Water pump noise control method, heat management system, electronic equipment and vehicle

Abstract

The embodiment of the invention provides a water pump noise control method, a heat management system, electronic equipment and a vehicle. The water pump noise control method comprises the steps of obtaining a target rotating speed of a motor in response to that a detected noise value of a water pump exceeds a preset noise threshold value; acquiring motor parameters of the motor; calculating feedback torque distribution of the motor through the rotating speed prediction model, determining a target control strategy from a plurality of pre-configured control strategies based on the feedback torque distribution, and outputting a predicted rotating speed and parameter information of the motor; and outputting a corresponding voltage control signal to a driving circuit connected with the motor based on the predicted rotating speed. The change trend of the actual rotating speed is estimated by taking the target rotating speed as the expected value through the rotating speed prediction model to obtain the predicted rotating speed, the controller works according to the control strategy corresponding to the controller parameters, and on the basis, the predicted rotating speed outputs the corresponding voltage control signal to the driving circuit, so that the motor rotating speed of the motor can accurately reach the predicted rotating speed, and the driving efficiency is improved. And a better noise suppression effect is achieved.

Description

Technical Field

[0001] This application relates to the field of power battery thermal management technology, and in particular to a water pump noise control method, a thermal management system, electronic equipment, and a vehicle. Background Technology

[0002] Currently, in the thermal management system of power batteries, a water pump is typically used to drive the coolant circulation to remove heat from the power battery and cool it. Due to factors such as mechanical vibration, hydrodynamic noise, and electromagnetic noise, the water pump generates noise during operation. This noise not only reduces the user's driving experience but can also interfere with other electronic devices and control systems, and even affect equipment safety. The working principle of a water pump is that a motor drives the pump impeller to rotate; the vibration frequency of the water pump is proportional to the motor speed. By adjusting the motor speed, the vibration frequency of the water pump can be changed, thereby changing the noise level generated by the water pump. Existing solutions for water pump noise suppression typically involve determining a target speed to suppress the noise based on the pump's operating state when the noise is too high, and directly generating a control signal based on the target speed and sending it to the drive circuit connected to the motor, so that the actual motor speed approaches the target speed. However, this method is not very effective at suppressing noise. Summary of the Invention

[0003] This application provides a water pump noise control method, a thermal management system, electronic equipment, and a vehicle to solve the above-mentioned technical problems.

[0004] The first aspect of this application provides a method for controlling the noise of a vehicle's water pump. The water pump contains a motor, and the control method is executed by a controller. The method includes: in response to a detected noise value of the water pump exceeding a preset noise threshold, obtaining a target speed of the motor; inputting the motor parameters and the target speed into a speed prediction model to calculate the feedback torque distribution of the motor using the speed prediction model; determining a target control strategy from a plurality of pre-configured control strategies based on the feedback torque distribution; and outputting the predicted speed and parameter information of the motor based on the target control strategy; wherein the parameter information is used to update the controller parameters of the controller; and outputting a corresponding voltage control signal to a drive circuit connected to the motor based on the predicted speed; wherein the voltage control signal is used to adjust the interval between turning the drive circuit on or off, so that the motor speed equals the predicted speed.

[0005] In some embodiments, the speed prediction model includes an RBFNN network; inputting the motor parameters and target speed of the motor into the speed prediction model, and calculating the feedback torque distribution of the motor through the speed prediction model, includes: inputting the motor parameters and target speed of the motor into the speed prediction model, the speed prediction model calculating the real-time speed of the motor based on the motor parameters, calculating the actual reference speed difference based on the real-time speed and the target speed and inputting it into the RBFNN network, so as to calculate the feedback torque distribution through the RBFNN network.

[0006] In some embodiments, calculating the feedback torque distribution of the motor using a speed prediction model further includes: the speed prediction model calculating the actual reference speed difference based on the real-time speed and the target speed and inputting it into an RBFNN network to calculate the feedback torque distribution through the RBFNN network; in response to the speed prediction model having already output predicted speed and parameter information, updating the weights in the RBFNN network corresponding to the controller parameters using the gradient descent method; the speed prediction model calculating the real-time speed of the motor based on the motor parameters, calculating the actual reference speed difference based on the real-time speed and the target speed and inputting it into the updated RBFNN network to calculate the feedback torque distribution through the updated RBFNN network.

[0007] In some embodiments, the motor parameters include the current output electromagnetic torque of the motor, the historical motor speed of the motor in the previous sampling period, a preset given speed, and a preset cutoff frequency; the method further includes: calculating the given electromagnetic torque based on the output electromagnetic torque and the historical motor speed; the speed prediction model calculates the real-time speed of the motor based on the motor parameters, including: the speed prediction model calculates the real-time speed based on the given electromagnetic torque, the given speed, the cutoff frequency, and the output electromagnetic torque.

[0008] In some embodiments, determining a target control strategy from a plurality of pre-configured control strategies based on the feedback torque distribution includes: solving a value function using an integral method based on the feedback torque distribution to obtain evaluation scores corresponding to the plurality of control strategies; and determining the control strategy with the highest evaluation score as the target control strategy.

[0009] In some embodiments, after outputting a voltage control signal to the drive circuit connected to the motor, the method further includes: acquiring the actual speed of the motor; calculating the speed difference between the actual speed and the predicted speed in response to the actual speed meeting the speed stability condition; and outputting a corresponding voltage control signal based on the speed difference.

[0010] In some embodiments, the voltage control signal includes a first control signal and a second control signal; outputting a corresponding voltage control signal based on the speed difference includes: outputting a first control signal in response to a speed difference greater than 0, the first control signal being used to extend the interval time; and outputting a second control signal in response to a speed difference less than 0, the second control signal being used to reduce the interval time.

