Motor active vibration and noise reduction method, system and device and storage medium

Abstract

The invention provides an active vibration and noise reduction method, system and device for a motor and a storage medium, and belongs to the technical field of motor vibration reduction. Inputting the real-time noise into the trained flexible Actor-Critic model, and obtaining the target harmonic injection frequency, the target phase and the target amplitude of the harmonic injection device; and generating a harmonic current for counteracting the radial electromagnetic force of the motor based on the target harmonic injection times, the target phase and the target amplitude. According to the method, different harmonic parameters are output according to different real-time noises of the motor through the flexible Actor-Critic model, active updating of harmonics is realized, and the noise reduction efficiency and accuracy of vibration and noise reduction of the motor are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of motor vibration reduction, and in particular to a method, system, device and storage medium for active motor vibration and noise reduction. Background Art

[0002] Motors are widely used in military, industrial, agricultural and other fields. During the operation of the motor, a lot of noise is often generated. According to the source of noise, motor noise can be divided into three categories: aerodynamic noise, mechanical noise, and electromagnetic noise. Among them, electromagnetic noise is considered to be the main source of motor noise, and radial electromagnetic waves are the main cause of motor vibration and noise. Electromagnetic noise is related to unavoidable factors such as motor magnetic circuit structure, slot-pole matching, winding distribution, current harmonics, eccentricity and material properties. And as long as the motor operates normally, corresponding electromagnetic vibration and noise will be generated.

[0003] The existing technology mainly injects harmonic currents of a specific order to interact with the fundamental magnetic field generated by the permanent magnet to generate radial electromagnetic forces of a specific spatial order and frequency, thereby weakening the vibration and noise caused by the electromagnetic force. This method of weakening noise is called the harmonic injection method. However, since the motor will operate in different working conditions during actual use, the noise generated by the motor under different working conditions is different, that is, it is necessary to adjust the harmonic injection parameters according to the applicability of the working conditions. In the prior art, the adjustment of the harmonic injection parameters is mostly passive. Specifically, when the noise is detected to be too loud, the harmonic injection parameters are manually adjusted to achieve vibration reduction and noise reduction. It has the following technical problems: the adjustment of the harmonic injection parameters is not precise enough, resulting in poor noise reduction effect.

[0004] Therefore, there is an urgent need to provide a method, system, device and storage medium for active vibration and noise reduction of a motor to achieve precise adjustment of harmonic injection parameters and ensure the active noise reduction effect of the motor. Summary of the invention

[0005] In view of this, it is necessary to provide a method, system, device and storage medium for active vibration and noise reduction of a motor to solve the technical problem in the prior art that the adjustment accuracy of harmonic injection parameters is reduced, resulting in poor noise reduction effect.

[0006] On the one hand, in order to solve the above technical problems, the present invention provides a method for actively reducing vibration and noise of a motor, comprising: Get the real-time noise of the motor; Inputting the real-time noise into the trained flexible Actor-Critic model to obtain the target harmonic injection order, target phase and target amplitude of the harmonic injection device; A harmonic current is generated to counteract the radial electromagnetic force of the motor based on the target harmonic injection order, the target phase, and the target amplitude.

[0007] In a possible implementation, the flexible Actor-Critic model includes a soft Q network, a value network, and a policy network; before inputting the real-time noise into the trained flexible Actor-Critic model, it also includes: Acquire a training sample; the training data in the training sample is a five-tuple data, and the five-tuple data includes a state at a first historical moment, an action at the first historical moment, a reward value at the first historical moment, a cumulative reward value at the first historical moment, and a state at a second historical moment; the second historical moment is a moment next to the first historical moment; Inputting the training data into the soft Q network, the value network and the strategy network respectively, and obtaining the predicted reward value, the predicted cumulative reward value and the predicted action respectively; Determining the reward value at the first historical moment and the reward loss value of the predicted reward value based on the first loss function of the soft Q network, and optimizing the network parameters of the soft Q network based on the reward loss value to obtain a target soft Q network; Determine the cumulative reward value at the first historical moment and the predicted reward loss value of the predicted cumulative reward value based on the second loss function of the value network, and optimize the network parameters of the value network based on the predicted reward loss value to obtain a target value network; Determine an action loss value based on a third loss function of the policy network, the state at the first historical moment, and the predicted state, and optimize a network parameter of the policy network based on the action loss value to obtain a target policy network; The target soft Q network, the target value network and the target strategy network constitute a trained flexible Actor-Critic model.

