component is restricted from participating in the braking force distribution, and the braking control model is reconstructed based on the vehicle health actuator evaluation data, increasing the wheel braking force distribution coefficient of the healthy actuator. If the EBD fault level is level three, a fault signal correction algorithm is used to filter, compensate and correct the signals of the faulty sensor or actuator, and dynamically adjust the braking force distribution ratio of the front and rear axle wheels within a predetermined range.

6. The method according to claim 1, characterized in that, The adjustment of the brake caliper pressure of each wheel and the execution of the braking force distribution coefficient also include: A seven-degree-of-freedom vehicle dynamics model is constructed. Using a model predictive control algorithm, the vehicle's yaw rate and lateral acceleration are taken as control targets. Combined with the vehicle's real-time state and current environmental parameters, the target braking force of each wheel corresponding to the braking force distribution coefficient is corrected in real time.

7. The method according to claim 1, characterized in that, The step of implementing corresponding fault handling measures based on the EBD fault level and determining the wheel braking force distribution coefficient also includes: Using vehicle braking safety parameters and driving stability parameters as reward functions, the wheel braking force distribution coefficient is optimized through a reinforcement learning algorithm.

8. An EBD fault-adaptive fault-tolerant control system, characterized in that, include: The data acquisition module is used to collect vehicle braking-related parameters; The fault type determination module is used to determine the EBD fault type by cross-validation, model prediction residual analysis and CAN communication threshold comparison of the braking-related parameters. The fault level determination module is used to calculate the fault error corresponding to the EBD fault type, and determine the EBD fault level based on the fault error corresponding to the EBD fault type and the preset level range threshold. The braking coefficient distribution module is used to execute corresponding fault handling measures according to the EBD fault level and determine the wheel braking force distribution coefficient. The braking execution module is used to adjust the pressure of the brake calipers of each wheel and execute the braking force distribution coefficient.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the EBD fault adaptive fault-tolerant control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed, it implements the steps of an EBD fault adaptive fault-tolerant control method as described in any one of claims 1 to 7.

Images