[0011] In some embodiments, the method further includes: acquiring the power supply voltage of the motor; and in response to the power supply voltage being 0, outputting a corresponding voltage control signal to the drive circuit based on a preset protection interval within a preset time period.

[0012] In some embodiments, the method further includes: acquiring a first noise value and a first rotational speed value of the water pump at a first moment; acquiring a second noise value and a second rotational speed value of the water pump at a second moment after the first moment; and in response to the difference between the second noise value and the first noise value being greater than a preset noise increase threshold and the difference between the second rotational speed value and the first rotational speed value being greater than a preset speed increase threshold, using the second noise value as a detected noise value.

[0013] A second aspect of this application provides a thermal management system for a vehicle. The thermal management system includes a water pump and a controller. The water pump contains a motor and a drive circuit. The drive circuit is connected to the motor, and the controller is connected to the drive circuit. The controller is configured to: obtain the target speed of the motor in response to the water pump's detected noise value exceeding a preset noise threshold; input the motor parameters and the target speed to a speed prediction model to calculate the feedback torque distribution of the motor; determine a target control strategy from a plurality of pre-configured control strategies based on the feedback torque distribution; and output the predicted speed and parameter information of the motor based on the target control strategy. The parameter information is used to update the controller parameters of the controller. The controller outputs a corresponding voltage control signal to the drive circuit based on the predicted speed. The voltage control signal is used to adjust the interval between turning the drive circuit on and off so that the motor speed equals the predicted speed.

[0014] A third aspect of this application provides an electronic device including a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to execute the program stored in the memory to implement the water pump noise control method of the first aspect.

[0015] The fourth aspect of this application provides a vehicle that includes a thermal management system as described in the second aspect.

[0016] The water pump noise control method, thermal management system, electronic equipment, and vehicle provided in this application detect that the noise level of the water pump exceeds a preset noise threshold. A target rotational speed capable of suppressing noise is then obtained, and the target rotational speed and motor parameters are input into a speed prediction model. This model predicts the motor's rotational speed change trend and calculates the feedback torque distribution. The effectiveness of multiple control strategies is evaluated using the feedback torque distribution, and the optimal target control strategy is determined from among these strategies, outputting the corresponding predicted rotational speed and parameter information. Thus, by estimating the actual rotational speed change trend using the target rotational speed as the desired value through the speed prediction model, the controller operates according to the control strategy corresponding to the controller parameters. Based on this, the predicted rotational speed outputs a corresponding voltage control signal to the drive circuit, enabling the motor speed to accurately reach the predicted speed, achieving better noise suppression and providing a more intelligent and precise response mechanism for water pump control. Attached Figure Description

[0017] Figure 1 A schematic diagram of the implementation environment of a water pump noise control method provided in an embodiment of this application is shown.

[0018] Figure 2 The illustration shows a first flowchart of a water pump noise control method provided in an embodiment of this application.

[0019] Figure 3 The diagram shows a sub-process diagram of step S201 in a water pump noise control method provided in an embodiment of this application.

[0020] Figure 4 The diagram shows the first sub-process of step S204 in a water pump noise control method provided in an embodiment of this application.

[0021] Figure 5 The diagram shows a second sub-process of step S204 in a water pump noise control method provided in an embodiment of this application.

[0022] Figure 6 The diagram shows a second process flow of a water pump noise control method provided in an embodiment of this application.

[0023] Figure 7 The diagram shows a third process flow of a water pump noise control method provided in an embodiment of this application.

[0024] Figure 8 A schematic diagram of a water pump noise control system provided in an embodiment of this application is shown.

[0025] Figure 9 A schematic diagram of a module of an electronic device provided in an embodiment of this application is shown.

[0026] Figure 10 A schematic diagram of a thermal management system provided in an embodiment of this application is shown.

[0027] Figure 11 A schematic diagram of a vehicle module provided in an embodiment of this application is shown. Detailed Implementation

[0028] To make the technical problems, technical solutions, and beneficial effects solved by this application clearer, the following detailed description is provided in conjunction with embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0029] In the thermal management system of a power battery, a water pump typically drives the coolant circulation to remove heat from the battery. However, the operation of the water pump may generate some noise. This noise mainly originates from the mechanical vibration of the water pump, hydrodynamic noise, and electromagnetic noise. Among these, electromagnetic noise is particularly complex and may be related to factors such as the operating mode and control strategy of the water pump's built-in motor. Noise not only reduces the user's driving experience but may also interfere with the vehicle's internal electronic equipment and control systems, and even affect vehicle safety.

[0030] Since the vibration frequency of a water pump is directly proportional to the speed of its built-in motor, excessively high motor speeds can lead to impeller rotation speed, potentially causing fluid dynamic instability, generating eddies and turbulence, and thus noise. High-speed operation can also intensify the vibration of internal pump components, generating mechanical noise. Conversely, excessively low motor speeds can slow impeller rotation, potentially causing poor fluid flow within the pump, resulting in pressure fluctuations and noise. At low speeds, the fluid volume inside the pump may be insufficient to suppress vibration, also generating noise. Therefore, changing the motor speed can alter the pump's vibration frequency, affecting the fluid flow characteristics within the pump and changing the noise level. Appropriately adjusting the motor speed can reduce noise generated by fluid flow.

