Fuzzy Adaptive Intelligent Wiper Motor Control System and Method Based on Noise Assessment

Abstract

This invention discloses a fuzzy adaptive intelligent wiper motor control method and system based on noise evaluation. It includes an initial speed curve design module for generating an initial angular velocity curve based on the wiper operating frequency and wiping angle; an adaptive algorithm optimization module that processes real-time wiper operating data through a fuzzy logic controller, outputting speed and acceleration adjustment values; a neural network optimization module that uses a multi-layer feedforward neural network to optimize the fuzzy logic controller parameters to minimize the objective function; and a motor control module that adjusts the motor setpoint in real time based on the optimized adjustment values. This invention solves the problem of abnormal noise from automotive wipers, which is caused by excessive noise or insufficient wiping efficiency due to improper speed control. It significantly reduces operating noise, ensures that the wiping frequency meets regulatory requirements, and improves the adaptability and stability of the control system.

Description

Technical Field

[0001] This invention relates to the field of automotive electronics technology, specifically to a fuzzy adaptive intelligent wiper motor control system and method based on noise evaluation. Background Technology

[0002] The windshield wiper system is a critical component for safe driving, and its noise control has always been a challenge for automotive engineers. The speed of the wiper operation significantly impacts noise: excessively high wiper motor speeds or accelerations increase current in the circuit, resulting in noticeable motor noise; simultaneously, excessive speed when the wiper reaches the flip position exacerbates the noise from the rubber blades flipping. Conversely, if the wiper speed is too slow, it fails to meet national regulations regarding wiping frequency, potentially leading to inadequate wiping in rainy weather and increasing the risk of traffic accidents. Therefore, engineers typically design wiper frequencies within the regulatory framework; however, current technology largely relies on experience to design the specific operating speed curve of the wiper motor, lacking a systematic optimization method.

[0003] Existing technologies primarily rely on empirical speed curve design, where engineers manually set the wiper motor's operating speed curve according to regulatory requirements for wiping frequency, ensuring it meets wiping angle requirements within a cycle. This method typically employs a fixed speed pattern, such as accelerating to a constant speed after wiper activation and then briefly decelerating near the flip position. However, this empirical design method has significant drawbacks: First, the lack of real-time feedback and adaptive adjustment prevents dynamic speed optimization based on actual operating conditions, making it difficult to achieve optimal noise levels. Second, empirical design struggles to balance multiple objectives; excessively high speeds increase noise and current, while excessively low speeds result in insufficient wiping efficiency, potentially leading to regulatory compliance risks. Finally, existing methods exhibit poor adaptability to complex operating conditions, easily resulting in noise fluctuations and performance instability. Summary of the Invention

[0004] The purpose of this invention is to provide a fuzzy adaptive intelligent wiper motor control system and method based on noise evaluation. This invention can monitor the position, speed, current and noise data of the wiper in real time through sensors, and use a fuzzy logic controller to perform multi-rule reasoning to dynamically adjust the speed setpoint and acceleration setpoint of the motor. At the same time, it combines a neural network to optimize the parameters of the fuzzy controller to minimize the objective function and realize the adaptive learning and iterative optimization of the wiper operation curve.

[0005] To achieve this objective, the present invention provides a fuzzy adaptive intelligent wiper motor control system based on noise evaluation, comprising: The initial velocity curve design module is used to obtain the initial angular velocity curve of the wiper based on the set wiper operating frequency and wiping angle. The adaptive algorithm optimization module is used to obtain the speed adjustment amount and acceleration adjustment amount of the wiper motor through a fuzzy logic controller based on real-time wiper operating condition data and wiper initial angular velocity curve, as well as the wiper motor's maximum allowable current, maximum allowable operating speed, maximum allowable acceleration, and maximum allowable speed at the flip position. The neural network optimization module optimizes the fuzzy logic controller using a multi-layer feedforward neural network based on the optimization objective function. The optimized wiper motor speed adjustment and acceleration adjustment are obtained through the optimized fuzzy logic controller. The motor control module is used to control the operating status of the wiper motor based on the optimized speed and acceleration adjustment amounts.

