WO2023124921A1

WO2023124921A1 - Torque estimation method and apparatus for permanent magnet synchronous motor, and device and storage medium

Info

Publication number: WO2023124921A1
Application number: PCT/CN2022/138178
Authority: WO
Inventors: 梁嘉宁; 孙天夫
Original assignee: 深圳先进技术研究院
Priority date: 2021-12-31
Filing date: 2022-12-09
Publication date: 2023-07-06
Also published as: CN116418260A

Abstract

Disclosed in the present invention are a torque estimation method and apparatus for a permanent magnet synchronous motor, and a device and a storage medium. The method comprises: acquiring a motor operation parameter in real time; and inputting the motor operation parameter into a pre-trained torque estimation model to obtain a final estimated torque value, wherein the torque estimation model comprises an Elman neural network model and a motor torque mathematical estimation model, the Elman neural network model performs prediction according to the motor operation parameter to obtain a first estimated torque value, the motor torque mathematical estimation model performs prediction according to the motor operation parameter to obtain a second estimated torque value, calculation is performed on the first estimated torque value and the second estimated torque value according to a weight parameter and a bias parameter, so as to obtain the final estimated torque value, and the weight parameter and the bias parameter are obtained by means of training when the torque estimation model is trained. In the present invention, a hybrid model is formed by using an Elman model and a mathematical model, thereby further improving the calculation speed and response speed, and also improving the prediction accuracy.

Description

Torque estimation method, device, equipment and storage medium of permanent magnet synchronous motor

technical field

The present application relates to the technical field of motor control, in particular to a torque estimation method, device, equipment and storage medium of a permanent magnet synchronous motor.

Background technique

Permanent magnet synchronous motors have the advantages of high power density, high efficiency, and high torque density, and have been widely used in robotics, industrial automation, and electric vehicles. However, because the IPMSM is affected by factors such as the nonlinearity, volatility, and operational uncertainty of the motor parameters, it cannot accurately achieve high-precision control of the motor torque. Therefore, in the traditional motor torque control strategy, the control accuracy of the motor electromagnetic torque is relatively low, which degrades the overall performance of the system.

In order to improve the torque estimation accuracy of permanent magnet synchronous motors, scholars at home and abroad have developed many schemes, which can be divided into two types: offline and online. For offline solutions, it is usually obtained by looking up a table. The table lookup method is simulated based on off-line experiments or finite element analysis. The method based on the table lookup method is simple and robust, but it is very time-consuming to implement and requires a large number of hardware resources, occupy a large amount of storage space, and it is impractical to test on each machine, these factors greatly reduce the efficiency and application range of torque estimation. For online methods, the extended Kalman filter algorithm is usually used. The extended Kalman filter algorithm (EKF) is an algorithm derived by scholars based on the fact that the Kalman (KF) filter algorithm cannot effectively track nonlinear systems. It is an approximation to nonlinear systems. The processing method has a good estimation effect on the nonlinear characteristics of the permanent magnet synchronous motor, and has strong anti-interference performance, but the calculation amount is relatively large.

Contents of the invention

The present application provides a torque estimation method, device, equipment and storage medium of a permanent magnet synchronous motor, so as to solve the problems of large calculation amount and low accuracy of the existing torque estimation.

In order to solve the above technical problems, a technical solution adopted by this application is to provide a torque estimation method of a permanent magnet synchronous motor, including: obtaining the motor operating parameters in real time; inputting the motor operating parameters into the pre-trained torque estimation method Measure the model to get the final torque estimation value, the torque estimation model includes the Elman neural network model and the motor torque mathematical estimation model, the Elman neural network model obtains the first torque estimation value according to the motor operation parameter prediction, the motor rotation The moment mathematical estimation model obtains the second torque estimation value according to the motor operation parameter prediction, the first torque estimation value and the second torque estimation value are calculated according to the weight parameter and the bias parameter to obtain the final torque estimation value, The weight parameters and bias parameters are trained when training the torque estimation model.

As a further improvement of the present application, the real-time acquisition of motor operating parameters includes: real-time acquisition of d-axis current, q-axis current, electrical angle parameters and motor speed of the motor based on a preset acquisition device.

As a further improvement of this application, the calculation formula of the final estimated value is:

in,

Represents the output of the torque estimation model, f(x _n ) represents the output of the Elman neural network model, E(T) represents the output of the torque mathematical model, α is the weight parameter, β is the bias parameter, α and β are in rotation Obtained during the training process of the moment estimation model.