[0031] Existing solutions for water pump noise suppression typically involve determining a target rotational speed based on the pump's operating state when noise is excessive, and then generating a control signal based on this target speed and sending it to the motor's drive circuit to approximate the target speed. However, the relationship between motor speed and the voltage control signal is not entirely linear, and the motor speed can be affected by noise, leading to errors between the actual and target speeds. Furthermore, water pump controllers often employ multiple control strategies, selecting one based on actual operating conditions (such as battery temperature, ambient humidity, and coolant viscosity). Under different control strategies, the error between the actual and target motor speeds may increase, resulting in poor noise suppression. Therefore, current solutions for water pump noise suppression are insufficient, and providing an intelligent response mechanism for water pump control to address noise suppression is a pressing technical problem that needs to be solved.

[0032] Therefore, this application provides a water pump noise control method, a thermal management system, electronic equipment, and a vehicle to solve the above-mentioned technical defects.

[0033] In this application, the GP model (Gaussian Process Model) is a Gaussian process model. A Gaussian process refers to a probability distribution defined over a continuous domain, where the joint distribution of any finite number of points follows a multivariate Gaussian distribution. The GP model in this application is a machine learning model for learning the nonlinear dynamics of a motor. It is used to quantify and predict the uncertainty of motor speed changes based on historical speed data, electromagnetic torque, control voltage, and other data, thereby predicting the trend of speed changes.

[0034] In this application, the Radial Basis Function (RBF) neural network is used to map low-dimensional nonlinear data to a high-dimensional space, making it linearly separable in the high-dimensional space. The RBFNN network includes an input layer, hidden layers, and an output layer. The input layer transforms the input data into vectors that the hidden layers can process. The hidden layers include radial basis functions, which assign each RBF neuron a specific operating condition feature and form local response characteristics. The output layer outputs the radial basis functions based on pre-configured weights from the hidden layer neurons to the output layer neurons, obtaining the feedback torque distribution of the motor. The weights determine the contribution ratio of different operating conditions to the final torque command, and the weights in the RBFNN network can be updated using gradient descent. The RBFNN network in this application is used to calculate the feedback torque distribution of the motor based on the error between the motor speed and a given speed. The feedback torque distribution is a dynamic torque command set generated through a probabilistic control strategy; its essence is to transform the uncertainty of the motor's operating state into a distribution function of control actions. Gradient descent is an optimization method that can be used to find local minima of a function. In the RBFNN network, the gradient of the cost function with respect to the weights is calculated, and the weights are updated in the opposite direction of the gradient to reduce the value of the cost function.

[0035] This application provides a water pump noise control method, a thermal management system, an electronic device, and a vehicle. The water pump noise control method includes: in response to a detected noise value of the water pump exceeding a preset noise threshold, obtaining a target speed of the motor; inputting the motor parameters and the target speed into a speed prediction model to calculate the feedback torque distribution of the motor; determining a target control strategy from a plurality of pre-configured control strategies based on the feedback torque distribution; and outputting the predicted speed and parameter information of the motor based on the target control strategy; wherein the parameter information is used to update the controller parameters of the controller; and outputting a corresponding voltage control signal to the drive circuit connected to the motor based on the predicted speed; wherein the voltage control signal is used to adjust the interval between turning the drive circuit on or off, so that the motor speed equals the target speed.

[0036] Compared to existing noise suppression solutions, this application obtains a target rotational speed capable of suppressing noise when the detected noise value of the water pump exceeds a preset noise threshold. The target rotational speed and motor parameters are then input into a speed prediction model. This model predicts the motor's rotational speed change trend and calculates the feedback torque distribution. The effectiveness of multiple control strategies is evaluated using this feedback torque distribution, and the optimal target control strategy is determined, outputting the corresponding predicted rotational speed and parameter information. Thus, by estimating the actual rotational speed change trend using the target rotational speed as the desired value through the speed prediction model, the controller operates according to the control strategy corresponding to the controller parameters. Based on this, the predicted rotational speed outputs a corresponding voltage control signal to the drive circuit, enabling the motor speed to accurately reach the target rotational speed, achieving better noise suppression and providing a more intelligent and precise response mechanism for water pump control.

[0037] This application provides a method for controlling water pump noise.

[0038] Please refer to Figure 1 , Figure 1 This diagram illustrates an implementation environment for a water pump noise control method provided in this embodiment. In this embodiment, the water pump noise control method is applied to a vehicle 100. Specifically, the vehicle 100 includes a power battery 300 and a thermal management system 600. The thermal management system 600 includes a controller 601, a water pump 200, and a cooling body. The cooling body is located within the power battery 300. The controller 601 controls the water pump 200 to operate, and the water pump 200 pushes coolant through the cooling body and into a circulation loop. The heat generated by the power battery 300 is absorbed by the coolant within the cooling body, achieving a cooling effect. Specifically, the water pump 200 includes a motor and a drive circuit. The motor is connected to the drive circuit, and the drive circuit is connected to the controller 601. The drive circuit controls the motor to operate in response to a voltage control signal output by the controller 601. The voltage control signal can control the interval between turning the drive circuit on and off to adjust the motor speed.

[0039] Below, in conjunction with the aforementioned description of the implementation environment, a water pump noise control method provided in the embodiments of this application will be introduced and explained.

[0040] Please refer to the above as well. Figure 2 , Figure 2 This illustration shows a first flowchart of a water pump noise control method provided in an embodiment of this application. The water pump noise control method includes the following steps: S201: Obtain the detected noise value of water pump 200.