[0008] In a possible implementation, when the number of training iterations of the network parameters of the soft Q network reaches a preset number, or the training error is less than a preset error, or the error change trend is less than a preset change trend, the network parameters of the soft Q network are stopped from being optimized to obtain the target soft Q network.

[0009] In a possible implementation, the inputting the real-time noise into a trained flexible Actor-Critic model to obtain a target harmonic injection order, a target phase, and a target amplitude of a harmonic injection device includes: Determine the real-time state of the motor based on the real-time noise; the real-time state includes the real-time amplitude, real-time noise frequency, noise phase constant and real-time motor frequency of the motor; Processing the real-time state based on the target strategy network to obtain a real-time target decision action, and controlling the harmonic injection device to execute the target decision action; Wherein, the target decision action includes the target harmonic injection number, the target phase and the target amplitude.

[0010] In a possible implementation, the optimal strategy of the policy network is:

[0011]

[0012] In the formula, is the optimal strategy; The status is , the action is Rewards when is the entropy discount factor; The status is Entropy of time; is the policy function of the policy network; To find the expectation of cumulative reward and maximum entropy; is the maximum value operator.

[0013] In a possible implementation, the first loss function is:

[0014] The second loss function is:

[0015] The third loss function is:

[0016] In the formula, is the first loss function; is the predicted value of the soft Q network; is the true value of the soft Q network; is the second loss function; is the predicted value of the value network; is the true value of the value network; is the third loss function; is the coefficient; is the output value of the policy network.

[0017] In a possible implementation, the optimization algorithm used during training of the soft Q network, the value network, and the policy network is stochastic gradient descent.

[0018] On the other hand, the present invention also provides a motor active vibration reduction and noise reduction system, comprising: A real-time noise acquisition unit, used for acquiring the real-time noise of the motor; A harmonic injection device parameter determination unit, used for inputting the real-time noise into a trained flexible Actor-Critic model to obtain a target harmonic injection number, target phase and target amplitude of the harmonic injection device; The vibration reduction and noise reduction unit is used to generate a harmonic current for counteracting the radial electromagnetic force of the motor based on the target harmonic injection order, the target phase and the target amplitude.

[0019] On the other hand, the present invention also provides a motor active vibration reduction and noise reduction device, including a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps of the method for active vibration and noise reduction of a motor described in any one of the possible implementations above.

[0020] On the other hand, the present invention also provides a computer-readable storage medium for storing computer-readable programs or instructions, which, when executed by a processor, can implement the steps of the method for active vibration and noise reduction of a motor described in any of the above possible implementation methods.

[0021] The beneficial effects of the present invention are as follows: the motor active vibration reduction and noise reduction method provided by the present invention takes the harmonic injection device as the intelligent agent, and determines the parameters of the harmonic injection device under different real-time noises (target harmonic injection times, target phase and target amplitude) based on the trained flexible Actor-Critic model, thereby realizing active vibration reduction and noise reduction of the motor. In addition, the flexible Actor-Critic model adds the entropy value of the action to the reward function, which enhances the stability of the model while improving the exploration ability of the intelligent agent; secondly, the flexible Actor-Critic model adopts offline strategy update, reuses previously collected data to improve efficiency, improves the injection efficiency while ensuring the accuracy of the harmonic injection device, and thus improves the vibration reduction and noise reduction effect and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A schematic flow chart of an embodiment of the method for active vibration and noise reduction of a motor provided by the present invention; Figure 2 A schematic diagram of the structure of an embodiment of the flexible Actor-Critic model provided by the present invention; Figure 3 A schematic diagram of a flow chart of an embodiment of training a flexible Actor-Critic model provided by the present invention; Figure 4 For the present invention Figure 1 A schematic flow chart of an embodiment of obtaining the target harmonic injection number, target phase and target amplitude in step S102; Figure 5 A schematic diagram of the structure of an embodiment of the active vibration and noise reduction system for a motor provided by the present invention; Figure 6 This is a schematic structural diagram of an embodiment of the active vibration and noise reduction device for a motor provided by the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0025] It should be understood that the schematic drawings are not drawn to scale. The flowchart used in the present invention shows the operations implemented according to some embodiments of the present invention. It should be understood that the operations of the flowchart can be implemented out of order, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art, under the guidance of the content of the present invention, can add one or more other operations to the flowchart, and can also remove one or more operations from the flowchart. Some of the block diagrams shown in the accompanying drawings are functional entities, which do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor systems and / or microcontroller systems.