As a further improvement of the present application, the step of pre-training the torque estimation model includes: constructing the torque estimation model to be trained, the weight parameters and bias parameters are initially set to default values; obtaining training sample input parameters and training The actual torque value corresponding to the sample input parameters; perform feature engineering on the training sample input parameters to obtain the sample feature vector; input the sample feature vector into the torque estimation model to obtain the sample torque estimation value; based on the pre-built loss function , the sample torque estimation value and the actual torque value are backpropagated to update the torque estimation model; the above training process is repeated until the torque estimation model reaches a preset accuracy or the number of iterations reaches a preset number of times.

As a further improvement of the present application, after obtaining the final estimated torque value, the method further includes: when the currently running control system is a torque control system, performing closed-loop control on the motor torque according to the final estimated torque value.

As a further improvement of the present application, the motor torque is closed-loop controlled according to the final torque estimation value, including: obtaining the calculation time consumed by calculating the final torque estimation value and the processing time consumed by the control system operation; if the current operation If the processor of the device is a single-core processor, the motor control cycle is set as the sum of calculation time and processing time, and according to the motor control cycle, the motor torque is calculated with the final torque estimate obtained in the motor control cycle Closed-loop control; if the processor of the currently running device is a multi-core processor, set the motor control cycle to the larger value of the calculation time and processing time, and according to the motor control cycle, use the final torque obtained in the motor control cycle The estimated value performs closed-loop control of the motor torque.

As a further improvement of the present application, after obtaining the final estimated torque value, it further includes: when the currently running control system is a non-torque control system, outputting the final estimated torque value as observation data.

In order to solve the above technical problems, another technical solution adopted by the present application is to provide a torque estimation device for a permanent magnet synchronous motor, including: an acquisition module for acquiring motor operating parameters in real time; an estimation module for The motor operating parameters are input into the pre-trained torque estimation model to obtain the final torque estimation value. The torque estimation model includes the Elman neural network model and the motor torque mathematical estimation model. The Elman neural network model is based on the motor operating parameters The first torque estimation value is obtained by prediction, and the motor torque mathematical estimation model predicts and obtains the second torque estimation value according to the motor operating parameters. The first torque estimation value and the second torque estimation value are calculated according to the weight parameters and The bias parameter is calculated to obtain the final torque estimation value, and the weight parameter and bias parameter are trained during the training of the torque estimation model.

In order to solve the above technical problems, another technical solution adopted by the present application is to provide a computer device, the computer device includes a processor, a memory coupled to the processor, and program instructions are stored in the memory, so When the program instructions are executed by the processor, the processor is made to execute the steps of the above neural network-based torque estimation method.

In order to solve the above-mentioned technical problems, another technical solution adopted by the present application is to provide a storage medium storing program instructions capable of realizing the above-mentioned neural network-based torque estimation method.

The beneficial effects of the present application are: the torque estimation method of the permanent magnet synchronous motor of the present application is based on the torque estimation model constructed jointly by the Elman neural network model and the motor torque mathematical estimation model, and then utilizes the torque The estimation model estimates the motor operating parameters collected in real time to obtain the final torque estimation value. Through the fusion of the Elman neural network and the motor mathematical model algorithm, the torque estimation model avoids harmonic interference in the motor operation, etc. Influence, optimize model performance, improve model prediction stability and accuracy.

Description of drawings

1 is a schematic flow chart of a torque estimation method for a permanent magnet synchronous motor according to a first embodiment of the present invention;

Fig. 2 is the structural representation of Elman neural network;

3 is a schematic diagram of functional modules of a torque estimation device for a permanent magnet synchronous motor according to an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of a computer device according to an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of a storage medium according to an embodiment of the present invention.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

The terms "first", "second", and "third" in this application are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features. Thus, features defined as "first", "second", and "third" may explicitly or implicitly include at least one of these features. In the description of the present application, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present application are only used to explain the relative positional relationship between the various components in a certain posture (as shown in the drawings) , sports conditions, etc., if the specific posture changes, the directional indication also changes accordingly. Furthermore, the terms "include" and "have", as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes unlisted steps or units, or optionally further includes For other steps or units inherent in these processes, methods, products or apparatuses.

Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The occurrences of this phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is understood explicitly and implicitly by those skilled in the art that the embodiments described herein can be combined with other embodiments.

FIG. 1 is a schematic flowchart of a torque estimation method for a permanent magnet synchronous motor according to a first embodiment of the present invention. It should be noted that the method of the present invention is not limited to the flow sequence shown in FIG. 1 if substantially the same result is obtained. As shown in Figure 1, the method includes steps:

Step S101: Acquiring motor operating parameters in real time.

It should be noted that this embodiment is aimed at real-time and online control of the torque of the motor during the real-time operation of the motor.

Specifically, during the operation of the motor, the motor operating parameters of the motor are collected in real time through the device.

The real-time acquisition of motor operating parameters includes: real-time acquisition of d-axis current, q-axis current, electrical angle parameters, and motor speed of the motor based on a preset acquisition device.

In this embodiment, by obtaining the motor speed, the speed factor of the motor is further considered, so that the prediction results obtained according to the above parameters are more accurate than those obtained only through the d-axis current, q-axis current and electrical angle parameters.

Step S102: Input the motor operating parameters into the pre-trained torque estimation model to obtain the final torque estimation value. The torque estimation model includes the Elman neural network model and the motor torque mathematical estimation model. The Elman neural network model The first torque estimation value is obtained according to the motor operation parameter prediction, and the motor torque mathematical estimation model is obtained according to the motor operation parameter prediction to obtain the second torque estimation value, the first torque estimation value and the second torque estimation value The final torque estimation value is calculated according to the weight parameter and the bias parameter, and the weight parameter and the bias parameter are trained when training the torque estimation model.

It should be noted that, in the actual application of the motor torque mathematical estimation model, there is a large error between the output torque and the actual torque due to nonlinear factors such as system parameter changes, magnet saturation, and harmonic disturbances during motor operation. Therefore, in this embodiment, the prediction result of the motor torque mathematical estimation model is integrated with the prediction result of the Elman neural network model, thereby improving the estimation stability and accuracy.

It should be noted that please refer to Figure 2. Figure 2 shows the structural diagram of the Elman neural network. The Elman neural network is a typical dynamic recursive neural network. It is based on the basic structure of the BP network and adds A succession layer, as a one-step delay operator, achieves the purpose of memory, so that the system has the ability to adapt to time-varying characteristics, and enhances the global stability of the network. It has stronger computing power than the feed-forward neural network. Its mathematical expression is:

y(k)=g(w ₃ x(k));

x(k)=f(w ₁ x _c (k)+w ₂ (u(k-1)));

_xc (k)=x(k-1);

Among them, y is the m-dimensional output node vector; x is the n-dimensional intermediate layer node unit vector; u is the r-dimensional input vector; x _c is the n-dimensional feedback state vector; w ₃ is the connection weight from the intermediate layer to the output layer; w ₂ is the connection weight from the input layer to the middle layer; w ₁ is the connection weight from the receiving layer to the middle layer; g() is the transfer function of the output neuron, which is the linear combination of the output of the middle layer; f() is the weight of the middle layer neuron The transfer function, often using the S function.

Specifically, the formula for calculating the final estimated value is:

in,

Among them, the motor torque mathematical estimation model is expressed as:

Among them, U represents the voltage, L represents the inductance, i represents the current, d represents the d-axis, q represents the q-axis, R is the motor stator coil, ψ is the motor flux linkage, p is the number of pole pairs of the motor, T _e is the second torque Estimated value, w is the angular velocity of the motor.

Further, the steps of pre-training the torque estimation model include:

1. Construct the torque estimation model to be trained, and the weight parameters and bias parameters are initially set to default values.

It should be noted that default values of weight parameters and bias parameters are preset.

2. Obtain the training sample input parameters and the actual torque value corresponding to the training sample input parameters.

Specifically, the sample input parameters and the actual torque value corresponding to each sample input parameter are collected during the actual operation of the motor. In , due to the mechanical response delay, that is, the torque signal is later than the motor modulation control current signal for a certain period, it is necessary to calibrate and match the collected data.

3. Perform feature engineering on the input parameters of the training samples to obtain the sample feature vectors.

4. Input the sample feature vector into the torque estimation model to obtain the sample torque estimation value.

5. Backpropagating the torque estimation model based on the pre-built loss function, the sample torque estimation value and the actual torque value.