[0041] S202: Determine whether the detected noise value of water pump 200 exceeds a preset noise threshold. If yes, proceed to step S203. If no, end. The noise threshold is used to verify whether the current noise value of water pump 200 is too high and needs to be suppressed. If the detected noise value of water pump 200 exceeds the noise threshold, it is considered that the water pump noise needs to be suppressed. Conversely, it is considered that the water pump noise does not need to be suppressed.

[0042] S203: Obtain the target speed of the motor. That is, in response to the detected noise value of the water pump 200 exceeding a preset noise threshold, the target speed of the motor is obtained. Here, the target speed is the speed value of the motor that can suppress water pump noise. By controlling the motor speed value to be equal to the target speed, the vibration frequency of the water pump 200 is changed, thereby reducing the water pump noise.

[0043] S204: Input the motor parameters and target speed of the motor into the speed prediction model. The speed prediction model calculates the feedback torque distribution of the motor, determines the target control strategy from multiple pre-configured control strategies based on the feedback torque distribution, and outputs the predicted speed and parameter information of the motor based on the target control strategy.

[0044] The speed prediction model is a Gaussian process-based GP model of the nonlinear dynamics of the cooling water pump 200 motor. Specifically, the GP model of the nonlinear dynamics of the cooling water pump 200 motor includes the relationship between motor speed and voltage control signal, as well as the influence of noise on motor speed, enabling the speed prediction model to accurately simulate the characteristics of motor speed, voltage control signal, and speed affected by noise.

[0045] The parameter information is used to update the controller parameters of controller 601. For example, the controller parameters include state parameters, signal variance, and noise variance, wherein the state parameters are physical quantities acquired by the sensing system, such as battery temperature, ambient humidity, coolant viscosity, noise frequency band, etc.

[0046] S205: Outputs a voltage control signal to the drive circuit connected to the motor based on the predicted speed. The voltage control signal is used to adjust the interval between turning the drive circuit on and off, so that the motor speed equals the target speed.

[0047] Thus, this application establishes a real-time noise perception mechanism. By acquiring the detected noise value of the water pump 200 and calculating the target speed required for noise suppression when the detected noise value exceeds the noise threshold, dynamic monitoring of the water pump noise is achieved, enabling the system to adjust the operating state of the water pump 200 according to the real-time noise level. Furthermore, the target speed and motor parameters are input into the speed prediction model. The speed prediction model can predict the motor speed change trend and calculate the feedback torque distribution. The effectiveness of multiple control strategies is evaluated through the feedback torque distribution, and the optimal target control strategy is determined from among the multiple control strategies to output the corresponding predicted speed and parameter information.

[0048] Thus, by using a speed prediction model to estimate the actual speed change trend with the target speed as the expected value, the predicted speed is obtained. The controller 601 operates according to the control strategy corresponding to the controller parameters. Based on this, the predicted speed outputs a corresponding voltage control signal to the drive circuit, enabling the motor speed to accurately reach the target speed, effectively reducing operating noise, and providing a more intelligent and precise response mechanism for the control of the water pump 200. On the other hand, this application controls the motor speed by dynamically adjusting the interval time, that is, the interval time between multiple opening and closing of the drive circuit. This method is flexible and efficient, and can quickly adjust the motor speed according to actual needs to adapt to different operating conditions.

[0049] In some embodiments, please refer to Figure 3 , Figure 3 This illustration shows a sub-flow diagram of step S201 in a water pump noise control method provided in an embodiment of this application. Step S201 includes: S301. Obtain the first noise value and the first speed value of the water pump 200 at the first moment. Wherein, the first speed value is the speed of the motor at the first moment.

[0050] S302. Obtain the second noise value and the second speed value of the water pump 200 at the second time point after the first time point. Wherein, the second speed value is the motor speed at the second time point.

[0051] S303. Determine whether the difference between the second noise value and the first noise value is greater than a preset noise increase threshold, and whether the difference between the second rotational speed value and the first rotational speed value is greater than a preset acceleration threshold. If yes, proceed to step S304; otherwise, end.

[0052] S304. Use the second noise value as the detected noise value and execute step S202. That is, in response to the difference between the second noise value and the first noise value being greater than a preset noise increase threshold, and the difference between the second speed value and the first speed value being greater than a preset speed increase threshold, use the second noise value as the detected noise value.

[0053] Specifically, the first time point is defined as time Tk-1, the second time point as time Tk, and time Tk-1 as the time point preceding time Tk. The first noise value of the water pump 200 at time Tk is labeled Y1, and the first rotational speed value of the water pump 200 at time Tk is labeled S1. The second noise value of the water pump 200 at time Tk-1 is labeled Y2. The value of (Y2-Y1) is calculated as Y△, and the value of (S2-S1) is calculated as S△. If Y△ is greater than 0, then Y1 is marked as noise increase data. If S△ is greater than 0, then S1 is marked as noise increase data. When both noise increase data and noise increase data exist simultaneously at time Tk, the second noise value is used as the detected noise value.

[0054] It is understandable that when pump noise is caused by excessively high motor speed leading to excessively high fluid vibration frequency, adjusting the motor speed can effectively suppress the pump noise. However, when pump noise is caused by other specific operating conditions, such as cavitation, even at low motor speeds, high-frequency noise will be generated. In such cases, adjusting the motor speed is not very effective in suppressing pump noise. This application obtains the noise value and motor speed value of the motor at the first and second moments, respectively, and triggers the noise suppression response mechanism only when both speed and noise increase simultaneously. This can accurately pinpoint the noise abrupt change caused by the speed change and avoid misjudgment.

