Method and device for identifying off-line parameters of static state of permanent magnet synchronous motor

Abstract

The invention belongs to the technical field of motors, and discloses a static state offline parameter identification method and device for a permanent magnet synchronous motor, and the method comprises the steps: obtaining nameplate information of a to-be-identified motor; inputting nameplate information of the to-be-identified motor into a grey box model used for predicting off-line parameters of the motor to obtain preset off-line parameters of the to-be-identified motor, and taking the preset off-line parameters as a static state off-line parameter identification result of the to-be-identified motor; wherein the grey box model used for predicting the off-line parameters of the motor is a large language model into which physical principle constraints of the permanent magnet synchronous motor are introduced; according to the method, the nameplate information of the to-be-identified motor is acquired and input into the grey box model used for predicting the off-line parameters of the motor, so that the preset off-line parameters of the motor can be quickly acquired, the off-line parameter identification of the motor in the static state is realized, the parameter identification process is greatly simplified, and the identification efficiency and precision of the off-line parameters are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of permanent magnet synchronous motors, and particularly relates to a method and device for off-line parameter identification of a permanent magnet synchronous motor in a stationary state. Background Art

[0002] Permanent Magnet Synchronous Machines (PMSMs) have the advantages of simple structure, high power density, fast response speed, and high operating efficiency, and are widely used in industrial production, aerospace, new energy transportation and other fields; especially in electric aircraft, as the core power component, the accuracy of the design and control of the permanent magnet synchronous motor has a crucial impact on the performance of the electric aircraft.

[0003] In order to ensure the efficient and stable operation of the permanent magnet synchronous motor, off-line parameter identification is particularly important, aiming to obtain the Maximum Torque Per Ampere (MTPA) curve or the Maximum Torque Per Loss (MTPL) curve of the motor, and then provide key support for optimizing the control strategy of the motor, improving the operating efficiency and control accuracy.

[0004] At present, the off-line parameter identification of permanent magnet synchronous motors is mainly divided into two methods: one is to use frequency domain information for identification, and the other is to use time domain information for identification; however, the above methods all have the limitations of low identification efficiency, complex identification operation, and large result errors, posing a huge challenge to the precise control of the motor; specifically, when using frequency domain information for identification, additional measurement equipment is usually required, and test equipment needs to be established separately for different types of motors, resulting in low identification efficiency and a significant increase in operation difficulty; when using time domain information for identification, although the parameters of the motor model can be calculated through the time domain response of applying perturbations and the off-line parameters can be predicted accordingly, this process has extremely high requirements for the accuracy of sampling data such as current; once the data accuracy is insufficient, it is extremely easy to cause result deviation; at the same time, the generality of the test conditions is also poor, resulting in generally low identification efficiency. Summary of the Invention

[0005] Aiming at the technical problems existing in the prior art, the present invention provides a method and device for off-line parameter identification of a permanent magnet synchronous motor in a stationary state to solve the technical problems of low identification efficiency, complex identification operation, and large result errors existing in the existing off-line parameter identification methods of permanent magnet synchronous motors.

[0006] To achieve the above object, the technical solution adopted by the present invention is as follows: The present invention provides a method for off-line parameter identification of a permanent magnet synchronous motor in a stationary state, including: Obtain the nameplate information of the motor to be identified; Input the nameplate information of the motor to be identified into the grey-box model for predicting the offline parameters of the motor, and obtain the preset offline parameters of the motor to be identified as the identification result of the offline parameters of the motor in the stationary state; wherein, the grey-box model for predicting the offline parameters of the motor is a large language model introduced with the physical principle constraints of the permanent magnet synchronous motor.

[0007] Furthermore, the nameplate information of the motor to be identified includes the bus voltage, rated current, rated speed, rated power, number of pole pairs, efficiency, and power factor of the motor to be identified.