The above training process is repeated until the torque estimation model reaches a preset accuracy or the number of iterations reaches a preset number.

In this embodiment, by continuously screening and adjusting the network model structure during the training process, including the number of network neurons, the number of hidden layers, the learning rate, and the number of training times, the torque estimation model can reach a preset accuracy or The number of iterations reaches the preset number, and a trained torque estimation model is obtained.

Further, in some embodiments, the final torque estimation value can also be used to perform torque control on the motor, therefore, after obtaining the final torque estimation value, it also includes:

When the currently running control system is a torque control system, the motor torque is closed-loop controlled according to the final torque estimation value.

Specifically, after embedding the above-mentioned Elman neural network model and the motor torque mathematical estimation model into the motor control program, if the current control system is a torque control system, the d Axis current, q-axis current and electrical angle parameters, and then estimated by d-axis current, q-axis current and electrical angle parameters to obtain the final torque estimation value, and then perform closed-loop control on the torque according to the final torque estimation value .

It should be noted that the difference in the number of processor cores of the current running device of the motor control program will make the execution of the motor control different. Therefore, the closed-loop control of the motor torque is performed according to the final torque estimation value, including:

1. Obtain the calculation time consumed for calculating the final torque estimation value and the processing time consumed for the operation of the control system.

Among them, the calculation time refers to the time consumed by the Elman neural network model and the motor torque mathematical estimation model from obtaining the motor operating parameters to obtaining the final torque estimation value according to the motor operating parameters, and the processing time refers to the time consumed by the operation of the control system time.

2. If the processor of the currently running device is a single-core processor, set the motor control cycle to the sum of the calculation time and processing time, and according to the motor control cycle, use the final torque estimate obtained in the motor control cycle Closed-loop control of motor torque.

3. If the processor of the currently running device is a multi-core processor, set the motor control cycle to the larger value of the calculation time and processing time, and according to the motor control cycle, use the final torque obtained in the motor control cycle to estimate The measured value performs closed-loop control on the motor torque.

Specifically, when the current device is a single-core processor, the Elman neural network model and the motor torque mathematical estimation model are in a serial relationship with the motor control program. Therefore, it is necessary to run the Elman neural network after the motor control program is completed. model and motor torque mathematical estimation model, at this time, the motor control cycle is set to the sum of calculation time and processing time, for example, the motor control program can be completed in about 25us, and this Elman neural network model and motor The torque mathematical estimation model takes 85us to calculate the final torque estimation value, so the motor control cycle is set to 150us.

When the current device is a multi-core processor, the Elman neural network model and the motor torque mathematical estimation model are in parallel with the motor control program. Therefore, the motor control program and the Elman neural network model and the motor torque mathematical estimation model can be simultaneously Execution, at this time, the motor control cycle is set to the larger value of the calculation time and processing time, for example, the motor control program can be completed in about 25us, and this time the Elman neural network model and the motor torque mathematical estimation model It takes 85us to calculate the final torque estimation value, so the motor control cycle is set to 100us.

It can be seen that the single-thread processing platform needs longer calculation time, and the motor control performance is slightly reduced, while the multi-thread processing platform has better motor control performance.

Further, after the weighted calculation of the first torque estimated value and the second torque estimated value to obtain the final torque estimated value, further includes:

When the currently operating control system is a non-torque control system, the final estimated torque value is output as observation data.

The torque estimation method of the permanent magnet synchronous motor of the first embodiment of the present invention is based on the torque estimation model constructed jointly by the Elman neural network model and the motor torque mathematical estimation model, and then using the torque estimation model Estimating the motor operating parameters collected in real time to obtain the final torque estimation value, through the fusion of the Elman neural network and the motor mathematical model algorithm, it avoids the influence of the torque estimation model on the harmonic interference in the motor operation, and optimizes The performance of the model is improved, and the stability and accuracy of the model prediction are improved.

FIG. 3 is a schematic diagram of functional modules of a torque estimation device for a permanent magnet synchronous motor according to an embodiment of the present invention. As shown in FIG. 3 , the torque estimation device 30 of the permanent magnet synchronous motor includes an acquisition module 31 and an estimation module 32 .

