Vehicle brake motor control method based on MRAS-ANFIS

Abstract

The invention discloses a vehicle brake motor control method based on MRAS-ANFIS, and belongs to the field of vehicle brake motors, and the method comprises the following steps: S1, collecting electromagnetic parameters and inverter parameters, and calibrating a three-phase current signal and a DC bus voltage signal in a static state; s2, estimating an electromagnetic torque and a mechanical angular velocity through an MRAS sensorless state; s3, the braking intention level of the driver is recognized; s4, the total demand braking torque is determined, and maximum regenerated energy recovery is achieved in combination with the slip rate; and S5, dynamically correcting the electromagnetic parameters, and returning to the step S1. By the adoption of the vehicle brake motor control method based on the MRAS-ANFIS, the sensorless state estimation capability of the MRAS and the intelligent decision advantage of the ANFIS are fused, and full-link intelligent control of state accurate sensing, intention dynamic recognition and braking force optimal distribution in the braking process is achieved.

Description

Technical Field

[0001] This invention relates to the field of vehicle brake motor technology, and in particular to a vehicle brake motor control method based on MRAS-ANFIS. Background Technology

[0002] With the advancement of vehicle electrification, the brake motor, as the core actuator for the coordinated operation of regenerative braking and mechanical braking, has seen its control precision, reliability, and energy recovery efficiency become key technical indicators.

[0003] As a core subsystem ensuring driving safety and energy recovery, the development of brake motor control technology in vehicle braking systems has attracted much attention. Traditional brake motor control schemes typically rely on physical sensors (such as rotary transformers and Hall effect sensors) to obtain key state parameters like motor speed and torque. However, these schemes have significant limitations: Firstly, the introduction of physical sensors not only increases system hardware costs and installation complexity but also makes them susceptible to electromagnetic interference, mechanical vibration, and high-temperature environments during vehicle operation, leading to signal distortion or even malfunctions. This severely weakens the accuracy of braking control and the robustness of the system. For example, in urban conditions with frequent start-stop cycles for electric vehicles or under high-vibration conditions for heavy vehicles, the probability of sensor failure can increase by more than 30%. Secondly, the measurement range and dynamic response characteristics of sensors also limit the adaptability of the braking system to extreme conditions (such as high-speed emergency braking and braking on low-traction surfaces). Summary of the Invention

[0004] The purpose of this invention is to provide a vehicle brake motor control method based on MRAS-ANFIS to solve the above-mentioned technical problems.

[0005] To achieve the above objectives, the present invention provides a vehicle brake motor control method based on MRAS-ANFIS, comprising the following steps: S1. System initialization and parameter calibration: Collect electromagnetic parameters and inverter parameters, obtain the control parameter matrix, and calibrate the three-phase current signal and DC bus voltage signal in a static state. S2, MRAS sensorless state estimation: Based on the control parameter matrix and the calibrated three-phase current signal and DC bus voltage signal, electromagnetic torque and mechanical angular velocity are estimated through MRAS sensorless state estimation. S3, ANFIS Braking Intent Recognition: Based on the estimated electromagnetic torque and mechanical angular velocity output from step S2, the driver's braking intent level is identified; S4. Braking torque distribution and coordinated control: Based on the braking intention level output by S3, combined with vehicle mass and wheel rolling radius calculation, the total required braking torque is determined, and combined with slip ratio to maximize regenerative energy recovery. S5. Dynamic Correction and Fault Monitoring: Collect the real-time motor temperature, MRAS sensorless state estimation, and three-phase current during step S4, dynamically correct the electromagnetic parameters, and return to step S1.

[0006] Therefore, the vehicle brake motor control method based on MRAS-ANFIS described above has the following beneficial effects: 1. Improved robustness without sensors: The MRAS algorithm enables high-precision estimation of key state quantities such as motor speed and torque (with errors of <1.2% at high speed and <3.5% at low speed), eliminating the dependence on physical sensors, reducing the risk of system failure due to sensor failure, and reducing hardware costs by approximately 18%.

[0007] 2. Improved accuracy in braking intent recognition: The ANFIS algorithm combines the advantages of fuzzy logic and neural networks, achieving a braking intent recognition accuracy of 92.3% with a response time of only 52±8ms, which is 40% shorter than traditional fuzzy control, thus avoiding imbalance in braking force distribution caused by misjudgment of intent.