[0026] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0027] The present invention provides a method, system, device and storage medium for active vibration and noise reduction of a motor, which are described below respectively.

[0028] Figure 1 A schematic diagram of an embodiment of the method for active vibration and noise reduction of a motor provided by the present invention is shown in FIG. Figure 1 As shown, the motor active vibration reduction and noise reduction method includes: S101, obtaining real-time noise of the motor; S102, inputting the real-time noise into the trained soft actor-critic (SAC) model to obtain the target harmonic injection number, target phase and target amplitude of the harmonic injection device; S103 , generating a harmonic current to offset the radial electromagnetic force of the motor based on the target harmonic injection order, the target phase, and the target amplitude.

[0029] Compared with the prior art, the motor active vibration reduction and noise reduction method provided by the embodiment of the present invention takes the harmonic injection device as the intelligent agent, and determines the parameters of the harmonic injection device under different real-time noises (target harmonic injection times, target phase and target amplitude) based on the trained flexible Actor-Critic model, thereby realizing active vibration reduction and noise reduction of the motor. In addition, the flexible Actor-Critic model adds the entropy value of the action to the reward function, which enhances the stability of the model while improving the exploration ability of the intelligent agent; secondly, the flexible Actor-Critic model adopts offline strategy update, reuses previously collected data to improve efficiency, improves the injection efficiency while ensuring the accuracy of the harmonic injection device, and thus improves the vibration reduction and noise reduction effect and efficiency.

[0030] In some embodiments of the present invention, Figure 2 As shown in Figure 2, the flexible Actor-Critic model includes a soft Q network, a value network, and a strategy network.

[0031] It should be noted that the soft Q network and the value network are the evaluation networks in the flexible Actor-Critic model. They are "critics" who do not take actions directly but evaluate the quality of actions. The policy network is an "actor" that determines decision actions based on the input state.

[0032] It should also be noted that: Figure 2 The solid arrows in the middle represent the process of forward parameter transfer, and the dotted arrows represent the process of backpropagation of parameters to update and iterate the network.

[0033] To ensure the validity of the flexible Actor-Critic model, before step S102, the flexible Actor-Critic model needs to be trained to obtain a trained flexible Actor-Critic model. Figure 3 As shown in Figure 1, the process of training the flexible Actor-Critic model is as follows: S301, obtaining a training sample; the training data in the training sample is a five-tuple data, the five-tuple data includes a state at a first historical moment, an action at the first historical moment, a reward value at the first historical moment, a cumulative reward value at the first historical moment, and a state at a second historical moment; the second historical moment is the next moment of the first historical moment; S302, input the training data into the soft Q network, the value network and the policy network respectively, and obtain the predicted reward value, the predicted cumulative reward value and the predicted action respectively; S303, determining a reward loss value of a reward value and a predicted reward value at a first historical moment based on a first loss function of the soft Q network, and optimizing a network parameter of the soft Q network based on the reward loss value to obtain a target soft Q network; S304, determining the cumulative reward value at the first historical moment and the predicted reward loss value of the predicted cumulative reward value based on the second loss function of the value network, and optimizing the network parameters of the value network based on the predicted reward loss value to obtain the target value network; S305, determining an action loss value based on the third loss function of the policy network, the state at the first historical moment, and the predicted state, and optimizing the network parameters of the policy network based on the action loss value to obtain a target policy network; The target soft Q network, target value network and target strategy network constitute the trained flexible Actor-Critic model.