[0006] The preferred method for obtaining the initial angular velocity curve of the windshield wiper is as follows: According to the set wiper operating frequency Calculate the wiper cycle : ; According to the wiper operating cycle and the wiper blade angle The specific formula for calculating the initial angular velocity of the windshield wiper is as follows: ; in, The initial angular velocity of the windshield wiper. This refers to the wiper running time; Plot the initial angular velocity curve based on the initial angular velocity of the windshield wiper; Preferably, the method for determining the maximum permissible current, maximum permissible operating speed, maximum permissible acceleration, and maximum permissible speed at the flip position of the wiper motor is as follows: By measuring the current and noise data of the wiper motor at different operating speeds through experiments, and combining the motor performance parameters, the maximum allowable current, maximum allowable operating speed, and maximum allowable acceleration of the wiper motor were determined. The wipers operate at a constant speed. The sound pressure level of the wiper flip position is collected at various speeds to determine the maximum noise of the wipers. The maximum allowable speed of the wiper flip position is then deduced from the maximum noise of the wipers. Preferably, the specific method for obtaining the speed adjustment and acceleration adjustment of the wiper motor based on real-time wiper operating data and the wiper initial angular velocity curve, as well as the maximum allowable current, maximum allowable operating speed, maximum allowable acceleration, and maximum allowable speed at the flip position of the wiper motor, and through fuzzy logic control, is as follows: Wiper position from real-time wiper status data wiper speed wiper current wiper noise Blur the image; wiper position Divided into three fuzzy sets: near the flip position, middle position, and far from the flip position; wiper speed Divided into three fuzzy sets: low speed, medium speed, and high speed; wiper current. The noise of the wipers is divided into three fuzzy sets: low current, medium current, and high current. It is divided into three fuzzy sets: low noise, medium noise, and high noise. A Gaussian membership function is set for each fuzzy set, and the center point and standard deviation of each function are determined. The wiper position θ(t) in the real-time wiper operation data is substituted into the Gaussian membership function set for the three fuzzy sets of near-flip position, middle position, and far from flip position for calculation. The wiper speed v(t) in the real-time wiper operation data is substituted into the Gaussian membership function of the three fuzzy sets of low speed, medium speed, and high speed for calculation. The wiper current i(t) in the real-time wiper operation data is substituted into the Gaussian membership function of the three fuzzy sets of low current, medium current, and high current for calculation. The wiper noise U(t) in the real-time wiper operation data is substituted into the Gaussian membership function of the three fuzzy sets of low noise, medium noise, and high noise for calculation. Based on the calculation results, the precise values ​​of wiper position θ(t), wiper speed v(t), wiper current i(t), and wiper noise U(t) are converted into fuzzy values ​​and stored in a fuzzy set. Fuzzy control rules are set based on the fuzzy set of the input variables, and inference is performed on the real-time wiper operating data according to the fuzzy rules to calculate the fuzzy set corresponding to each fuzzy control rule. Calculate the centroid position of the fuzzy set corresponding to each fuzzy control rule to obtain the velocity adjustment amount and acceleration adjustment amount.

[0007] Preferably, the specific method for controlling the operating status of the wiper motor is as follows: Based on the optimized wiper motor speed and acceleration adjustment values, the wiper motor speed setpoint is adjusted in real time. and acceleration setpoint ,in, Set the speed value. The initial velocity, This refers to the amount of windshield wiper motor speed adjustment. Set the acceleration value. For the initial acceleration, For acceleration adjustment; Simultaneously, the adjusted speed and acceleration settings of the wiper motor are fed back into the adaptive algorithm to optimize the objective function. If the expected value is not achieved, the neural network will readjust the parameters of the fuzzy logic controller, continuously iterating and optimizing until... When the speed converges to the set range, output the corresponding speed setpoint. and acceleration setpoint It converts the speed setpoint and speed setting value into a drive signal that the motor can execute, thereby controlling the operating status of the wiper motor.

[0008] The beneficial effects of this invention are as follows: This invention proposes a fuzzy adaptive intelligent wiper motor control system based on noise evaluation. By collecting wiper position, speed, current, and noise data in real time, and utilizing a fuzzy logic controller combined with multi-rule inference, the system dynamically adjusts the motor speed and acceleration, effectively reducing the noise from the wiper blade flipping and the motor operation noise at the flip position. Specifically, a Gaussian membership function is used for fuzzification processing, combined with a neural network to optimize the objective function, enabling the system to adaptively focus on noise-sensitive areas, thereby minimizing noise under complex operating conditions. By constructing a multi-objective optimization function, the actual wiping frequency of the wiper is ensured to always meet regulatory requirements. The system automatically accelerates to improve wiping efficiency when moving away from the flip position and decelerates to reduce noise when approaching the flip position, thus ensuring timely wiping while avoiding the risk of traffic accidents. A multi-layer feedforward neural network is used to optimize the fuzzy logic controller parameters online, enabling the system to iteratively adjust the control strategy based on real-time operating data. This adaptive mechanism significantly enhances the system's adaptability to various operating conditions, avoiding the performance fluctuation problem of traditional fixed speed curves in complex environments. Through modular design, closed-loop real-time adjustment from data acquisition and fuzzy inference to motor control is achieved. This method not only simplifies system deployment but also ensures the accuracy and smoothness of control commands through operations such as defuzzification using the center of gravity method, effectively reducing the risks of mechanical shock and current overload. This invention achieves multi-objective collaborative optimization of wiper noise, current, and wiping frequency through the intelligent fusion of fuzzy adaptive and neural network technologies, improving driving comfort while ensuring safety and regulatory compliance. Attached Figure Description

[0009] Figure 1 This is a schematic diagram of the structure of the present invention; Figure 2 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0010] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of them. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to represent selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0011] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments: Example 1 A fuzzy adaptive intelligent wiper motor control system based on noise evaluation, such as Figure 1 As shown, it includes: A fuzzy adaptive intelligent wiper motor control system based on noise evaluation, characterized in that it comprises: The initial velocity curve design module is used to obtain the initial angular velocity curve of the wiper based on the set wiper operating frequency and wiping angle. The adaptive algorithm optimization module is used to obtain the speed adjustment amount and acceleration adjustment amount of the wiper motor through a fuzzy logic controller based on real-time wiper operating condition data and wiper initial angular velocity curve, as well as the wiper motor's maximum allowable current, maximum allowable operating speed, maximum allowable acceleration, and maximum allowable speed at the flip position. The neural network optimization module optimizes the fuzzy logic controller using a multi-layer feedforward neural network based on the optimization objective function. The optimized wiper motor speed adjustment and acceleration adjustment are obtained through the optimized fuzzy logic controller. The motor control module is used to control the operating status of the wiper motor based on the optimized speed and acceleration adjustment amounts.