[0008] Furthermore, the construction process of the grey-box model for predicting the offline parameters of the motor includes: Construct a white-box model based on the physical principles of the permanent magnet synchronous motor; wherein, the white-box model is used to describe the internal electromagnetic relationship and energy conversion process of the permanent magnet synchronous motor; Construct a large language model based on reinforcement learning or deep learning to obtain an initial black-box model; Obtain the operating parameters of the permanent magnet synchronous motor to obtain a training data set; wherein, the operating parameters of the permanent magnet synchronous motor include the current, voltage, and temperature of the permanent magnet synchronous motor under different loads and different speeds; Divide the training data set into a training set and a validation set; Use the training set to train the initial black-box model to obtain a trained black-box model; Fuse the trained black-box model with the white-box model to obtain a grey-box model; wherein, in the grey-box model, the white-box model is used to provide the physical principle constraints of the permanent magnet synchronous motor; Use the validation set to validate the grey-box model to obtain a grey-box model for predicting the offline parameters of the motor.

[0009] Furthermore, the white-box model includes the physical constraint equations and physical implicit representations of the permanent magnet synchronous motor; The physical constraint equations of the permanent magnet synchronous motor include the voltage equation, flux linkage equation, and torque equation of the permanent magnet synchronous motor; The physical implicit representation of the permanent magnet synchronous motor is a non-causal model established based on the set of physical characteristic parameters and the set of operating space parameters of the permanent magnet synchronous motor; wherein, the set of physical characteristic parameters of the permanent magnet synchronous motor includes the direct-axis inductance, quadrature-axis inductance, number of pole pairs, permanent magnet flux linkage, and stator resistance of the permanent magnet synchronous motor; the set of operating space parameters of the permanent magnet synchronous motor includes the bus voltage, input current, and mechanical angular velocity of the permanent magnet synchronous motor.

[0010] Furthermore, the preset offline parameters of the motor to be identified include the direct-axis inductance, quadrature-axis inductance, stator resistance, and permanent magnet flux linkage of the motor to be identified.

[0011] Further, it further includes a control strategy curve fitting step; The control strategy curve fitting step is as follows: Based on the preset offline parameters of the motor to be identified, fit the preset motor control strategy curve to obtain the control strategy curve of the motor to be identified.

[0012] Further, the process of fitting the preset motor control strategy curve based on the preset offline parameters of the motor to be identified to obtain the control strategy curve of the motor to be identified includes: Construct a target curve model; wherein, the target curve model is the MTPA target curve model of the motor to be identified or the MTPL target curve model of the motor to be identified; the MTPA target curve model of the motor to be identified is the MTPA target curve model with electromagnetic torque as the optimization target, and the MTPL target curve model of the motor to be identified is the MTPL target curve model with torque loss as the optimization target; Based on the preset offline parameters of the motor to be identified, fit the target curve model to obtain the control strategy curve of the motor to be identified; wherein, the control strategy curve of the motor to be identified is the MTPA control curve or the MTPL control curve of the motor to be identified.

[0013] The present invention also provides a permanent magnet synchronous motor static state offline parameter identification system, including: An information acquisition module, configured to acquire the nameplate information of the motor to be identified; A parameter identification module, configured to input the nameplate information of the motor to be identified into a gray box model for predicting the offline parameters of the motor to obtain the preset offline parameters of the motor to be identified as the identification result of the static state offline parameters of the motor to be identified; wherein, the gray box model for predicting the offline parameters of the motor is a large language model introduced with the physical principle constraints of the permanent magnet synchronous motor.

[0014] The present invention also provides an electronic device, including: A processor, suitable for executing a computer program; A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, it executes the permanent magnet synchronous motor static state offline parameter identification method described above.

[0015] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the permanent magnet synchronous motor static state offline parameter identification method described above.

[0016] Compared with the prior art, the beneficial effects of the present invention are: The off-line parameter identification method for permanent magnet synchronous motors in a stationary state provided by the present invention can quickly obtain the preset off-line parameters of the motor by acquiring the nameplate information of the motor to be identified and inputting it into the grey-box model for predicting the off-line parameters of the motor, realizing the off-line parameter identification of the motor in a stationary state, greatly simplifying the parameter identification process, and improving the identification efficiency and accuracy of the off-line parameters; among them, only the nameplate information of the motor to be identified needs to be acquired, without additional measuring equipment, reducing the professional requirements for operators and also reducing the equipment cost; secondly, introducing the physical principle constraints of the permanent magnet synchronous motor into the grey-box model for predicting the off-line parameters of the motor can more accurately predict the off-line parameters of the motor and improve the accuracy of parameter identification; at the same time, the grey-box model for predicting the off-line parameters of the motor is universal and can be applied to different types of permanent magnet synchronous motors, improving the universality of the parameter identification method; the off-line parameter identification result of the motor in a stationary state obtained by the present invention provides key support for optimizing the control strategy of the motor, helps to more accurately control the operation of the motor, improves the operation efficiency and control accuracy of the motor, and further improves the overall performance of the motor.