[0008] 3. Enhanced braking safety: By dynamically maintaining the slip ratio within the optimal range (15%-20%), the emergency braking distance is shortened by 15.3% compared to traditional PID control (from 50.2m to 42.5m at an initial speed of 120km / h), and the braking distance on low-adhesion surfaces such as ice is shortened by up to 21.7%.

[0009] 4. Optimized energy recovery efficiency: The regenerative braking energy recovery rate under WLTC cycle conditions is increased to 28.6%, which is 32% higher than the traditional solution, significantly extending the driving range of electric vehicles.

[0010] 5. Enhanced adaptability under all operating conditions: Through the adaptive speed estimation of MRAS and the fuzzy rule self-learning of ANFIS, stable control is achieved under complex operating conditions such as high and low speed (19rpm-2920rpm), dry and wet ice surfaces, with an overshoot of only 4.3% (compared to 18.2% for traditional PID).

[0011] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0012] Figure 1 This is a flowchart of the vehicle brake motor control method based on MRAS-ANFIS of the present invention. Detailed Implementation

[0013] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the embodiments of the present invention and are not intended to limit the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of this application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout.

[0014] It should be noted that the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, such as a process, method, system, product, or server that includes a series of steps or units, not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such process, method, product, or device.

[0015] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0016] like Figure 1 As shown, the vehicle brake motor control method based on MRAS-ANFIS includes the following steps: S1. System initialization and parameter calibration: Collect electromagnetic parameters and inverter parameters, obtain the control parameter matrix, and calibrate the three-phase current signal and DC bus voltage signal in a static state. Step S1 specifically includes the following steps: S11. Collect electromagnetic parameters and inverter parameters to determine the inherent electromagnetic properties of the motor and the hardware constraints of the inverter. Among them, electromagnetic parameters include rated power Rated speed Extreme logarithms 25℃ reference stator resistance d-axis inductance q-axis inductance Peak torque And the no-load back electromotive force coefficient measured on the motor test bench ; Inverter parameters include MOSFET on-resistance Maximum output current and DC bus rated voltage ;in, , Indicates the rated current of the brake motor; Control parameter matrix ,in, Represents the electromagnetic parameter matrix, and ; Let represent the inverter constraint parameter matrix, and ; S12. Acquire the raw three-phase current signal under static state. and the original signal of DC bus voltage ; and calculate the current offset respectively. and voltage offset : ; ; In the formula, Indicates the number of valid samples; Indicates the index of the number of samples; S13, Based on current offset and voltage offset Calibrate the three-phase current and DC bus voltage: ; ; In the formula, This indicates the calibrated three-phase current; This indicates the calibrated DC bus voltage.

[0017] S2, MRAS sensorless state estimation: Based on the control parameter matrix and the calibrated three-phase current signal and DC bus voltage signal, electromagnetic torque and mechanical angular velocity are estimated through MRAS sensorless state estimation. Step S2 specifically includes the following steps: S21. Construct a reference model: ; ; In the formula, and These represent the reference d-axis current and the reference q-axis current, respectively. Indicates the electrical angle of the reference model; and They represent In the stationary coordinate system shaft current and shaft current, and ; Represents the integral variable; and They represent the first The second sampling and the first The mechanical angular velocity of the next sample; Indicates the moment of inertia of the brake motor; Indicates the first The reference electromagnetic torque of the next sample. , Indicates permanent magnet flux linkage; Indicates the first The load torque sampled in the second time; Indicates the coefficient of viscous friction; Indicates the sampling period; S22, Based on real-time motor temperature Correcting stator resistance and dq-axis inductance: ; ; ; In the formula, , and These represent the corrected stator resistance, d-axis inductance, and q-axis inductance, respectively. and These represent the temperature coefficients of the stator resistance and inductance, respectively. S23. Calculate the dq axis voltage: ; ; in, ; In the formula, and These represent the d-axis voltage and the q-axis voltage, respectively. This indicates an estimated electrical angle; This indicates an estimate of the mechanical angular velocity; Indicates the sampling time; S24. Estimate the dq-axis current based on the dq-axis voltage and the corrected stator resistance and dq-axis inductance: ; ; In the formula, and They represent the first The second sampling and the first Estimated d-axis current from the next sample; Indicates the first The d-axis voltage of the next sample; Indicates the first The estimated mechanical angular velocity from the next sample; and They represent the first The second sampling and the first Estimate the q-axis current from the next sample; Indicates the first The q-axis voltage of the next sample; S25, Based on current error Correcting the estimated mechanical angular velocity and the corrected estimated mechanical angular velocity Substituting back into step S24, we obtain the corrected estimated dq-axis current. and : ; Constraints: ; in, ; In the formula, Indicates the first The estimated mechanical angular velocity from the next sample; and These represent the proportional coefficient and the integral coefficient, respectively. and They represent the first The second sampling and the first Current error of the second sampling; Indicates the maximum speed of the brake motor; This indicates the maximum mechanical angular velocity of the brake motor; and They represent the first The reference d-axis current and reference q-axis current were sampled in this second sampling. S26. Estimate the electromagnetic torque based on the corrected estimated current. : .