[0012] In some preferred embodiments, by defining the overall modular structure of the system, including an initial speed curve design module, an adaptive algorithm optimization module, a neural network optimization module, and a motor control module, the modular division of labor is clear. The initial speed curve module ensures that the wipers have a basic operating trajectory that complies with regulations, providing a foundation for subsequent optimization; the adaptive algorithm module dynamically adjusts the speed through real-time data feedback, effectively reducing noise when the wipers flip; the neural network module introduces learning capabilities to improve the accuracy and adaptability of control; and the motor control module directly executes optimization commands to achieve closed-loop control. A complete intelligent control system is constructed, enabling the wipers to automatically optimize noise performance during operation while ensuring wiping efficiency, avoiding the uncertainties of relying on experience-based design.

[0013] In some preferred embodiments, the specific method for obtaining the initial angular velocity curve of the windshield wiper is as follows: According to the set wiper operating frequency Calculate the wiper cycle (i.e., the time it takes for the windshield wipers to run for one cycle): ; According to the wiper operating cycle and the wiper blade angle The specific formula for calculating the initial angular velocity of the windshield wiper is as follows: ; in, The initial angular velocity of the windshield wiper. This refers to the wiper running time; The initial angular velocity curve is plotted based on the initial angular velocity of the windshield wiper. In an optional embodiment, the horizontal axis represents time and the vertical axis represents angular velocity. The initial angular velocity curve is set based on experience, and this angular velocity is uniform. After subsequent optimization, it becomes non-uniform.

[0014] In some preferred embodiments, the calculation method for the initial angular velocity curve is specified, the cycle is calculated using the wiper operating frequency, and the angular velocity is obtained based on the integration of the wiper angle. This ensures that the wiper operation strictly complies with regulatory requirements regarding frequency and angle, providing a scientific and repeatable initial curve and avoiding the arbitrariness of traditional empirical design. This lays a reliable foundation for subsequent adaptive optimization, ensuring that the wiper has basic compliance before optimization and reducing initial errors in iterative optimization.

[0015] In some preferred embodiments, the methods for determining the maximum permissible current, maximum permissible operating speed, maximum permissible acceleration, and maximum permissible speed at the flip position of the wiper motor are as follows: By measuring the current and noise data of the wiper motor at different operating speeds through experiments, and combining the motor performance parameters, the maximum allowable current, maximum allowable operating speed, and maximum allowable acceleration of the wiper motor were determined. The wipers operate at a constant speed. The sound pressure level of the wiper flip position is collected at various speeds to indicate the noise level at the wiper flip position. The maximum noise of the wipers is determined, and the maximum allowable speed of the wiper flip position is deduced from the maximum noise of the wipers. In determining the maximum allowable current, maximum allowable operating speed, and maximum allowable acceleration of the wiper motor, in some preferred embodiments, a current sensor is added to the wiper motor circuit to record the current data of the wiper motor during uniform motion. When the wiper motor's operating speed increases, the current will increase synchronously, which will lead to increased motor noise. The current data is collected in real time and fed back to the controller to adjust the speed and acceleration. At the same time, combined with the motor's performance data, the maximum tolerable current, maximum wiper operating speed, and maximum acceleration are confirmed.

[0016] In determining the maximum permissible speed at the flip-over position, some preferred embodiments involve placing the test vehicle in a soundproof chamber and positioning a microphone at the driver's head to collect noise data. The wipers operate at a constant speed, and noise levels at the flip-over position are collected at various speeds. The collected data is processed, and data from the wiper's flip-over position and its vicinity are extracted to obtain a sound pressure level (U), representing the noise level at the flip-over position. After evaluation by engineers, the maximum tolerable noise level is determined, and the maximum speed of the wiper at the flip-over position is derived from this.

[0017] To deduce the maximum permissible speed of the wiper in the flip position from the maximum wiper noise, some preferred embodiments involve adjusting the wiper operating speed to a constant speed, measuring the noise of the wiper in the flip position, measuring the noise at different speeds, and mapping the measured speed values ​​to the noise values. Once the maximum noise is determined, the maximum speed can be determined.

[0018] In some preferred embodiments, thresholds are set by specifying methods for determining parameters such as the maximum permissible current, speed, and acceleration of the wiper motor, experimentally measuring current and noise data, and combining this with motor performance. Safety boundaries are established based on actual test data to prevent motor overload or excessive noise. For example, maximum current limits can prevent motor overheating and damage, and maximum speed limits at the flip position directly address the noise from the wiper blade flipping. This ensures the system operates within a safe and controllable range, improving reliability and durability, while also providing accurate input constraints for fuzzy control.

[0019] In some preferred embodiments, the maximum permissible operating speed of the wiper motor is The following conditions must be met: ; in, For the wiper blade angle, The time it takes for the windshield wipers to complete one cycle; Maximum allowable current of wiper motor It needs to meet the following requirements. , This refers to the current generated during the constant-speed movement of the windshield wiper.