Obtaining module 31, used for obtaining motor operating parameters in real time;

The estimation module 32 is used to input the motor operating parameters into the pre-trained torque estimation model to obtain the final torque estimation value. The torque estimation model includes an Elman neural network model and a motor torque mathematical estimation model, The Elman neural network model obtains the first torque estimation value according to the motor operating parameter prediction, and the motor torque mathematical estimation model obtains the second torque estimation value according to the motor operating parameter prediction, the first torque estimation value and the second torque estimation value The moment estimated value is calculated according to the weight parameter and the offset parameter to obtain the final torque estimated value, and the weight parameter and the offset parameter are trained when training the torque estimation model.

Optionally, the acquisition module 31 executes the operation of acquiring the operating parameters of the motor in real time, specifically including: acquiring the d-axis current, q-axis current, electrical angle parameters and motor speed of the motor in real time based on a preset acquisition device.

Optionally, the formula for calculating the final estimated value is:

in,

Optionally, it also includes a training module, which is used to perform the operation of pre-training the torque estimation model, specifically including: constructing the torque estimation model to be trained, and initially setting the weight parameters and bias parameters to default values; obtaining The training sample input parameters and the actual torque value corresponding to the training sample input parameters; perform feature engineering on the training sample input parameters to obtain the sample feature vector; input the sample feature vector to the torque estimation model to obtain the sample torque estimation value ;Update the torque estimation model based on the pre-built loss function, sample torque estimation value and actual torque value backpropagation; repeat the above training process until the torque estimation model reaches the preset accuracy or the number of iterations reaches the preset up to the number of times.

Optionally, after the estimation module 32 executes the operation of obtaining the final torque estimation value, it is also used for: when the currently running control system is a torque control system, perform a closed-loop operation on the motor torque according to the final torque estimation value control.

Optionally, the estimation module 32 executes the operation of performing closed-loop control on the motor torque according to the final torque estimation value, specifically including: obtaining the calculation time consumed by calculating the final torque estimation value and the processing consumed by the control system operation time; if the processor of the currently running device is a single-core processor, set the motor control cycle to the sum of the calculation time and processing time, and according to the motor control cycle, use the final torque estimate obtained in the motor control cycle Perform closed-loop control on the motor torque; if the processor of the currently running device is a multi-core processor, set the motor control cycle to the larger value of the calculation time and processing time, and according to the motor control cycle, take the motor control cycle The obtained final torque estimate performs closed-loop control of the motor torque.

Optionally, after the estimation module 32 executes the operation of obtaining the final torque estimation value, it is further configured to: when the currently running control system is a non-torque control system, output the final torque estimation value as observation data.

For other details of the implementation of the technical solution of each module in the torque estimation device of the permanent magnet synchronous motor in the above embodiment, please refer to the description in the torque estimation method of the permanent magnet synchronous motor in the above embodiment, and will not repeat them here .

It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. For the same and similar parts in each embodiment, refer to each other, that is, Can. As for the device-type embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for related parts, please refer to part of the description of the method embodiments.

Please refer to FIG. 4 , which is a schematic structural diagram of a computer device according to an embodiment of the present invention. As shown in FIG. 4, the computer device 60 includes a processor 61 and a memory 62 coupled to the processor 61. Program instructions are stored in the memory 32. When the program instructions are executed by the processor 61, the processor 61 performs any of the above-mentioned operations. The steps of the method for estimating the torque of the permanent magnet synchronous motor described in the embodiment.

Wherein, the processor 61 may also be called a CPU (Central Processing Unit, central processing unit). The processor 61 may be an integrated circuit chip with signal processing capabilities. The processor 61 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components . A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.

Referring to FIG. 5 , FIG. 5 is a schematic structural diagram of a storage medium according to an embodiment of the present invention. The storage medium in the embodiment of the present invention stores program instructions 71 capable of realizing all the above-mentioned methods, wherein the program instructions 71 can be stored in the above-mentioned storage medium in the form of software products, including several instructions to make a computer device (which can It is a personal computer, a server, or a network device, etc.) or a processor (processor) that executes all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc., which can store program codes. , or computer equipment such as computers, servers, mobile phones, and tablets.

In the several embodiments provided in this application, it should be understood that the disclosed computer equipment, devices and methods may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated. to another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units. The above is only the implementation mode of this application, and does not limit the scope of patents of this application. Any equivalent structure or equivalent process conversion made by using the contents of this application specification and drawings, or directly or indirectly used in other related technical fields, All are included in the scope of patent protection of the present application in the same way.