[0034] It should be noted that the execution order of steps S303, S304 and S305 is not limited to sequential execution, and can also be executed in parallel or in other sequential executions. For example, steps S304, S303, S305 are executed in sequence, etc., and it is only necessary to ensure that the parameters in the soft Q network, the value network and the policy network are all trained and optimized.

[0035] In some embodiments of the present invention, the training stop condition of the soft Q network includes but is not limited to: the number of training iterations reaches a preset number, or the training error is less than a preset error, or the error change trend is less than a preset change trend. That is, when the number of training iterations of the network parameters of the soft Q network reaches a preset number, or the training error is less than a preset error, or the error change trend is less than a preset change trend, the network parameters of the soft Q network are stopped from being optimized to obtain a target soft Q network.

[0036] Similarly, the training stopping conditions for the policy network and the value network are the same as those for the soft Q network, and will not be described in detail here.

[0037] In a specific embodiment of the present invention, the optimal strategy of the policy network is:

[0038]

[0039] In the formula, is the optimal strategy; The status is , the action is Rewards when is the entropy discount factor; The status is Entropy of time; is the policy function of the policy network; To find the expectation of cumulative reward and maximum entropy; is the maximum value operator.

[0040] From the above formula of the optimal strategy, it can be seen that the embodiment of the present invention takes into account the cumulative reward and the entropy value of the action during the strategy optimization process, and has the dual goals of maximizing the reward and maximizing the entropy (exploration). In other words, the present invention introduces the entropy regularization term to make the strategy more random when making decisions, thereby improving the exploration ability, and further improving the accuracy of the determined harmonic injection parameters and improving the vibration reduction and noise reduction efficiency.

[0041] In a specific embodiment of the present invention, the first loss function is:

[0042] The second loss function is:

[0043] The third loss function is:

[0044] In the formula, is the first loss function; is the predicted value of the soft Q network; is the true value of the soft Q network; is the second loss function; is the predicted value of the value network; is the true value of the value network; is the third loss function; is the coefficient; is the output value of the policy network.

[0045] When training the flexible Actor-Critic model, the loss value is calculated according to the first loss function, the second loss function and the third loss function, and the policy network, the soft Q network and the value network are back-propagated to update / optimize the network parameters until convergence, thereby completing the training of the flexible Actor-Critic model.

[0046] In some embodiments of the present invention, after the flexible Actor-Critic model is trained, Figure 4 As shown, in step S102, the real-time noise is input into the trained flexible Actor-Critic model to obtain the target harmonic injection number, target phase and target amplitude of the harmonic injection device, including: S401, determining a real-time state of the motor based on the real-time noise; the real-time state includes the real-time amplitude of the motor, the real-time noise frequency, the noise phase constant and the real-time motor frequency; S402, processing the real-time state based on the target strategy network, obtaining the real-time target decision action, and controlling the harmonic injection device to execute the target decision action; Among them, the target decision action includes the target harmonic injection number, target phase and target amplitude.

[0047] As the real-time noise changes, the target decision action also changes accordingly, achieving dynamic noise reduction of real-time noise and ensuring the vibration and noise reduction effect.

[0048] It should be noted that during the training of the flexible Actor-Critic model, the optimization algorithm for updating / optimizing the network parameters in the soft Q network, value network, and policy network is the stochastic gradient descent method.

[0049] The embodiment of the present invention can further improve the training speed of the flexible Actor-Critic model by setting the optimization algorithm to the stochastic gradient descent method, thereby further improving the vibration reduction and noise reduction efficiency.

[0050] To sum up, the method for active vibration and noise reduction of a motor proposed in an embodiment of the present invention takes a harmonic injection device as an intelligent body, outputs specific harmonic orders, phases and amplitudes according to the noise of the motor to weaken the electromagnetic noise generated by the motor, thereby realizing active updating of the injected harmonics and improving the efficiency of vibration and noise reduction.