[0020] In some preferred embodiments, by supplementing the condition of the maximum permissible operating speed, the integral constraints of current and angular velocity are emphasized to further refine the performance boundaries, ensuring that the wiper speed is fast enough to meet the wiping angle and time requirements, and avoiding the safety risk of insufficient wiping due to excessively slow speed. While ensuring basic efficiency, this is coordinated with noise control objectives to prevent regulatory compliance from being sacrificed during optimization.

[0021] In some preferred embodiments, the specific method for obtaining the speed adjustment amount and acceleration adjustment amount of the wiper motor through fuzzy logic control, based on real-time wiper operating condition data and the wiper initial angular velocity curve, as well as the maximum allowable current, maximum allowable operating speed, maximum allowable acceleration, and maximum allowable speed at the flip position of the wiper motor, is as follows: Wiper position from real-time wiper status data wiper speed wiper current wiper noise Blur the image; wiper position Divided into three fuzzy sets: near the flip position, middle position, and far from the flip position; wiper speed Divided into three fuzzy sets: low speed, medium speed, and high speed; wiper current. The noise of the wipers is divided into three fuzzy sets: low current, medium current, and high current. It is divided into three fuzzy sets: low noise, medium noise, and high noise. A Gaussian membership function is set for each fuzzy set, and the center point and standard deviation of each function are determined. The wiper position θ(t) in the real-time wiper operation data is substituted into the Gaussian membership function set for the three fuzzy sets of near-flip position, middle position, and far from flip position for calculation. The wiper speed v(t) in the real-time wiper operation data is substituted into the Gaussian membership function of the three fuzzy sets of low speed, medium speed, and high speed for calculation. The wiper current i(t) in the real-time wiper operation data is substituted into the Gaussian membership function of the three fuzzy sets of low current, medium current, and high current for calculation. The wiper noise U(t) in the real-time wiper operation data is substituted into the Gaussian membership function of the three fuzzy sets of low noise, medium noise, and high noise for calculation. Based on the calculation results, the precise values ​​of wiper position θ(t), wiper speed v(t), wiper current i(t), and wiper noise U(t) are converted into fuzzy values ​​and stored in a fuzzy set. Fuzzy control rules are set based on the fuzzy set of the input variables, and inference is performed on the real-time wiper operating data according to the fuzzy rules to calculate the fuzzy set corresponding to each fuzzy control rule. Calculate the centroid position of the fuzzy set corresponding to each fuzzy control rule to obtain the velocity adjustment amount and acceleration adjustment amount.

[0022] In some preferred embodiments, the specific fuzzy control rules are shown in Table 1 below: Table 1 Examples of Fuzzy Control Rules For the wiper position θ(t), wiper speed v(t), wiper current i(t), and wiper noise U(t) in real-time wiper operating data, in some preferred embodiments, the wiper position is obtained through the speed sensor integrated inside the motor, the current value is obtained through an external sensor, and the noise value is obtained through real-time measurement. This algorithm is an offline algorithm, and after matching it to the actual vehicle and designing the speed curve, it does not need to be adjusted. The determination of the design process parameters is completed by the laboratory.

[0023] In some preferred embodiments, the implementation of fuzzy logic control is described in detail. Real-time wiper position, speed, current, and noise data are fuzzified, and adjustment values ​​are output based on a rule table. This transforms complex operating conditions into fuzzy logic, making the control more similar to human decision-making, such as automatically reducing speed to decrease noise when approaching a flip position. This enables real-time, adaptive adjustment, improving the system's responsiveness to dynamic environments and making wiper operation smoother and more intelligent.

[0024] In some preferred embodiments, the specific method for constructing the optimization objective function is as follows: Let the weight of the wiper noise index be... The weight of the wiper current index is The weight of the wiper acceleration smoothness index is The weight of wiper frequency error is ,and + + + =1, optimize the objective function It can be represented as: ( + + ; in, For the sound pressure level of the flip tone, For the average sound pressure coefficient, For the maximum current coefficient, The average current coefficient, This represents the sound pressure level at the wiper's flip position. This represents the average sound pressure level during the operation of the wiper motor. This is the maximum allowable current for the wiper motor. This represents the average current during the operation of the wiper motor. For wiper angle acceleration, Let t be the actual wiping frequency of the windshield wipers. The absolute value of the deviation from the required wiper frequency. As an evaluation indicator of brushing frequency.

[0025] In some preferred embodiments, an optimization objective function is constructed that integrates indicators such as noise, current, acceleration smoothness, and frequency error, and multiple objectives are balanced through weighting. This quantifies the abstract control objective into a computable function, providing an evaluation criterion for neural network optimization and ensuring that the system evolves towards a globally optimal balance during iteration, rather than optimizing a single indicator.