Claims

A method for estimating torque of a permanent magnet synchronous motor, characterized in that it comprises:

Real-time acquisition of motor operating parameters;

Input the motor operating parameters into the pre-trained torque estimation model to obtain the final torque estimation value. The torque estimation model includes an Elman neural network model and a motor torque mathematical estimation model. The Elman The neural network model predicts and obtains a first torque estimated value according to the motor operating parameter, and the motor torque mathematical estimation model obtains a second torque estimated value according to the motor operating parameter prediction, and the first torque The estimated value and the second torque estimated value are calculated according to weight parameters and bias parameters to obtain the final torque estimated value, and the weight parameters and bias parameters are trained when training the torque estimation model get.
The method for estimating torque of a permanent magnet synchronous motor according to claim 1, wherein the real-time acquisition of motor operating parameters comprises:

The d-axis current, q-axis current, electrical angle parameters and motor speed of the motor are obtained in real time based on the preset acquisition device.
The method for estimating torque of a permanent magnet synchronous motor according to claim 1, wherein the formula for calculating the final estimated value is:

in,
Represents the output of the torque estimation model, f(x n ) represents the output of the Elman neural network model, E(T) represents the output of the torque mathematical model, α is a weight parameter, and β is a bias parameter , α and β are obtained during the training process of the torque estimation model.
The method for estimating torque of a permanent magnet synchronous motor according to claim 1, wherein the step of pre-training the torque estimating model includes:

Constructing the torque estimation model to be trained, the weight parameter and the bias parameter are initially set to default values;

Obtain training sample input parameters and actual torque values corresponding to the training sample input parameters;

performing feature engineering on the training sample input parameters to obtain sample feature vectors;

The sample feature vector is input to the torque estimation model to obtain a sample torque estimate;

back-propagating to update the torque estimate model based on a pre-built loss function, the sample torque estimate and the actual torque value;

The above training process is repeated until the torque estimation model reaches a preset accuracy or the number of iterations reaches a preset number.
The method for estimating torque of a permanent magnet synchronous motor according to claim 1, wherein, after obtaining the final estimated torque value, further comprising:

When the currently running control system is a torque control system, the motor torque is closed-loop controlled according to the final estimated torque value.
The method for estimating torque of a permanent magnet synchronous motor according to claim 5, wherein the closed-loop control of the motor torque according to the final estimated torque value comprises:

obtaining computation time consumed in computing the final torque estimate and processing time consumed in operation of the control system;

If the processor of the currently running device is a single-core processor, set the motor control cycle as the sum of the calculation time and the processing time, and according to the motor control cycle, use the motor control cycle obtained in the motor control cycle The final torque estimate performs closed-loop control of the motor torque;

If the processor of the currently running device is a multi-core processor, the motor control cycle is set to the larger value of the calculation time and the processing time, and according to the motor control cycle, within the motor control cycle The acquired final torque estimate performs closed-loop control on the motor torque.
The method for estimating torque of a permanent magnet synchronous motor according to claim 1, wherein, after obtaining the final estimated torque value, further comprising:

When the currently operating control system is a non-torque control system, the final estimated torque value is output as observation data.
A torque estimation device for a permanent magnet synchronous motor, characterized in that it comprises:

An acquisition module is used to acquire motor operating parameters in real time;

The estimation module is used to input the motor operating parameters into the pre-trained torque estimation model to obtain the final torque estimation value, and the torque estimation model includes Elman neural network model and motor torque mathematical estimation A measurement model, the Elman neural network model is predicted to obtain a first torque estimation value according to the motor operation parameter, and the motor torque mathematical estimation model is obtained according to the motor operation parameter prediction to obtain a second torque estimation value, The first estimated torque value and the second estimated torque value are calculated according to weight parameters and bias parameters to obtain the final torque estimated value, and the weight parameters and bias parameters are used to train the torque It is obtained when training the moment estimation model.
A computer device, characterized in that the computer device includes a processor and a memory coupled to the processor, and program instructions are stored in the memory, and when the program instructions are executed by the processor, the The processor executes the steps of the method for estimating the torque of the permanent magnet synchronous motor according to any one of claims 1-7.
A storage medium, characterized by storing program instructions capable of realizing the torque estimation method for a permanent magnet synchronous motor according to any one of claims 1-7.