[0051] In order to better implement the motor active vibration reduction and noise reduction method in the embodiment of the present invention, based on the motor active vibration reduction and noise reduction method, the embodiment of the present invention also provides a motor active vibration reduction and noise reduction system, such as Figure 5 As shown, the motor active vibration and noise reduction system 500 includes: A real-time noise acquisition unit 501 is used to acquire the real-time noise of the motor; A harmonic injection device parameter determination unit 502 is used to input real-time noise into the trained flexible Actor-Critic model to obtain a target harmonic injection number, target phase and target amplitude of the harmonic injection device; The vibration reduction and noise reduction unit 503 is used to generate a harmonic current for offsetting the radial electromagnetic force of the motor based on a target harmonic injection order, a target phase and a target amplitude.

[0052] The motor active vibration reduction and noise reduction system 500 provided in the above embodiment can implement the technical solution described in the above motor active vibration reduction and noise reduction method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above motor active vibration reduction and noise reduction method embodiment, which will not be repeated here.

[0053] like Figure 6 As shown, the present invention also provides a motor active vibration reduction and noise reduction device 600. The motor active vibration reduction and noise reduction device 600 includes a processor 601, a memory 602 and a display 603. Figure 6 Only some components of the motor active vibration and noise reduction device 600 are shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0054] In some embodiments, the processor 601 may be a central processing unit (CPU), a microprocessor or other data processing chip, and is used to run program codes or process data stored in the memory 602, such as the motor active vibration reduction and noise reduction method of the present invention.

[0055] In some embodiments of the present invention, the processor 601 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 601 may be local or remote. In some embodiments, the processor 601 may be implemented in a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

[0056] In some embodiments, the memory 602 may be an internal storage unit of the motor active vibration reduction and noise reduction device 600, such as a hard disk or memory of the motor active vibration reduction and noise reduction device 600. In other embodiments, the memory 602 may also be an external storage device of the motor active vibration reduction and noise reduction device 600, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the motor active vibration reduction and noise reduction device 600.

[0057] Furthermore, the memory 602 may include both an internal storage unit and an external storage device of the motor active vibration reduction and noise reduction device 600. The memory 602 is used to store application software and various data installed in the motor active vibration reduction and noise reduction device 600.

[0058] In some embodiments, the display 603 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 603 is used to display information of the motor active vibration reduction and noise reduction device 600 and to display a visual user interface. The components 601-603 of the motor active vibration reduction and noise reduction device 600 communicate with each other through a system bus.

[0059] In some embodiments of the present invention, when the processor 601 executes the motor active vibration and noise reduction program in the memory 602, the following steps may be implemented: Get the real-time noise of the motor; The real-time noise is input into the trained flexible Actor-Critic model to obtain the target harmonic injection number, target phase and target amplitude of the harmonic injection device; A harmonic current is generated to counteract the radial electromagnetic force of the motor based on a target harmonic injection order, a target phase, and a target amplitude.

[0060] It should be understood that: when the processor 601 executes the motor active vibration and noise reduction program in the memory 602, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

[0061] Furthermore, the embodiment of the present invention does not specifically limit the type of the motor active vibration reduction and noise reduction device 600 mentioned. The motor active vibration reduction and noise reduction device 600 may be a portable motor active vibration reduction and noise reduction device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable motor active vibration reduction and noise reduction devices include but are not limited to portable motor active vibration reduction and noise reduction devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable motor active vibration reduction and noise reduction device may also be other portable motor active vibration reduction and noise reduction devices. It should also be understood that in some other embodiments of the present invention, the motor active vibration reduction and noise reduction device 600 may not be a portable motor active vibration reduction and noise reduction device, but a desktop computer with a touch-sensitive surface (such as a touch panel).

[0062] Correspondingly, an embodiment of the present invention also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, the steps or functions of the motor active vibration and noise reduction method provided in the above-mentioned method embodiments can be implemented.

[0063] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0064] The above is a detailed introduction to the method, system, device and storage medium for active vibration and noise reduction of a motor provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for active vibration and noise reduction of a motor, characterized in that: include: Get the real-time noise of the motor; Inputting the real-time noise into the trained flexible Actor-Critic model to obtain the target harmonic injection order, target phase and target amplitude of the harmonic injection device; A harmonic current is generated to counteract the radial electromagnetic force of the motor based on the target harmonic injection order, the target phase, and the target amplitude.