[0026] In some preferred embodiments, the specific method for optimizing the fuzzy logic controller using a multilayer feedforward neural network is as follows: The network structure is set based on real-time sensor data. The input layer has m neurons, the hidden layer has h neurons, and the output layer has p neurons. For the th... There are neurons, and their inputs are: ; in It is the input layer. The first neuron is connected to the hidden layer. The weights of each neuron, It is the input layer. The input value of each neuron, It is the hidden layer. The bias of each neuron determines the output of the hidden layer neurons: ; in, For the Sigmoid function; For the output layer There are neurons, and their inputs are: ; in, For the hidden layer The nth neuron to the output layer The weights of each neuron, It is the output layer. Bias of each neuron; Then, the backpropagation algorithm is used for training, and the error function is defined. : ; in This is the expected output value. This is the actual output value of the neural network. The weights and biases of the neural network are updated according to the error function to obtain the optimized fuzzy logic controller. The weight update formula is: ; in, For the updated weights, The weights before the update are: The learning rate is used, and the bias update formula is: ; For the updated bias, This is the bias before the update.

[0027] In some preferred embodiments, a multi-layer feedforward neural network and an error backpropagation algorithm are used to optimize the fuzzy logic controller parameters. The advantage of this design is that it leverages the self-learning capability of the neural network to automatically adjust the membership function or rule coefficients to adapt to changes in different vehicles or environments. The aim is to improve the generalization and robustness of the control system, enabling the wiper management to maintain optimal performance over the long term and reducing the need for manual parameter tuning.

[0028] In some preferred embodiments, the specific method for controlling the operating state of the wiper motor is as follows: Based on the optimized wiper motor speed and acceleration adjustment values, the wiper motor speed setpoint is adjusted in real time. and acceleration setpoint ,in, Set the speed value. The initial velocity, This refers to the amount of windshield wiper motor speed adjustment. Set the acceleration value. For the initial acceleration, For acceleration adjustment; Simultaneously, the adjusted speed and acceleration settings of the wiper motor are fed back into the adaptive algorithm to optimize the objective function. If the expected value is not achieved, the neural network will readjust the parameters of the fuzzy logic controller, continuously iterating and optimizing until... When the speed converges to the set range, output the corresponding speed setpoint. and acceleration setpoint It converts the speed setpoint and speed setting value into a drive signal that the motor can execute, thereby controlling the operating status of the wiper motor.

[0029] In some preferred embodiments, the centroid method is used to defuzzify the synthesized output fuzzy set to obtain the abscissa value corresponding to the centroid position of the fuzzy set. This abscissa value is the accurate value obtained after defuzzification. Based on the accurate value, the final optimized speed adjustment amount Δv and acceleration adjustment amount Δa are obtained.

[0030] In some preferred embodiments, the adaptive algorithm is a closed-loop intelligent control system integrating perception, decision-making, execution, evaluation, and optimization. It consists of a fuzzy logic controller and a multi-layer feedforward neural network. The fuzzy logic is responsible for fast, real-time reactive control, while the neural network is responsible for slow but global parameter optimization. Working together, the two enable the wiper system to continuously adjust itself, ultimately finding the optimal balance between multiple objectives such as noise, efficiency, and current consumption.

[0031] In some preferred embodiments, by specifying a specific method for controlling the motor's operating state, dynamic closed-loop control is achieved by adjusting the speed setpoint and acceleration setpoint in real time and iteratively optimizing the feedback. This continuously corrects the operating curve until the objective function converges, ensuring that the wiper continues to optimize in actual use, avoiding performance degradation caused by static control, and improving the user experience.

[0032] Example 2 A fuzzy adaptive intelligent wiper motor control method based on noise evaluation, such as Figure 2 As shown, it includes: Based on the set wiper operating frequency and wiping angle, the initial angular velocity curve of the wiper is obtained; Based on real-time wiper operating data and wiper initial angular velocity curve, as well as the wiper motor's maximum allowable current, maximum allowable operating speed, maximum allowable acceleration, and maximum allowable speed at the flip position, the speed adjustment and acceleration adjustment of the wiper motor are obtained through a fuzzy logic controller. Based on the optimization objective function, a multi-layer feedforward neural network is used to optimize the fuzzy logic controller. The optimized wiper motor speed adjustment and acceleration adjustment are obtained through the optimized fuzzy logic controller. The operating status of the wiper motor is controlled based on the optimized speed and acceleration adjustment values.

[0033] In some preferred embodiments, the present invention mainly consists of three steps: 1. Design an initial dynamic speed adjustment curve: reduce speed as the wiper approaches the flip position to minimize rubber strip flipping noise. Increase speed as the wiper moves away from the flip position to improve wiping efficiency and ensure wiping frequency meets regulatory requirements.

[0034] 2. Determine the threshold range through testing. By measuring the noise and current of the rubber strip flipping at different operating speeds, a preset threshold is set. Taking into account regulatory requirements, driving safety, and noise control, multi-objective optimization is achieved.

[0035] 3. Optimization using adaptive algorithms: The position and speed of the wipers are monitored by sensors, and the data is fed back in real time. The algorithm dynamically adjusts the motor speed according to the current position to optimize the overall running curve.

[0036] In some preferred implementation schemes, the specific processing flow is as follows: (1) Design the initial dynamic adjustment speed curve According to regulations, if the frequency of windshield wiper operation is confirmed to be F, then the windshield wiper operation cycle T = 1 / F; The wiper blade angle is designed to be... The real-time angular velocity of the wiper motor is The angular acceleration is α, and it needs to satisfy... angular velocity This is a value that needs to be designed, and it changes over time. The position of the wiper, i.e., the angle from the initial position, is θ. An initial speed curve is set, and subsequent optimization and adjustment are carried out based on this. When the wipers start running, the speed increases and then runs at a constant speed. When approaching the wiper flip position, the speed decreases. When passing the wiper flip position, the speed increases again and then runs at a constant speed. When approaching the stop position, the speed decreases. The designed speed must simultaneously meet the operating frequency requirements in the regulations.

