Speed sensorless control method and system for permanent magnet synchronous motor

Abstract

The invention belongs to the technical field of motor control, and particularly relates to a permanent magnet synchronous motor speed sensorless control method and system. A motor mathematical model is used as a basis, a rotating speed difference value between actual output of a motor and a mathematical model calculation value is used as output of a data set, and a neural network model is trained; the problem that an accurate motor mathematical model is difficult to establish due to factors such as nonlinearity, electromagnetism and mechanical inertia of a motor magnetic circuit is effectively solved, meanwhile, the problem that application of a neural network model trained by directly utilizing the actual rotating speed of the motor in a control system is limited is solved, and the neural network training burden and the model complexity are reduced.

Description

Technical Field

[0001] The present application belongs to the field of motor control technology, and specifically relates to a speed sensorless control method and system for a permanent magnet synchronous motor. Background Art

[0002] In the permanent magnet synchronous motor control system, a speed sensor is usually installed to achieve closed-loop control. However, in practical applications, factors such as manufacturing cost and installation space restrict the use of sensors, and mechanical failures of sensors and electromagnetic interference of detection signals will have adverse effects on the performance of the motor control system. Therefore, the research on sensorless control becomes very important.

[0003] During the operation of the motor, the motor parameters will change and be easily affected by harmonic disturbances due to the influence of the nonlinearity of the motor magnetic circuit, electromagnetic and mechanical inertia. This makes the direct use of the motor's mathematical model for sensorless control have problems such as inaccurate modeling, complex observer structure, and low observation accuracy, which affects the control accuracy of the motor and the operating performance of the motor system.

[0004] There are many advantages to using neural networks for sensorless control. Neural networks can effectively handle complex systems with high-dimensional and nonlinear characteristics through self-learning capabilities; they can adapt to the behavior dynamics of permanent magnet synchronous motors under different loads and operating conditions, effectively capture long-term dependencies in data, and model and observe time series data.

[0005] In the motor closed-loop control system, when using neural networks to obtain the speed information of permanent magnet synchronous motors, current and voltage are usually used as the input of the neural network, and the speed is directly used as the output for training. Since the speed output feedback will also directly affect the changes in input quantities such as current and voltage, when there is a significant deviation between the observed value and the actual value, it will cause drastic fluctuations in current and voltage, which will further deteriorate the subsequent observation results and affect the control performance of the motor system. At the same time, due to the high dynamics and complexity of data such as current and speed, it is difficult for neural networks to cover all possible changes. Even if the generalization ability of the neural network is enhanced by adding disturbances or expanding the data set, it is difficult to completely eliminate the imbalance of the motor system caused by the accumulation of observation errors. This requires extremely high accuracy when the neural network is applied in the motor control system, which increases the training burden. In addition, as a "black box" model, neural networks have problems in interpreting and understanding model behavior. The observed motor output does not conform to the motor operating characteristics, which also limits the application of neural networks in motor control systems. Summary of the invention

[0006] Based on the above problems, the present invention adopts the speed error as the training set output to train the neural network model, and improves the model based on the motor rotor acceleration limit. The technical solution is as follows: A speed sensorless control method for a permanent magnet synchronous motor comprises the following steps: S1. Establish a mathematical model of a permanent magnet synchronous motor to obtain the difference between the actual value of the motor speed and the value calculated by the mathematical model; S2. The three-phase stator current and voltage of the permanent magnet synchronous motor are used as the input of the neural network, and the calculated error of the motor speed is used as the output. The actual value of the motor speed can be obtained by adding the output to the speed calculation value of the mathematical model. Based on this, a motor speed observation model based on the LSTM neural network is constructed; S3. The motor speed observation of the LSTM neural network model is improved based on the motor rotor acceleration limitation, and the speed value observed by the neural network model is processed.

[0007] Preferably, in step S1, a mathematical model of the permanent magnet synchronous motor in the abc coordinate system is established, and the voltage equation is: (1); in, , , is the stator three-phase voltage, is the winding resistance, , , is the three-phase current, , , is the stator flux; transform the mathematical model in the abc coordinate system to the αβ coordinate system, and the transformation relationship between the two coordinate systems is: (2); After coordinate transformation, the mathematical model in the αβ coordinate system can be obtained: (3); (4) ; (5); in, , is the αβ axis voltage, , is the αβ axis current, and the differential operator Instead of d / dt, , is the αβ axis magnetic flux; is the motor electromagnetic torque, is the number of motor pole pairs; is the calculated motor speed; is the rotational inertia of the motor; is the motor load torque.