[0017] The off-line parameter identification system, electronic device and computer-readable storage medium for permanent magnet synchronous motors in a stationary state provided by the present invention have all the advantages of the above-mentioned off-line parameter identification method for permanent magnet synchronous motors in a stationary state. Brief Description of the Drawings

[0018] Figure 1 It is a flowchart of the off-line parameter identification method for permanent magnet synchronous motors in a stationary state provided in Embodiment 1; Figure 2 It is a structural block diagram of the off-line parameter identification system for permanent magnet synchronous motors in a stationary state provided in Embodiment 2; Figure 3 It is a structural block diagram of the electronic device provided in Embodiment 3. Detailed Description of the Embodiment

[0019] In order to make the technical problems, technical solutions and beneficial effects solved by the present invention clearer, the following specific embodiments are used to further elaborate on the present invention. It should be understood that the specific embodiments described here are only used to explain the present invention and are not used to limit the present invention.

[0020] Before introducing the solutions of this application, first, the concepts involved in this application are explained: Large language model (LLM): It refers to a language model with a large number of parameters and powerful capabilities, which learns the statistical laws and semantic relationships of language by pre-training on a large-scale text data; usually uses unsupervised learning methods to predict the next word or fill in the missing word to capture the context and semantic information of the language.

[0021] The Maximum Torque Per Ampere (MTPA) curve is a curve that describes the operating state in which the motor consumes the least current under a given torque demand.

[0022] The Maximum Torque Per Loss (MTPL) curve is a curve used to describe the maximum torque that can be generated per unit loss of the motor under different load conditions.

[0023] The present invention provides a method for off-line parameter identification of a permanent magnet synchronous motor in a stationary state, including the following steps: Step 100: Obtain the nameplate information of the motor to be identified.

[0024] Step 200: Input the nameplate information of the motor to be identified into a grey-box model for predicting the off-line parameters of the motor, and obtain the preset off-line parameters of the motor to be identified as the identification result of the off-line parameters of the motor in the stationary state; wherein, the grey-box model for predicting the off-line parameters of the motor is a large language model introduced with the physical principle constraints of the permanent magnet synchronous motor.

[0025] Optionally, the method for off-line parameter identification of a permanent magnet synchronous motor in a stationary state according to the present invention further includes a control strategy curve fitting step; specifically, the control strategy curve fitting step is as follows: Based on the preset off-line parameters of the motor to be identified, fit the preset motor control strategy curve to obtain the control strategy curve of the motor to be identified.

[0026] The method for off-line parameter identification of a permanent magnet synchronous motor in a stationary state provided by the present invention uses a large language model introduced with the physical principle constraints of the permanent magnet synchronous motor as a grey-box model for predicting the off-line parameters of the motor. The model effectively combines the constraints of physical principles and the ability of data-driven, and can more accurately predict the off-line parameters of the motor; the identification method is simple, easy to operate, and does not require additional test equipment or complex test environments, improving the efficiency and accuracy of parameter identification; optionally, by fitting the preset motor control strategy curve based on the preset off-line parameters of the motor to be identified, the control strategy curve of the motor to be identified more conforms to the actual operating characteristics of the motor, and can improve the control precision and response speed of the motor.