[0018] S3, ANFIS Braking Intent Recognition: Based on the estimated electromagnetic torque and mechanical angular velocity output from step S2, the driver's braking intent level is identified; Step S3 specifically includes the following steps: S31, Based on estimated electromagnetic torque And estimating mechanical angular velocity Calculate the rate of change of electromagnetic torque and rate of change of mechanical angular velocity : ; ; In the formula, Indicates the first The estimated mechanical angular velocity from the next sample; and They represent the first The second sampling and the first Estimated electromagnetic torque from the next sample; S32, Estimate electromagnetic torque Estimating the mechanical angular velocity Electromagnetic torque change rate and rate of change of mechanical angular velocity The fuzzy subset of the input variable is obtained by mapping the membership degree of the fuzzy subset. S33. Construct a mapping relationship between the fuzzy subset of input variables and braking intention, and input the fuzzy subset of input variables into the ANFIS network to obtain the braking intention level.

[0019] S4. Braking torque distribution and coordinated control: Based on the braking intention level output by S3, combined with vehicle mass and wheel rolling radius calculation, the total required braking torque is determined, and combined with slip ratio to maximize regenerative energy recovery. Step S4 specifically includes the following steps: S41. Calculate the total required braking torque. : ; in, ; In the formula, Indicates vehicle mass; Indicates braking deceleration; Indicates the rolling radius of the wheel; This indicates the braking intent level output by the ANFIS network; Indicates the efficiency of the transmission system; S42, Based on estimated mechanical angular velocity Supercapacitor voltage Rated and peak torque Determine the maximum value of regenerative torque. : ; in, ; ; ; In the formula, This indicates the maximum regenerative torque limited by the brake motor itself; Indicates the maximum regenerative torque limited by the battery; This indicates the maximum regenerative torque limited by the supercapacitor; This indicates the electrical angular velocity corresponding to the motor's base speed; Indicates the peak power of the motor; Indicates the conversion factor; and These represent the rated voltages of the battery and the supercapacitor, respectively. and These represent the maximum charging current of the battery and the supercapacitor, respectively. and These represent the charging efficiency of the battery and the supercapacitor, respectively. S43, Braking torque based on total demand Maximum regenerative torque Combined slip ratio Distribute torque: ; ; in, ; In the formula, and These represent the target torque of the brake motor and the target torque of the mechanical brake after slip ratio correction, respectively. and These represent the target torque of the brake motor and the target torque of the mechanical brake, respectively, in the basic allocation. This represents the slip ratio correction factor; S44. Based on the torque distribution results, allocate hybrid energy storage charging: ; ; in, ; In the formula, Indicates regeneration power; Indicates the power generation efficiency of the brake motor; and These represent the target charging currents for the supercapacitor and the battery, respectively. This indicates the power distribution ratio of the supercapacitor.

[0020] S5. Dynamic Correction and Fault Monitoring: Collect the real-time motor temperature, MRAS sensorless state estimation, and three-phase current during step S4, dynamically correct the electromagnetic parameters, and return to step S1.

[0021] In step S5, the 25°C reference stator resistance is dynamically corrected. d-axis inductance q-axis inductance And the corrected 25℃ reference stator resistance d-axis inductance q-axis inductance Substitute into step S1: ; ; ; In the formula, , and These represent the dynamically corrected 25℃ reference stator resistance, d-axis inductance, and q-axis inductance, respectively. , and These represent the initial 25℃ reference stator resistance, d-axis inductance, and q-axis inductance, respectively. Indicates the saturation coefficient; and These represent the temperature coefficients of the stator resistance and inductance, respectively.