[0037] (2) Determine the threshold range through experiments A current sensor is added to the wiper motor circuit to record the current data I during the wiper motor's constant speed movement. When the wiper motor's operating speed increases, the current increases synchronously, which leads to increased motor noise. The current data is collected in real time and fed back to the controller to adjust the speed and acceleration. At the same time, combined with the motor's performance data, the maximum tolerable current level is determined. Maximum operating speed of windshield wipers Maximum acceleration ; The test vehicle was placed in a soundproof chamber, and a microphone was placed at the driver's head position to collect noise data. The windshield wipers operated at a constant speed, and noise levels at various speeds were collected at the wiper flip position. The collected data was processed, and data from the wiper flip position and its vicinity were extracted to obtain the sound pressure level (U), representing the noise level at the wiper flip position. After evaluation, the maximum tolerable noise was determined, and the maximum speed of the wiper at the flip position was deduced. .

[0038] Maximum operating speed of windshield wipers during operation Needs to be satisfied, The current i during wiper operation needs to meet the following requirements. The angular velocity during the entire operation must satisfy the following equation. .

[0039] (3) Optimization using an adaptive algorithm The evaluation indicators include noise levels, current levels, and brush frequency. Noise level: Noise is a key concern in this invention, and it is measured using the sound pressure level (SPL) collected by a microphone placed at the driver's head position during windshield wiper operation. Particular attention is paid to the noise levels during wiper rotation and motor operation. The SPL value at the wiper rotation position is calculated accordingly. and the average sound pressure value during motor operation As a specific indicator for noise assessment.

[0040] Current rating: Current data is obtained through a current sensor in the wiper motor circuit, representing the maximum current during wiper operation. and average current As an indicator for evaluating current.

[0041] Scraping frequency index: based on actual scraping frequency The absolute value of the deviation from the required brushing frequency F As an evaluation indicator of wiping frequency, it is necessary to ensure that the operation of the wipers meets regulatory requirements.

[0042] Construct the optimization objective function: Let the weight of the noise index be... This is used to punish excessive noise. The weight of the current index is... To prevent motor overload and excessive motor noise, the weight of the acceleration smoothness index is... To reduce mechanical shock and prevent excessive motor noise, the frequency error is weighted as follows: To prevent the wiper efficiency from failing to meet regulatory requirements, and + + + =1, and the objective function J can be expressed as: ( + + .

[0043] in, For the sound pressure level of the flip tone, For the average sound pressure coefficient, For the maximum current coefficient, This is the average current coefficient, used to balance the influence of each sub-indicator on the objective function. Weighting coefficient. , Adjustments can be made based on actual needs and key considerations. For example, if more attention is paid to the noise of the rubber strip flipping, the adjustment can be increased. The value of .

[0044] Data Acquisition and Processing: Real-time acquisition of wiper position information using position sensors. The speed sensor obtains the real-time speed of the windshield wipers. The current sensor obtains the motor current. Microphone acquires noise data Data from these sensors is collected at a specific sampling frequency and transmitted to the controller. The collected data is preprocessed, and a Kalman filter is used to filter the position and velocity data to remove noise interference, thereby improving the accuracy and reliability of the data.

[0045] (4) Adaptive algorithm design Input variable (wiper position) ,speed Current ,noise () to blur.

[0046] wiper position Divided into three fuzzy sets: "near the flip position", "middle position", and "far from the flip position"; speed Divided into three fuzzy sets: "low speed," "medium speed," and "high speed"; current Divided into three fuzzy sets: "low current", "medium current", and "high current", noise The data is divided into three fuzzy sets: "low noise", "medium noise", and "high noise". All sets are fuzzified using similar Gaussian membership functions. Then, the Mamdani method is used for fuzzy inference, and the centroid method is used for defuzzification.

[0047] (5) Parameter update and learning A multi-layer feedforward neural network is used to optimize the parameters of the fuzzy logic controller. The network structure is as follows: the input layer has m=4 neurons, corresponding to the wiper positions respectively. ,speed Current ,noise The hidden layer has h neurons; the output layer has p neurons, corresponding to the adjustable parameters of the fuzzy logic controller. For the l-th neuron in the hidden layer, its input is ,in These are the weights from the i-th neuron in the input layer to the l-th neuron in the hidden layer. It is the input value of the i-th neuron in the input layer. It is the bias of the l-th neuron in the hidden layer, and the output of the hidden layer neuron is... ,here Using the Sigmoid function ; For the q-th neuron in the output layer, its input is ,in These are the weights from the i-th neuron in the hidden layer to the q-th neuron in the output layer. This is the bias of the q-th neuron in the output layer. The output of the neuron in the output layer... This is an adjustable parameter of the fuzzy logic controller.