[0055] In some embodiments, step S202 includes: determining whether the detected noise value of the water pump 200 exceeds a preset noise threshold; if so, outputting a warning message to execute step S203; otherwise, ending the process. The warning message is used to verify that the water pump noise exceeds the limit due to excessive rotational speed, ensuring that control is only initiated when the noise exceeds the limit and is accompanied by an increase in rotational speed.

[0056] In some embodiments, step S203 includes: in response to receiving a warning message, inputting the motor's state information into a target speed analysis model to calculate a target speed capable of suppressing pump noise. The motor's state information includes monitoring data such as the motor's current speed. The target speed analysis model is a neural model that learns the relationship between the motor's speed and the noise value of the pump 200, and can calculate a target speed capable of suppressing pump noise based on the motor's current state.

[0057] In some embodiments, the motor parameters include output electromagnetic torque, historical motor speed, given speed, cutoff frequency, and given electromagnetic torque.

[0058] Specifically, before step S204, the pump noise suppression method further includes: acquiring the current output electromagnetic torque of the motor, the historical motor speed in the previous sampling period, a preset given speed, and a preset cutoff frequency. Based on the output electromagnetic torque and the historical motor speed, the given electromagnetic torque is calculated.

[0059] The calculation of the given electromagnetic torque includes both difference calculation and integration. Specifically, the difference between the given speed and the motor speed in the previous sampling period is calculated, and then the difference is integrated to obtain the given electromagnetic torque. Calculating the given electromagnetic torque using the motor's output electromagnetic torque and historical motor speeds reduces signal noise and distortion.

[0060] In some embodiments, please refer to the following: Figure 4 , Figure 4 This illustration shows a first sub-process diagram of step S204 in a water pump noise control method provided in an embodiment of this application. Step S204 includes: S401: Input the motor parameters and target speed into the speed prediction model.

[0061] S402: The speed prediction model calculates the real-time speed of the motor based on motor parameters. Specifically, the speed prediction model calculates the real-time speed based on a given electromagnetic torque, a given speed, a cutoff frequency, and an output electromagnetic torque.

[0062] In the speed prediction model, the real-time speed of the motor is expressed by a transfer function model to improve the reliability. The speed prediction model calculates the real-time speed of the motor based on the motor parameters as follows: The speed prediction model calculates the real-time speed of the motor at the current moment based on the cutoff frequency, given speed, given electromagnetic torque, output electromagnetic torque, motor moment of inertia and the motor speed at the current moment through formula (1).

[0063] (1) in, The cutoff frequency; It is a differential operator; Given a rotational speed; Given electromagnetic torque; To output electromagnetic torque; This represents the motor's current speed. This represents the moment of inertia of the motor.

[0064] In some embodiments, the speed prediction model includes an RBFNN network, in which weights corresponding to the controller parameters are pre-configured.

[0065] In this application, the controller 601 of the water pump 200 employs a state observer (such as a Kalman filter). The controller 601 is configured with multiple control strategies, and can use different control strategies to control the motor speed of the water pump 200 in various scenarios affecting water pump noise. The control strategies are pre-configured with adjustment rules corresponding to the controller parameters; that is, the controller 601 dynamically switches or adjusts the controller parameters according to the identified operating conditions to operate under the corresponding control strategy, maintaining the accuracy of state estimation and the robustness of control performance.

[0066] For example, the control strategies include a first control strategy, a second control strategy, a third control strategy, and a fourth control strategy. The operating variable for the first control strategy is the battery temperature. When the battery temperature exceeds 45°C and the system is under high load, the first control strategy prioritizes cooling. In this scenario, the controller 601 increases the signal variance and noise variance.

[0067] The operating variable for the second control strategy is ambient humidity. When the ambient humidity exceeds 80℃, the system is prone to cavitation, and the adjustment focus of the second control strategy is to limit the upper limit of the rotational speed. In this scenario, controller 601 increases the signal variance and noise variance.

[0068] The operating variable for the third control strategy is coolant viscosity. When the coolant temperature is lower than the preset value or the coolant viscosity is higher than the preset value, the increased viscosity of the coolant at low temperatures leads to increased viscous friction. The adjustment focus of the third control strategy is to slowly increase the motor speed during the startup phase. In this scenario, the controller 601 increases the noise variance.

[0069] The operating condition variable for the fourth control strategy is historical noise records. Within a specific speed range, interface or fluid resonance is triggered, causing the vibration amplitude of a certain characteristic to exceed the limit. The adjustment focus of the fourth control strategy is the active vibration damping speed range. In this scenario, controller 601 increases the noise variance.

[0070] S403: Calculate the feedback torque distribution of the motor using a speed prediction model. Specifically, the speed prediction model calculates the real-time speed of the motor based on its parameters, calculates the actual reference speed difference between the real-time speed and the target speed, and inputs it into the RBFNN network to calculate the feedback torque distribution. The actual reference speed difference reflects the difference between the real-time speed and the target speed.

[0071] It is understandable that the predicted speed is obtained by estimating the trend of actual speed change using the GP model with the target speed as the expected value. The actual reference speed difference is obtained based on the real-time speed and the target speed. The distribution of the actual reference speed difference is averaged into the RBFNN network, and the RBFNN network calculates the feedback torque distribution.

[0072] S404: Determine the target control strategy from multiple pre-configured control strategies based on the feedback torque distribution. Specifically, the value function is solved using the integral method based on the feedback torque distribution to obtain the evaluation scores corresponding to multiple control strategies. The control strategy with the highest evaluation score is determined as the target control strategy, and the corresponding predicted speed and parameter information are output.