[0027] The following uses some specific embodiments to further explain the method for off-line parameter identification of a permanent magnet synchronous motor in a stationary state provided by the present invention: Embodiment 1 As shown in the appendix Figure 1 This Embodiment 1 provides a method for off-line parameter identification of a permanent magnet synchronous motor in a stationary state, including the following steps: Step 1: Obtain the nameplate information of the motor to be identified. Among them, the nameplate information of the motor to be identified includes the bus voltage, rated current, rated speed, rated power, number of pole pairs, efficiency, and power factor of the motor to be identified. It should be noted that the nameplate information of the motor to be identified, as an inherent attribute of the motor to be identified, is the original data source for the off-line parameter identification process of the motor, providing initial data support for the prediction analysis of the gray-box model used to predict the off-line parameters of the motor, enabling the gray-box model used to predict the off-line parameters of the motor to predict the preset off-line parameters of the motor to be identified based on the known initial data support; it should also be noted that the nameplate information of the motor to be identified can also be the product number or serial number of the motor to be identified, and the performance parameters of the motor to be identified are included in the product number or serial number of the motor to be identified.

[0028] Step 2: Input the nameplate information of the motor to be identified into the gray-box model used to predict the off-line parameters of the motor to obtain the preset off-line parameters of the motor to be identified, which are used as the off-line parameter identification result of the motor to be identified in the static state; among them, the gray-box model used to predict the off-line parameters of the motor is a large language model introduced with the physical principle constraints of the permanent magnet synchronous motor. The preset off-line parameters of the motor to be identified include the direct-axis inductance, quadrature-axis inductance, stator resistance, and permanent magnet flux linkage of the motor to be identified.

[0029] Specifically, the construction process of the gray-box model used to predict the off-line parameters of the motor includes: Step 21: Build a white-box model based on the physical principle of the permanent magnet synchronous motor; among them, the white-box model is used to describe the internal electromagnetic relationship and energy conversion process of the permanent magnet synchronous motor. Specifically, the white-box model includes the physical constraint equations and physical implicit representations of the permanent magnet synchronous motor.

[0030] The construction process of the physical constraint equations of the permanent magnet synchronous motor is as follows: Based on the basic physical theorems of the permanent magnet synchronous motor, establish the physical constraint equations of the permanent magnet synchronous motor; among them, the basic physical theorems of the permanent magnet synchronous motor include the electromagnetic induction law and Ampere's law; the physical constraint equations of the permanent magnet synchronous motor include the voltage equation, flux linkage equation, and torque equation of the permanent magnet synchronous motor.

[0031] The voltage equation of the permanent magnet synchronous motor is as follows:

[0032]

[0033] Among them, is the equivalent voltage of the permanent magnet synchronous motor on the direct axis; is the stator resistance of the permanent magnet synchronous motor; is the equivalent current of the permanent magnet synchronous motor on the direct axis; is the equivalent magnetic flux of the permanent magnet synchronous motor on the direct axis; is time; is the rotor speed of the permanent magnet synchronous motor; is the equivalent magnetic flux of the permanent magnet synchronous motor on the quadrature axis; is the equivalent voltage of the permanent magnet synchronous motor on the quadrature axis; is the equivalent current of the permanent magnet synchronous motor on the quadrature axis.

[0034] The magnetic flux equation of the permanent magnet synchronous motor is as follows:

[0035]

[0036] Among them, is the equivalent inductance of the permanent magnet synchronous motor on the direct axis; is the permanent magnet flux of the permanent magnet synchronous motor; is the equivalent inductance of the permanent magnet synchronous motor on the quadrature axis.

[0037] The torque equation of the permanent magnet synchronous motor is as follows:

[0038] Among them, is the electromagnetic torque of the permanent magnet synchronous motor; is the number of pole pairs of the permanent magnet synchronous motor.

[0039] The physical implicit representation of the permanent magnet synchronous motor is a non-causal model established based on the set of physical characteristic parameters and the set of operating space parameters of the permanent magnet synchronous motor; among them, the set of physical characteristic parameters of the permanent magnet synchronous motor includes the direct-axis inductance, quadrature-axis inductance, number of pole pairs, permanent magnet flux, and stator resistance of the permanent magnet synchronous motor; the set of operating space parameters of the permanent magnet synchronous motor includes the bus voltage, input current, and mechanical angular velocity of the permanent magnet synchronous motor.