[0008] Preferably, in step S1, during the operation of the motor, there is an error between the actual speed value of the motor and the value calculated by the mathematical model, and the relationship between them is expressed as: (6); in, is the actual speed of the motor; is the motor speed error calculated using the motor mathematical model.

[0009] Preferably, in step S2, in order to make the current data meet the input requirements of the neural network, it is normalized, a normalization coefficient K is introduced, and K is set to: (7); Introduce the floating point relative error limit eps, let , the processed three-phase current can be expressed as: (8); The other training data are preprocessed by maximum and minimum normalization, and the preprocessed data set is divided into a training set and a test set. The training set is used to train the neural network, and the test set is used to evaluate the performance of the trained neural network.

[0010] Preferably, in step S2, the speed value observed by the neural network model is processed, and the model is improved based on the motor rotor acceleration limit. The relationship between the electromagnetic torque and the load torque difference is: (9); in, is the electromagnetic torque With load torque The maximum torque difference , the maximum rotor acceleration : (10); Therefore, the motor speed output by the observation model is adjusted to: (11); in, is the motor speed at the current moment; is the motor speed at the last moment; is the motor speed acceleration at the current moment; is the sampling period of the discrete model.

[0011] A speed sensorless control system for a permanent magnet synchronous motor, comprising a data acquisition module, a data processing module and an output module; Data acquisition module: obtain the three-phase stator current, voltage and motor speed parameters of the permanent magnet synchronous motor; Data processing module: Construct a motor speed observation model based on LSTM neural network, take the three-phase stator current and voltage of permanent magnet synchronous motor as the input of neural network, take the calculation error of motor speed as output, add the output to the speed calculation value of mathematical model to get the actual value of motor speed; improve the motor speed observation of LSTM neural network model based on motor rotor acceleration limit, and process the speed value observed by neural network model; Output module: output the results visually.

[0012] Compared with the prior art, the present invention has the following beneficial effects: 1) Based on the mathematical model of the motor, the speed difference between the actual output of the motor and the calculated value of the mathematical model is used as the output of the data set to train the neural network model. This effectively overcomes the problem of difficulty in establishing an accurate mathematical model of the motor caused by factors such as motor magnetic circuit nonlinearity, electromagnetic and mechanical inertia. At the same time, it also solves the problem of limited application of neural network models trained directly using the actual speed of the motor in control systems, reducing the burden of neural network training and model complexity.

[0013] 2) The motor operation characteristics are integrated into the neural network to improve the model output, which enhances the interpretability and adjustment capabilities of the neural network and effectively improves the speed observation accuracy and the stability of the motor operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is the flow chart of this application; Figure 2 A schematic diagram of an embodiment of a physical model of a permanent magnet synchronous motor in an abc coordinate system and an αβ coordinate system provided by the present invention; Figure 3 In order to apply the model trained with speed as output to the motor vector control system, the actual motor speed is compared with the observed value; Figure 4 A comparison chart of the actual motor speed and the observed value in order to apply the model trained with the speed error as the output quantity to the motor vector control system; Figure 5 Diagram of sensorless control system of permanent magnet synchronous motor; Figure 6 In order to apply the improved model to the motor vector control system, the actual motor speed is compared with the observed value as shown in the figure. DETAILED DESCRIPTION

[0015] The following will be combined with the embodiments of the present invention and the drawings of the specification 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] The purpose of the invention of this application is to provide a speed sensorless control scheme for a permanent magnet synchronous motor. Based on the mathematical model of the motor, the speed difference between the actual output of the motor and the calculated value of the mathematical model is used as the output of the data set to train the neural network model, which effectively overcomes the problem of difficulty in establishing an accurate mathematical model of the motor caused by factors such as the nonlinearity of the motor magnetic circuit, electromagnetic and mechanical inertia, and solves the problem of limited application of the neural network model directly trained using the actual speed of the motor in the control system, thereby reducing the burden of neural network training and the complexity of the model; the motor operating characteristics are integrated into the neural network, the model is improved, the interpretability and adjustment ability of the neural network are enhanced, and the speed observation accuracy and the stability of the motor operation are effectively improved.