[0073] By solving the value function using the integral method, the cumulative time-domain benefits and risks of the control strategy can be quantitatively evaluated. Thus, by selecting the control strategy with the highest evaluation score as the target control strategy, the optimal and effective balance point can be found among different control strategies, achieving multi-objective dynamic balance.

[0074] In some embodiments, please refer to the following: Figure 5 , Figure 5 This illustration shows a second sub-process diagram of step S204 in a water pump noise control method provided in an embodiment of this application. In the sub-process of step S204, after step S403, the water pump noise control method further includes: S501: In response to the fact that the speed prediction model has calculated the predicted speed and parameter information, the weights in the RBFNN network corresponding to the controller parameters are updated using the gradient descent method.

[0075] Based on historical data and the calculation results of the current RBFNN network, gradient descent is used to iteratively update the weights of the current RBFNN network and the corresponding controller parameters. The controller parameters include state parameters, signal variance, and noise variance.

[0076] Specifically, historical data includes relevant data on the feedback torque distribution that has been calculated before by the speed prediction model, including the feedback torque distribution, predicted speed and parameter information output by the speed prediction model, as well as the actual operating status of the motor after the controller 601 outputs a voltage control signal based on the predicted speed and controller parameters.

[0077] It is understandable that, given that the speed prediction model has already output predicted speed and parameter information, it has already calculated historical feedback torque distributions before this calculation, and historical data is stored in the system. Therefore, based on the historical data and the currently calculated feedback torque distribution, the gradient descent method can be used to iteratively update the current RBFNN network.

[0078] S502: The speed prediction model calculates the actual reference speed difference based on the real-time speed and the target speed, and inputs it into the updated RBFNN network to recalculate the feedback torque distribution through the updated RBFNN network, and then executes step S404. The calculation method for the real-time speed can be found in the relevant explanation of step S402 above.

[0079] Specifically, the average distribution of the actual reference speed difference is fed into the updated RBFNN network, and the feedback torque distribution is calculated from the updated RBFNN network. Based on the feedback torque distribution, the value function is solved using the integral method to obtain the evaluation scores corresponding to multiple control strategies. The control strategy with the highest evaluation score is determined as the target control strategy.

[0080] It is understandable that if the speed prediction model calculates the feedback torque distribution through the RBFNN network without having calculated the feedback torque distribution beforehand, then the effectiveness of each control strategy can be directly evaluated based on the current feedback torque distribution, and the predicted speed and controller parameters can be output.

[0081] If the speed prediction model has already calculated the feedback torque distribution, then the feedback torque distribution is calculated through the RBFNN network. Using the currently calculated feedback torque distribution and historical data, the weights of the controller parameters in the RBFNN network are updated using the gradient descent method. The feedback torque distribution is then recalculated through the updated RBFNN network. The effectiveness of each control strategy is evaluated using the updated feedback torque distribution, and the predicted speed and controller parameters are output.

[0082] Thus, this application constructs a speed prediction model through GP-RBFNN hybrid modeling and iteratively optimizes the RBFNN network by updating it using the gradient descent method. This minimizes the deviation between the motor speed and the given speed, making the motor speed controlled by the output voltage control signal closer to the predicted speed. This achieves precise adjustment of the motor speed to suppress noise, while reducing oscillations during system operation and improving the control accuracy and stability of the system.

[0083] It is worth noting that the step of updating and iterating the RBFNN network in this application can be performed after recalculating the target rotational speed, or after the controller parameters change.

[0084] In some embodiments, the voltage control signal includes a first control signal, a second control signal, and a third control signal.

[0085] Correspondingly, step S205 includes: S2051: Calculate the speed difference between the actual speed and the predicted speed of the motor.

[0086] Specifically, when the speed difference is greater than 0, the current actual speed of the motor is determined to be too fast; when the speed difference is less than 0, the current actual speed of the motor is determined to be too slow; when the speed difference is equal to 0, the current actual speed of the motor is determined to meet the adjustment requirements.

[0087] S2052: Outputs a corresponding voltage control signal based on the speed difference.

[0088] Specifically, in response to a speed difference greater than 0, a first control signal is output to extend the interval time. In response to a speed difference less than 0, a second control signal is output to decrease the interval time. In response to a speed difference equal to 0, a third control signal is output to maintain the current interval time.

[0089] Specifically, the actual rotational speed is denoted as Va, the predicted rotational speed as Vt, and the initial interval time as Ti.

[0090] If Va > Vt, it indicates that the current motor speed is too fast and needs to be reduced. Therefore, the first control signal is output to increase Ti, specifically by reducing the time the drive circuit is turned on, increasing the time the drive circuit is turned off, reducing the effective working time of the motor, and reducing the motor speed.

[0091] If Va < Vt, it indicates that the current motor speed is too slow and needs to be increased. In this case, a second control signal is output to reduce Ti. Specifically, this means increasing the time the drive circuit is turned on and decreasing the time the drive circuit is turned off, thus increasing the effective working time of the motor and increasing the motor speed.

[0092] When Va=Vt, it means that the current motor speed has reached the target expected value. Then, the third control signal is output to maintain the current Ti, so that the motor maintains the current speed.

[0093] In some embodiments, please refer to the following: Figure 6 , Figure 6 This illustration shows a second flowchart of a water pump noise control method provided in an embodiment of this application. After step S205, the water pump noise control method further includes: S601: Obtain the power supply voltage of the motor.

[0094] S602: Determine if the power supply voltage is 0. If yes, proceed to step S603. If no, end the process.

[0095] S603: Within a preset time period, outputs a corresponding voltage control signal to the drive circuit based on a preset protection interval time.