[0022] In step S5, the proportional and integral coefficients are also corrected based on the temperature, and the corrected proportional and integral coefficients are substituted into step S25: ; ; In the formula, and These represent the corrected proportional coefficient and integral coefficient, respectively.

[0023] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A vehicle brake motor control method based on MRAS-ANFIS, characterized in that: Includes the following steps: S1. System initialization and parameter calibration: Collect electromagnetic parameters and inverter parameters, obtain the control parameter matrix, and calibrate the three-phase current signal and DC bus voltage signal in a static state. S2, MRAS sensorless state estimation: Based on the control parameter matrix and the calibrated three-phase current signal and DC bus voltage signal, electromagnetic torque and mechanical angular velocity are estimated through MRAS sensorless state estimation. S3, ANFIS Braking Intent Recognition: Based on the estimated electromagnetic torque and mechanical angular velocity output from step S2, the driver's braking intent level is identified; S4. Braking torque distribution and coordinated control: Based on the braking intention level output by S3, combined with vehicle mass and wheel rolling radius calculation, the total required braking torque is determined, and combined with slip ratio to maximize regenerative energy recovery. S5. Dynamic Correction and Fault Monitoring: Collect the real-time motor temperature, MRAS sensorless state estimation, and three-phase current during step S4, dynamically correct the electromagnetic parameters, and return to step S1.

2. The vehicle brake motor control method based on MRAS-ANFIS according to claim 1, characterized in that: Step S1 specifically includes the following steps: S11. Collect electromagnetic parameters and inverter parameters to determine the inherent electromagnetic properties of the motor and the hardware constraints of the inverter. Among them, electromagnetic parameters include rated power Rated speed Extreme logarithms 25℃ reference stator resistance d-axis inductance q-axis inductance Peak torque And the no-load back electromotive force coefficient measured on the motor test bench ; Inverter parameters include MOSFET on-resistance Maximum output current and DC bus rated voltage ;in, , Indicates the rated current of the brake motor; Control parameter matrix ,in, Represents the electromagnetic parameter matrix, and ; Let represent the inverter constraint parameter matrix, and ; S12. Acquire the raw three-phase current signal under static state. and the original signal of DC bus voltage ; and calculate the current offset respectively. and voltage offset : ； ； In the formula, Indicates the number of valid samples; Indicates the index of the number of samples; S13, Based on current offset and voltage offset Calibrate the three-phase current and DC bus voltage: ； ； In the formula, This indicates the calibrated three-phase current; This indicates the calibrated DC bus voltage.

3. The vehicle brake motor control method based on MRAS-ANFIS according to claim 2, characterized in that: Step S2 specifically includes the following steps: S21. Construct a reference model: ； ； In the formula, and These represent the reference d-axis current and the reference q-axis current, respectively. Indicates the electrical angle of the reference model; and They represent In the stationary coordinate system shaft current and shaft current, and ; Represents the integral variable; and They represent the first The second sampling and the first The mechanical angular velocity of the next sample; This represents the moment of inertia of the brake motor. Indicates the first The reference electromagnetic torque of the next sample. , Indicates permanent magnet flux linkage; Indicates the first The load torque sampled in the second time; Indicates the coefficient of viscous friction; Indicates the sampling period; S22, Based on real-time motor temperature Correcting stator resistance and dq-axis inductance: ； ； ； In the formula, , and These represent the corrected stator resistance, d-axis inductance, and q-axis inductance, respectively. and These represent the temperature coefficients of the stator resistance and inductance, respectively. S23. Calculate the dq-axis voltage: ； ； in, ； In the formula, and These represent the d-axis voltage and the q-axis voltage, respectively. This indicates an estimated electrical angle; This indicates an estimate of the mechanical angular velocity; Indicates the sampling time; S24. Estimate the dq-axis current based on the dq-axis voltage and the corrected stator resistance and dq-axis inductance: ； ； In the formula, and They represent the first The second sampling and the first Estimated d-axis current from the next sample; Indicates the first The d-axis voltage of the next sample; Indicates the first The estimated mechanical angular velocity from the next sample; and They represent the first The second sampling and the first The estimated q-axis current for the second sampling; Indicates the first The q-axis voltage of the next sample; S25, Based on current error Correcting the estimated mechanical angular velocity and the corrected estimated mechanical angular velocity Substituting back into step S24, we obtain the corrected estimated dq-axis current. and : ； Constraints: ; in, ； In the formula, Indicates the first The estimated mechanical angular velocity from the next sample; and These represent the proportional coefficient and the integral coefficient, respectively. and They represent the first The second sampling and the first Current error of the second sampling; Indicates the maximum speed of the brake motor; This indicates the maximum mechanical angular velocity of the brake motor; and They represent the first The reference d-axis current and reference q-axis current were sampled in this second sampling. S26. Estimate the electromagnetic torque based on the corrected estimated current. : 。 4. The vehicle brake motor control method based on MRAS-ANFIS according to claim 3, characterized in that: Step S3 specifically includes the following steps: S31, Based on estimated electromagnetic torque And estimating mechanical angular velocity Calculate the rate of change of electromagnetic torque and rate of change of mechanical angular velocity : ； ； In the formula, Indicates the first The estimated mechanical angular velocity from the next sample; and They represent the first The second sampling and the first Estimated electromagnetic torque from the next sample; S32, Estimate electromagnetic torque Estimating the mechanical angular velocity Electromagnetic torque change rate and rate of change of mechanical angular velocity The fuzzy subset of the input variable is obtained by mapping the membership degree of the fuzzy subset. S33. Construct a mapping relationship between the fuzzy subset of input variables and braking intention, and input the fuzzy subset of input variables into the ANFIS network to obtain the braking intention level.