[0017] Combination Figure 1 Come and see, Figure 1 The present invention provides a flow chart of a sensorless control method for a permanent magnet synchronous motor, which mainly includes the following steps: Step 1: Establish a mathematical model of the permanent magnet synchronous motor to obtain the difference between the actual value of the motor speed and the value calculated by the mathematical model (i.e., the error calculated by the mathematical model).

[0018] The mathematical model of the permanent magnet synchronous motor in the abc coordinate system is established, and the voltage equation is: (1); in, , , is the stator three-phase voltage, is the winding resistance, , , is the three-phase current, , , is the stator flux; transform the mathematical model in the abc coordinate system to the αβ coordinate system, and combine Figure 2 Come and see, Figure 2 The schematic diagram of an embodiment of the physical model of a permanent magnet synchronous motor in the abc coordinate system and the αβ coordinate system provided by the present invention shows that the transformation relationship between the two coordinate systems is: (2); After coordinate transformation, the mathematical model in the αβ coordinate system can be obtained: (3); (4) ; (5); in, , is the αβ axis voltage, , is the αβ axis current, and the differential operator Instead of d / dt, , is the αβ axis magnetic flux; is the motor electromagnetic torque, is the number of motor pole pairs; is the calculated motor speed; is the rotational inertia of the motor; is the motor load torque.

[0019] During the operation of the motor, due to the influence of factors such as magnetic circuit nonlinearity, electromagnetic and mechanical inertia, there is usually a certain error between the actual speed value of the motor and the value calculated by the mathematical model. The relationship can be expressed as: (6); in, is the actual speed of the motor; is the motor speed error calculated using the motor mathematical model.

[0020] Step 2: Using the LSTM neural network, the three-phase stator current and voltage of the permanent magnet synchronous motor are used as the input of the neural network, and the calculated error of the motor speed is used as the output. The actual value of the motor speed can be obtained by adding the output to the speed calculation value of the mathematical model. Based on this, a motor speed observation model based on the LSTM neural network is constructed.

[0021] LSTM neural network is a special recurrent neural network that is specifically used to process and observe time series data. Motor observation data such as current, voltage, and speed all change over time and contain time series information. LSTM neural network can effectively capture long-term dependencies in data and model and observe time series data. Using LSTM neural network to process motor observation data can provide strong support for motor speed observation.

[0022] In order to make the current data meet the input requirements of the neural network, it is normalized. The normalization coefficient K is introduced and set to: (7); In order to prevent zero division errors and avoid numerical instability, the floating point relative error limit eps is introduced. eps can be regarded as an infinitesimal quantity, usually ranging from 1×10-10 to 1×10-8. The processed three-phase current can be expressed as: (8); It can be seen from formula (8) that the current input to the neural network is adjusted to between [-1, 1] after normalization.

[0023] The other training data are preprocessed by maximum and minimum normalization, and the preprocessed data set is divided into a training set and a test set. The training set is used to train the neural network, and the test set is used to evaluate the performance of the trained neural network.

[0024] Since the motor speed value is relatively large and has large fluctuations, this will increase its training burden and the complexity of the model; while the speed error value is relatively small, using the speed error as the output for training significantly improves its accuracy when used in the motor control system, and also reduces the training burden and model complexity of the neural network. This is not only conducive to neural network training, but also can reduce the impact of excessive error fluctuations in motor control on input quantities such as current and voltage, which helps to maintain the stable operation of the system. The model trained using speed as the output is applied to the motor vector control system. The actual motor speed is compared with the observed value. Figure 3 As shown in the figure, the model trained by using the speed error as the output is applied to the motor vector control system to compare the actual motor speed with the observed value. Figure 4 As shown in Figure 2, the two models have the same parameter settings during training.

[0025] Step 3: Process the speed value observed by the neural network model and improve the model based on the motor rotor acceleration limit. The permanent magnet synchronous motor rotor acceleration can be obtained from formula (6): The relationship between the electromagnetic torque and the load torque difference is: (9); in, is the electromagnetic torque With load torque difference.

[0026] Considering that the motor has a maximum torque difference when running , so the rotor acceleration has a maximum value : (10); Therefore, the motor speed output by the observation model is adjusted to: (11); Among them, among them, is the motor speed at the current moment; is the motor speed at the last moment; is the motor speed acceleration at the current moment; is the sampling period of the discrete model. The sensorless control system of permanent magnet synchronous motor is shown in the figure Figure 5 The actual motor speed is compared with the observed value. Figure 6 shown.