[0096] In response to a power supply voltage of 0, within a preset time period, a corresponding voltage control signal is output to the drive circuit based on a preset protection interval, controlling the drive circuit to switch on and off according to the protection interval. Specifically, the preset time period can be half a voltage cycle. There can be multiple protection intervals, and the magnitude of the multiple protection intervals can be the same, or they can increase or decrease sequentially according to a predetermined proportional coefficient.

[0097] Understandably, whenever the motor's power supply voltage is detected to be 0, the drive circuit is switched on and off multiple times in sequence according to a number of preset protection intervals during the next half voltage cycle. This is done to adjust the effective value of the power supply voltage, thereby adjusting the actual speed of the motor. At the same time, a zero-crossing switch protection mechanism is established for the motor to avoid mechanical shock caused by a sudden drop in speed.

[0098] In some embodiments, please refer to the following: Figure 7 , Figure 7 This illustration shows a second flowchart of a water pump noise control method provided in an embodiment of this application. After step S205, the water pump noise control method further includes: S701: Obtain the actual speed of the motor.

[0099] S702: Determine whether the actual rotational speed meets the speed stability condition. If yes, proceed to step S703. If no, end the process.

[0100] Specifically, in response to the actual speed meeting the speed stability condition, the speed difference between the actual speed and the predicted speed of the motor is calculated. For example, the speed stability condition can be: the rate of change of the actual speed within a preset time period is less than a preset range.

[0101] S703: Calculates the speed difference between the actual speed and the predicted speed of the motor.

[0102] Specifically, when the speed difference is greater than 0, the current actual speed of the motor is determined to be too fast; when the speed difference is less than 0, the current actual speed of the motor is determined to be too slow; when the speed difference is equal to 0, the current actual speed of the motor is determined to meet the adjustment requirements.

[0103] S704: Outputs corresponding voltage control signals based on the speed difference.

[0104] Specifically, in response to a speed difference greater than 0, a first control signal is output to extend the interval time. In response to a speed difference less than 0, a second control signal is output to decrease the interval time. In response to a speed difference equal to 0, a third control signal is output to maintain the current interval time.

[0105] Specifically, after adjusting the motor speed, the system needs to detect the actual speed of the motor and determine whether it is stable before adjusting the speed. This is to eliminate the impact of motor speed fluctuations caused by various factors (such as load changes, power supply voltage fluctuations, inertial delays, etc.), reduce the risk of overshoot or undershoot oscillation, and improve system efficiency.

[0106] Understandably, by monitoring the noise and motor speed of water pump 200 in real time and adjusting the motor speed, noise pollution during the operation of water pump 200 is effectively reduced, improving the environmental performance of the system. At the same time, the intelligent early warning and response mechanism and high-precision control strategy enable the system to quickly identify and resolve potential problems, improving the system's stability and reliability.

[0107] This application also provides a water pump noise control system 400, please refer to it as well. Figure 8 , Figure 8 A schematic diagram of a water pump noise control system 400 provided in an embodiment of this application is shown. The water pump noise control system 400 includes: a noise monitoring module 401 for acquiring the detected noise value of the water pump 200; a speed calculation module 402 for acquiring the target speed of the motor in response to the detected noise value of the water pump 200 exceeding a preset noise threshold; a parameter acquisition module 403 for acquiring the motor parameters; a noise analysis module 404 for inputting the motor parameters and the target speed into a speed prediction model to calculate the feedback torque distribution of the motor through the speed prediction model, determine the target control strategy from a plurality of pre-configured control strategies based on the feedback torque distribution, and output the predicted speed and parameter information of the motor. The parameter information is used to update the controller parameters of the controller 601; and an output control module for outputting a corresponding voltage control signal to the drive circuit based on the predicted speed. The voltage control signal is used to adjust the interval between turning the drive circuit on or off so that the motor speed equals the target speed.

[0108] This application also provides an electronic device 500, which can be referred to in conjunction with the above. Figure 9 , Figure 9 A schematic diagram of an electronic device 500 provided in an embodiment of this application is shown. The electronic device 500 includes a processor 501 and a memory, wherein the memory is used to store computer programs, and the processor 501 is used to execute the programs stored in the memory to implement the water pump noise control method as described in the above embodiment.

[0109] This application also provides a thermal management system 600, which can be referred to in conjunction with the above. Figure 10 , Figure 10A schematic diagram of a thermal management system 600 provided in an embodiment of this application is shown. The thermal management system 600 includes a water pump 200 and a controller 601. The water pump 200 is equipped with a motor and a drive circuit. The drive circuit is connected to the motor, and the controller 601 is connected to the drive circuit. The controller 601 is used to: obtain the target speed of the motor in response to the detected noise value of the water pump 200 exceeding a preset noise threshold; obtain the motor parameters; input the motor parameters and the target speed into a speed prediction model to calculate the feedback torque distribution of the motor; determine the target control strategy from a plurality of pre-configured control strategies based on the feedback torque distribution; and output the predicted speed and parameter information of the motor. The parameter information is used to update the controller parameters of the controller 601. Based on the predicted speed, output a corresponding voltage control signal to the drive circuit. The voltage control signal is used to adjust the interval between turning the drive circuit on or off so that the motor speed is equal to the target speed.

[0110] This application also provides a vehicle 100, please refer to it as well. Figure 11 , Figure 11 A schematic diagram of a vehicle 100 provided in an embodiment of this application is shown. The vehicle 100 includes a power battery 300 and a thermal management system 600 as described in the above embodiment.