5. The vehicle brake motor control method based on MRAS-ANFIS according to claim 4, characterized in that: Step S4 Specifically, the following steps are included: S41. Calculate the total required braking torque. : ； in, ； In the formula, Indicates vehicle mass; Indicates braking deceleration; Indicates the rolling radius of the wheel; This indicates the braking intent level output by the ANFIS network; Indicates the efficiency of the transmission system; S42, Based on estimated mechanical angular velocity Supercapacitor voltage Rated and peak torque Determine the maximum value of regenerative torque. : ； in, ； ； ； In the formula, This indicates the maximum regenerative torque limited by the brake motor itself; Indicates the maximum regenerative torque limited by the battery; This indicates the maximum regenerative torque limited by the supercapacitor; This indicates the electrical angular velocity corresponding to the motor's base speed; Indicates the peak power of the motor; Indicates the conversion factor; and These represent the rated voltages of the battery and the supercapacitor, respectively. and These represent the maximum charging current of the battery and the supercapacitor, respectively. and These represent the charging efficiency of the battery and the supercapacitor, respectively. S43, Braking torque based on total demand Maximum regenerative torque Combined slip ratio Distribute torque: ； ； in, ； In the formula, and These represent the target torque of the brake motor and the target torque of the mechanical brake after slip ratio correction, respectively. and These represent the target torque of the brake motor and the target torque of the mechanical brake, respectively, in the basic allocation. This represents the slip ratio correction factor; S44. Based on the torque distribution results, allocate hybrid energy storage charging: ； ； in, ； In the formula, Indicates regeneration power; Indicates the power generation efficiency of the brake motor; and These represent the target charging currents for the supercapacitor and the battery, respectively. This indicates the power distribution ratio of the supercapacitor.

6. The vehicle brake motor control method based on MRAS-ANFIS according to claim 5, characterized in that: In step S5, the 25°C reference stator resistance is dynamically corrected. d-axis inductance q-axis inductance And the corrected 25℃ reference stator resistance d-axis inductance q-axis inductance Substitute into step S1: ； ； ； In the formula, , and These represent the dynamically corrected 25℃ reference stator resistance, d-axis inductance, and q-axis inductance, respectively. , and These represent the initial 25℃ reference stator resistance, d-axis inductance, and q-axis inductance, respectively. Indicates the saturation coefficient; and These represent the temperature coefficients of the stator resistance and inductance, respectively.

7. The vehicle brake motor control method based on MRAS-ANFIS according to claim 6, characterized in that: In step S5, the proportional and integral coefficients are also corrected based on the temperature, and the corrected proportional and integral coefficients are substituted into step S25: ； ； In the formula, and These represent the corrected proportional coefficient and integral coefficient, respectively.

Images