[0048] Training is performed using the backpropagation algorithm, and the error function is defined as follows: ; in This is the expected output value. This is the actual output value of the neural network. The weights and biases of the neural network are updated according to the error function. The weight update formula is: The bias update formula is: ,in It is the learning rate; The controller adjusts the motor speed setpoint in real time based on the results of optimization using fuzzy logic controller and neural network. and acceleration setpoint Meanwhile, the adjusted operating results are fed back into the adaptive algorithm; if the optimized objective function J does not reach the expected value, the neural network will readjust the parameters of the fuzzy logic controller and continuously iterate and optimize until the objective function J converges to a satisfactory range.

[0049] (6) Setup of the test environment Test vehicles equipped with optimized intelligent wiper motor controllers were placed in various test environments, such as different amounts of rainfall, vehicle speeds, temperatures, and humidity levels, to simulate various complex conditions in actual driving.

[0050] (7) Experimental data collection and analysis During each test, windshield wiper operation data was continuously collected, including position, speed, current, noise, and wiping frequency. The collected data was analyzed to assess the wiper performance at different stages.

[0051] (8) Results evaluation and adjustment Based on the analysis of the test data, the optimized wiper motor controller is evaluated to determine whether it meets the design requirements. If certain indicators do not meet the requirements, such as excessively high noise levels, non-compliant wiping frequency, or excessive current, the parameters of the adaptive algorithm are adjusted.

[0052] (9) Multi-round iterative optimization Through multiple rounds of testing and parameter adjustments, the adaptive algorithm was continuously optimized, enabling the wiper motor controller to achieve optimal performance under various operating conditions. After each iteration, the optimization process was summarized and analyzed, an optimization database was established, and the adjusted parameters and test results were recorded to provide reference and experience for subsequent optimizations. Ultimately, this effectively solved the problem of abnormal wiper noise. Through the above steps, the adaptive algorithm can achieve a globally optimal balance between noise and wiping efficiency while ensuring regulatory compliance.

[0053] Example 3 A computer program product includes a computer program, characterized in that, when the computer program is executed by a processor, it implements the steps of the method described in Embodiment 2.

[0054] The contents not described in detail in this specification are existing technologies known to those skilled in the art.

Claims

1. A fuzzy adaptive intelligent wiper motor control system based on noise evaluation, characterized in that, It includes: The initial velocity curve design module is used to obtain the initial angular velocity curve of the wiper based on the set wiper operating frequency and wiping angle. The adaptive algorithm optimization module is used to obtain the speed adjustment amount and acceleration adjustment amount of the wiper motor through a fuzzy logic controller based on real-time wiper operating condition data and wiper initial angular velocity curve, as well as the wiper motor's maximum allowable current, maximum allowable operating speed, maximum allowable acceleration, and maximum allowable speed at the flip position. The neural network optimization module optimizes the fuzzy logic controller using a multi-layer feedforward neural network based on the optimization objective function. The optimized wiper motor speed adjustment and acceleration adjustment are obtained through the optimized fuzzy logic controller. The motor control module is used to control the operating status of the wiper motor based on the optimized speed and acceleration adjustment amounts.

2. The fuzzy adaptive intelligent wiper motor control system based on noise evaluation according to claim 1, characterized in that: The specific method for obtaining the initial angular velocity curve of the windshield wiper is as follows: According to the set wiper operating frequency Calculate the wiper cycle : ； According to the wiper operating cycle and the wiper blade angle The specific formula for calculating the initial angular velocity of the windshield wiper is as follows: ； in, The initial angular velocity of the windshield wiper. This refers to the wiper running time; Plot the initial angular velocity curve based on the initial angular velocity of the wiper, where the horizontal axis represents the wiper running time and the vertical axis represents the initial angular velocity of the wiper.

3. The fuzzy adaptive intelligent wiper motor control system based on noise evaluation according to claim 1, characterized in that: The methods for determining the maximum permissible current, maximum permissible operating speed, maximum permissible acceleration, and maximum permissible speed at the flip position of the wiper motor are as follows: By measuring the current and noise data of the wiper motor at different operating speeds through experiments, and combining the motor performance parameters, the maximum allowable current, maximum allowable operating speed, and maximum allowable acceleration of the wiper motor were determined. The wipers operate at a constant speed. The sound pressure level of the wiper rotation position is collected at various speeds to determine the maximum noise of the wipers. The maximum allowable speed of the wiper rotation position is then deduced from the maximum noise level.

4. The fuzzy adaptive intelligent wiper motor control system based on noise evaluation according to claim 3, characterized in that: Maximum permissible operating speed of wiper motor The following conditions must be met: ； in, For the wiper blade angle, The time it takes for the windshield wipers to run for one cycle; Maximum allowable current of wiper motor It needs to meet the following requirements. , This refers to the current generated during the constant-speed movement of the windshield wiper.