[0111] It is understood that the beneficial effects and implementation principles of the water pump noise control system 400, electronic equipment 500, thermal management system 600 and vehicle 100 provided in this application can be specifically seen in the relevant descriptions in the foregoing embodiments, and will not be repeated here.

[0112] The terms "first," "second," and "third," etc., used in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. The methods disclosed in the embodiments of this application or the methods shown in the flowcharts include one or more steps for implementing the method. Without departing from the scope of the claims, the execution order of multiple steps can be interchanged, and some steps can also be deleted.

[0113] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for controlling the noise of a vehicle's water pump, wherein the water pump contains a motor, characterized in that... The control method is executed by the controller, and the method includes: In response to the detection noise value of the water pump exceeding a preset noise threshold, the target speed of the motor is obtained; The motor parameters and the target speed of the motor are input into the speed prediction model to calculate the feedback torque distribution of the motor. Based on the feedback torque distribution, a target control strategy is determined from a plurality of pre-configured control strategies, and the predicted speed and parameter information of the motor are output based on the target control strategy. The parameter information is used to update the controller parameters of the controller. Based on the predicted rotational speed, a corresponding voltage control signal is output to the drive circuit connected to the motor; The voltage control signal is used to adjust the interval between turning the drive circuit on or off, so that the motor speed is equal to the predicted speed.

2. The water pump noise control method according to claim 1, characterized in that, The speed prediction model includes an RBFNN network; The step of inputting the motor parameters and the target speed of the motor into the speed prediction model, and calculating the feedback torque distribution of the motor through the speed prediction model, includes: The motor parameters and the target speed are input into the speed prediction model. The speed prediction model calculates the real-time speed of the motor based on the motor parameters, calculates the actual reference speed difference based on the real-time speed and the target speed, and inputs it into the RBFNN network to calculate the feedback torque distribution through the RBFNN network.

3. The water pump noise control method according to claim 2, characterized in that, The step of calculating the feedback torque distribution of the motor using the speed prediction model further includes: In response to the fact that the speed prediction model has already output the predicted speed and the parameter information, the weights in the RBFNN network corresponding to the controller parameters are updated using the gradient descent method; The speed prediction model calculates the actual reference speed difference based on the real-time speed and the predicted speed, and inputs it into the updated RBFNN network to calculate the feedback torque distribution through the updated RBFNN network.

4. The water pump noise control method according to claim 2, characterized in that, The motor parameters include the current output electromagnetic torque of the motor, the historical motor speed of the motor in the previous sampling period, the preset given speed, and the preset cutoff frequency. The method further includes: calculating a given electromagnetic torque based on the output electromagnetic torque and historical motor speed; The speed prediction model calculates the real-time speed of the motor based on the motor parameters, including: The speed prediction model calculates the real-time speed based on the given electromagnetic torque, the given speed, the cutoff frequency, and the output electromagnetic torque.

5. The water pump noise control method according to claim 1, characterized in that, The step of determining the target control strategy from a plurality of pre-configured control strategies based on the feedback torque distribution includes: Based on the feedback torque distribution, the value function is solved using the integral method to obtain the evaluation scores corresponding to multiple control strategies; The control strategy with the highest evaluation score is determined as the target control strategy.

6. The water pump noise control method according to claim 1, characterized in that, After outputting the voltage control signal to the drive circuit connected to the motor, the method further includes: Obtain the actual speed of the motor; In response to the actual speed satisfying the speed stability condition, the speed difference between the actual speed and the predicted speed is calculated; The corresponding voltage control signal is output based on the speed difference.

7. The water pump noise control method according to claim 6, characterized in that, The voltage control signal includes a first control signal and a second control signal; The step of outputting the corresponding voltage control signal based on the speed difference includes: In response to the speed difference being greater than 0, the first control signal is output, which is used to extend the interval time. In response to the speed difference being less than 0, a second control signal is output, which is used to reduce the interval time.

8. The water pump noise control method according to claim 1, characterized in that, The method further includes: Obtain the power supply voltage of the motor; In response to the power supply voltage being 0, within a preset time period, a corresponding voltage control signal is output to the drive circuit based on a preset protection interval time.

9. The water pump noise control method according to claim 1, characterized in that, The method further includes: The first noise value and the first rotational speed value of the water pump at the first moment are obtained; Obtain the second noise value and the second rotational speed value of the water pump at a second time after the first time. In response to the fact that the difference between the second noise value and the first noise value is greater than a preset noise increase threshold, and the difference between the second rotation speed value and the first rotation speed value is greater than a preset speed increase threshold, the second noise value is used as the detected noise value.

10. A thermal management system for a vehicle, characterized in that, The thermal management system includes a water pump and a controller. The water pump contains a motor and a drive circuit. The drive circuit is connected to the motor, and the controller is connected to the drive circuit. The controller is used for: In response to the detection noise value of the water pump exceeding a preset noise threshold, the target speed of the motor is obtained; The motor parameters and the target speed of the motor are input into the speed prediction model to calculate the feedback torque distribution of the motor. Based on the feedback torque distribution, a target control strategy is determined from a plurality of pre-configured control strategies, and the predicted speed and parameter information of the motor are output based on the target control strategy. The parameter information is used to update the controller parameters of the controller. Based on the predicted rotational speed, a corresponding voltage control signal is output to the drive circuit; The voltage control signal is used to adjust the interval between turning the drive circuit on or off, so that the motor speed is equal to the predicted speed.

11. An electronic device, characterized in that, The device includes a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to execute the program stored in the memory to implement the water pump noise control method according to any one of claims 1 to 9.

12. A vehicle, characterized in that, The vehicle includes the thermal management system as described in claim 10.

Images