[0027] A speed sensorless control system for a permanent magnet synchronous motor, comprising a data acquisition module, a data processing module and an output module; Data acquisition module: obtain the three-phase stator current, voltage and motor speed parameters of the permanent magnet synchronous motor; Data processing module: Construct a motor speed observation model based on LSTM neural network, take the three-phase stator current and voltage of permanent magnet synchronous motor as the input of neural network, take the calculation error of motor speed as output, add the output to the speed calculation value of mathematical model to get the actual value of motor speed; improve the motor speed observation of LSTM neural network model based on motor rotor acceleration limit, and process the speed value observed by neural network model; Output module: output the results visually.

[0028] The method embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0029] The system is constructed to run the method of the present application. Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0030] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A speed sensorless control method for a permanent magnet synchronous motor, characterized in that: The following steps are involved: S1. Establish a mathematical model of a permanent magnet synchronous motor to obtain the difference between the actual value of the motor speed and the value calculated by the mathematical model; S2. The three-phase stator current and voltage of the permanent magnet synchronous motor are used as the input of the neural network, and the calculation error of the motor speed is used as the output, and a motor speed observation model based on the LSTM neural network is constructed accordingly; S3. The motor speed observation of the LSTM neural network model is improved based on the motor rotor acceleration limitation, and the speed value observed by the neural network model is processed.

2. The speed sensorless control method of a permanent magnet synchronous motor according to claim 1, characterized in that: In step S1, a mathematical model of the permanent magnet synchronous motor in the abc coordinate system is established, and the voltage equation is: （1）； in, , , is the stator three-phase voltage, is the winding resistance, , , is the three-phase current, , , is the stator flux; transform the mathematical model in the abc coordinate system to the αβ coordinate system, and the transformation relationship between the two coordinate systems is: (2)； After coordinate transformation, the mathematical model in the αβ coordinate system can be obtained: (3)； (4) ； (5)； in, , is the αβ axis voltage, , is the αβ axis current, and the differential operator Instead of d / dt, , is the αβ axis magnetic flux; is the motor electromagnetic torque, is the number of motor pole pairs; is the calculated motor speed; is the rotational inertia of the motor; is the motor load torque.

3. The speed sensorless control method of a permanent magnet synchronous motor according to claim 1, characterized in that: In step S1, during the operation of the motor, there is an error between the actual speed value of the motor and the value calculated by the mathematical model, and the relationship between them is expressed as: (6)； in, is the actual speed of the motor; is the motor speed error calculated using the motor mathematical model.

4. The speed sensorless control method of a permanent magnet synchronous motor according to claim 1, characterized in that: In step S2, in order to make the current data meet the input requirements of the neural network, it is normalized, a normalization coefficient K is introduced, and K is set to: (7)； Introduce the floating point relative error limit eps, let , the processed three-phase current can be expressed as: (8)； The other training data are preprocessed by maximum and minimum normalization, and the preprocessed data set is divided into a training set and a test set. The training set is used to train the neural network, and the test set is used to evaluate the performance of the trained neural network.

5. The speed sensorless control method of a permanent magnet synchronous motor according to claim 1, characterized in that: In step S2, the speed value observed by the neural network model is processed, and the model is improved based on the motor rotor acceleration limit. The relationship between the electromagnetic torque and the load torque difference is: (9)； in, is the electromagnetic torque With load torque The maximum torque difference , the maximum rotor acceleration : (10)； Therefore, the motor speed output by the observation model is adjusted to: (11)； in, is the motor speed at the current moment; is the motor speed at the last moment; is the motor speed acceleration at the current moment; is the sampling period of the discrete model.

6. A speed sensorless control system for a permanent magnet synchronous motor, using the speed sensorless control method for a permanent magnet synchronous motor according to any one of claims 1 to 5, characterized in that: It includes data acquisition module, data processing module and output module; Data acquisition module: obtain the three-phase stator current, voltage and motor speed parameters of the permanent magnet synchronous motor; Data processing module: Construct a motor speed observation model based on LSTM neural network, take the three-phase stator current and voltage of permanent magnet synchronous motor as the input of neural network, take the calculation error of motor speed as output, add the output to the speed calculation value of mathematical model to get the actual value of motor speed; improve the motor speed observation of LSTM neural network model based on motor rotor acceleration limit, and process the speed value observed by neural network model; Output module: output the results visually.

Images