2. The method for active vibration and noise reduction of a motor according to claim 1, characterized in that: The flexible Actor-Critic model includes a soft Q network, a value network and a strategy network; Before inputting the real-time noise into the trained flexible Actor-Critic model, the method further includes: Acquire a training sample; the training data in the training sample is a five-tuple data, and the five-tuple data includes a state at a first historical moment, an action at the first historical moment, a reward value at the first historical moment, a cumulative reward value at the first historical moment, and a state at a second historical moment; the second historical moment is a moment next to the first historical moment; Inputting the training data into the soft Q network, the value network and the strategy network respectively, and obtaining the predicted reward value, the predicted cumulative reward value and the predicted action respectively; Determining the reward value at the first historical moment and the reward loss value of the predicted reward value based on the first loss function of the soft Q network, and optimizing the network parameters of the soft Q network based on the reward loss value to obtain a target soft Q network; Determine the cumulative reward value at the first historical moment and the predicted reward loss value of the predicted cumulative reward value based on the second loss function of the value network, and optimize the network parameters of the value network based on the predicted reward loss value to obtain a target value network; Determine an action loss value based on a third loss function of the policy network, the state at the first historical moment, and the predicted state, and optimize a network parameter of the policy network based on the action loss value to obtain a target policy network; The target soft Q network, the target value network and the target strategy network constitute a trained flexible Actor-Critic model.

3. The method for active vibration and noise reduction of a motor according to claim 2, characterized in that: When the number of training iterations of the network parameters of the soft Q network reaches a preset number, or the training error is less than a preset error, or the error change trend is less than a preset change trend, the optimization of the network parameters of the soft Q network is stopped to obtain the target soft Q network.

4. The method for active vibration and noise reduction of a motor according to claim 2, characterized in that: The real-time noise is input into the trained flexible Actor-Critic model to obtain the target harmonic injection number, target phase and target amplitude of the harmonic injection device, including: Determine the real-time state of the motor based on the real-time noise; the real-time state includes the real-time amplitude, real-time noise frequency, noise phase constant and real-time motor frequency of the motor; Processing the real-time state based on the target strategy network to obtain a real-time target decision action, and controlling the harmonic injection device to execute the target decision action; Wherein, the target decision action includes the target harmonic injection number, the target phase and the target amplitude.

5. The method for active vibration and noise reduction of a motor according to claim 2, characterized in that: The optimal strategy of the policy network is: In the formula, is the optimal strategy; The status is , the action is Rewards when is the entropy discount factor; The status is Entropy of time; is the policy function of the policy network; To find the expectation of cumulative reward and maximum entropy; is the maximum value operator.

6. The method for active vibration and noise reduction of a motor according to claim 2, characterized in that: The first loss function is: The second loss function is: The third loss function is: In the formula, is the first loss function; is the predicted value of the soft Q network; is the true value of the soft Q network; is the second loss function; is the predicted value of the value network; is the true value of the value network; is the third loss function; is the coefficient; is the output value of the policy network.

7. The method for active vibration and noise reduction of a motor according to claim 2, characterized in that: The optimization algorithm during training of the soft Q network, the value network and the policy network is stochastic gradient descent.

8. A motor active vibration and noise reduction system, characterized in that: include: A real-time noise acquisition unit, used for acquiring the real-time noise of the motor; A harmonic injection device parameter determination unit, used for inputting the real-time noise into a trained flexible Actor-Critic model to obtain a target harmonic injection number, target phase and target amplitude of the harmonic injection device; The vibration reduction and noise reduction unit is used to generate a harmonic current to offset the radial electromagnetic force of the motor based on the target harmonic injection order, the target phase and the target amplitude.

9. A motor active vibration reduction and noise reduction device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps of the method for active vibration and noise reduction of a motor as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps of the motor active vibration and noise reduction method described in any one of claims 1 to 7.

Images