5. The fuzzy adaptive intelligent wiper motor control system based on noise evaluation according to claim 1, characterized in that: Based on real-time wiper operating data and the initial angular velocity curve of the wiper motor, as well as the maximum allowable current, maximum allowable operating speed, maximum allowable acceleration, and maximum allowable speed at the flip position of the wiper motor, the specific method for obtaining the speed adjustment and acceleration adjustment of the wiper motor through fuzzy logic control is as follows: Wiper position from real-time wiper status data wiper speed wiper current wiper noise Blur the image; wiper position Divided into three fuzzy sets: near the flip position, middle position, and far from the flip position; wiper speed Divided into three fuzzy sets: low speed, medium speed, and high speed; wiper current. The noise of the wipers is divided into three fuzzy sets: low current, medium current, and high current. It is divided into three fuzzy sets: low noise, medium noise, and high noise. A Gaussian membership function is set for each fuzzy set, and the center point and standard deviation of each function are determined. The wiper position θ(t) in the real-time wiper operation data is substituted into the Gaussian membership function set for the three fuzzy sets of near-flip position, middle position, and far from flip position for calculation. The wiper speed v(t) in the real-time wiper operation data is substituted into the Gaussian membership function of the three fuzzy sets of low speed, medium speed, and high speed for calculation. The wiper current i(t) in the real-time wiper operation data is substituted into the Gaussian membership function of the three fuzzy sets of low current, medium current, and high current for calculation. The wiper noise U(t) in the real-time wiper operation data is substituted into the Gaussian membership function of the three fuzzy sets of low noise, medium noise, and high noise for calculation. Based on the calculation results, the precise values ​​of wiper position θ(t), wiper speed v(t), wiper current i(t), and wiper noise U(t) are converted into fuzzy values ​​and stored in a fuzzy set. Fuzzy control rules are set based on the fuzzy set of the input variables, and inference is performed on the real-time wiper operating data according to the fuzzy rules to calculate the fuzzy set corresponding to each fuzzy control rule. Calculate the centroid position of the fuzzy set corresponding to each fuzzy control rule to obtain the velocity adjustment amount and acceleration adjustment amount.

6. The fuzzy adaptive intelligent wiper motor control system based on noise evaluation according to claim 1, characterized in that: The specific method for constructing the optimization objective function is as follows: Let the weight of the wiper noise index be... The weight of the wiper current index is The weight of the wiper acceleration smoothness index is The weight of wiper frequency error is ,and + + + =1, optimize the objective function It can be represented as: ( + + ； in, For the sound pressure level of the flip tone, For the average sound pressure coefficient, For the maximum current coefficient, The average current coefficient, This represents the sound pressure level at the wiper's flip position. This represents the average sound pressure level during the operation of the wiper motor. This is the maximum allowable current for the wiper motor. This represents the average current during the operation of the wiper motor. For wiper angle acceleration, Let t be the actual wiping frequency of the windshield wipers. The absolute value of the deviation from the required wiper frequency. As an evaluation indicator of brushing frequency.

7. A fuzzy adaptive intelligent wiper motor control system based on noise evaluation according to claim 1 or 6, characterized in that: The specific method for optimizing a fuzzy logic controller using a multilayer feedforward neural network is as follows: The network structure is set based on real-time sensor data. The input layer has m neurons, the hidden layer has h neurons, and the output layer has p neurons. For the th... There are neurons, and their inputs are: ； in It is the input layer. The first neuron is connected to the hidden layer. The weights of each neuron, It is the input layer. The input value of each neuron, It is the hidden layer. The bias of each neuron determines the output of the hidden layer neurons: ； in, For the Sigmoid function; For the output layer There are neurons, and their inputs are: ； in, For the hidden layer The nth neuron to the output layer The weights of each neuron, It is the output layer. Bias of each neuron; Then, the backpropagation algorithm is used for training, and the error function is defined. : ； in This is the expected output value. This is the actual output value of the neural network. The weights and biases of the neural network are updated according to the error function to obtain the optimized fuzzy logic controller. The weight update formula is: ； in, For the updated weights, The weights before the update are: The learning rate is used, and the bias update formula is: ； For the updated bias, This is the bias before the update.

8. A fuzzy adaptive intelligent wiper motor control system based on noise evaluation according to claim 7, characterized in that: The specific method for controlling the operating status of the wiper motor is as follows: Based on the optimized wiper motor speed and acceleration adjustment values, the wiper motor speed setpoint is adjusted in real time. and acceleration setpoint ,in, Set the speed value. The initial velocity, This refers to the amount of windshield wiper motor speed adjustment. Set the acceleration value. For the initial acceleration, For acceleration adjustment; Simultaneously, the adjusted speed and acceleration settings of the wiper motor are fed back into the adaptive algorithm to optimize the objective function. If the expected value is not achieved, the neural network will readjust the parameters of the fuzzy logic controller, continuously iterating and optimizing until... When the speed converges to the set range, output the corresponding speed setpoint. and acceleration setpoint It converts the speed setpoint and speed setting value into a drive signal that the motor can execute, thereby controlling the operating status of the wiper motor.

9. A fuzzy adaptive intelligent wiper motor control method based on noise evaluation, characterized in that, It includes: Based on the set wiper operating frequency and wiping angle, the initial angular velocity curve of the wiper is obtained; Based on real-time wiper operating data and wiper initial angular velocity curve, as well as the wiper motor's maximum allowable current, maximum allowable operating speed, maximum allowable acceleration, and maximum allowable speed at the flip position, the speed adjustment and acceleration adjustment of the wiper motor are obtained through a fuzzy logic controller. Based on the optimization objective function, a multi-layer feedforward neural network is used to optimize the fuzzy logic controller. The optimized wiper motor speed adjustment and acceleration adjustment are obtained through the optimized fuzzy logic controller. The operating status of the wiper motor is controlled based on the optimized speed and acceleration adjustment values.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method of claim 9.

Images