[0040] Specifically, the construction process of the non-causal model established based on the set of physical characteristic parameters and the set of operating space parameters of the permanent magnet synchronous motor is as follows: Establish a first-order ordinary differential equation description of the dynamic behavior of the permanent magnet synchronous motor; among them, the first-order ordinary differential equation description of the dynamic behavior of the permanent magnet synchronous motor is as follows:

[0041]

[0042] Among them, is the direct-axis equivalent current of the permanent magnet synchronous motor at time ; is the direct-axis equivalent voltage of the permanent magnet synchronous motor at time ; is the mechanical angular velocity of the permanent magnet synchronous motor; is the quadrature axis equivalent current of the permanent magnet synchronous motor at time ; is the quadrature axis equivalent voltage of the permanent magnet synchronous motor at time ;

[0043] The mechanical angular velocity of the permanent magnet synchronous motor, the direct axis equivalent voltage of the permanent magnet synchronous motor at time , the quadrature axis equivalent voltage of the permanent magnet synchronous motor at time , the direct axis equivalent current of the permanent magnet synchronous motor at time and the quadrature axis equivalent current of the permanent magnet synchronous motor at time in the first-order ordinary differential equation description of the dynamic behavior of the permanent magnet synchronous motor are normalized to obtain a normalized space.

[0044] The first-order ordinary differential equation description of the dynamic behavior of the permanent magnet synchronous motor is transformed into the normalized space to obtain the first-order ordinary differential equation description of the normalized dynamic behavior of the permanent magnet synchronous motor; among them, the first-order ordinary differential equation description of the normalized dynamic behavior of the permanent magnet synchronous motor is as follows:

[0045]

[0046] , ,

[0047] , , , , , ,

[0048] Among them, , and are all scale parameters; is the normalization result of the direct axis equivalent current of the permanent magnet synchronous motor at time ; is the normalization result of the direct axis equivalent voltage of the permanent magnet synchronous motor at time ; is the normalization result of the mechanical angular velocity of the permanent magnet synchronous motor; is the normalized result of the quadrature-axis equivalent current of the permanent magnet synchronous motor at time ; are all characterization parameters of the permanent magnet synchronous motor in the normalized space; , , , , , and ; is the maximum value of the mechanical angular velocity of the permanent magnet synchronous motor; is the rated current of the permanent magnet synchronous motor; is the DC voltage.

[0049] According to the description of the first-order ordinary differential equation of the dynamic behavior of the normalized permanent magnet synchronous motor, a non-causal model is constructed based on the physical characteristic parameter set and the operation space parameter set of the permanent magnet synchronous motor; among them, the non-causal model established based on the physical characteristic parameter set and the operation space parameter set of the permanent magnet synchronous motor is as follows:

[0050] Among them, is the equivalent inductance of the permanent magnet synchronous motor on the direct axis; is the equivalent inductance of the permanent magnet synchronous motor on the quadrature axis.

[0051] It should be noted that by mapping the physical characteristic parameter set and the operation space parameter set of the permanent magnet synchronous motor to the normalized space, a non-causal model established based on the physical characteristic parameter set and the operation space parameter set of the permanent magnet synchronous motor is obtained to explain the physical implicit representation of the permanent magnet synchronous motor; among them, the data in the physical characteristic parameter set and the operation space parameter set of the permanent magnet synchronous motor are the operation data of the permanent magnet synchronous motor in the preset open-source motor database.

[0052] It should also be noted that in the gray-box model, the white-box model can provide double constraints of basic physical theorems and empirical knowledge; among them, the physical constraint equation of the permanent magnet synchronous motor constructed based on the basic physical theorem of the permanent magnet synchronous motor clarifies the operation mechanism of the motor under various conditions, so that the gray-box model used to predict the off-line parameters of the motor follows the basic physical theorem of the permanent magnet synchronous motor during the process of predicting the off-line parameters of the motor; the physical implicit representation of the permanent magnet synchronous motor distills the operation data of the permanent magnet synchronous motor in the preset open-source motor database, extracts prior knowledge from the operation data of the permanent magnet synchronous motor, provides rich empirical knowledge for the gray-box model used to predict the off-line parameters of the motor, and helps the model make more accurate judgments and decisions in complex situations.

[0053] Step 22: Construct a large language model based on reinforcement learning or deep learning to obtain an initial black-box model. Large language models based on reinforcement learning, such as DeepSeek-R1 (an open-source large language model based on reinforcement learning); large language models based on deep learning, such as the Transformer model (a deep learning model architecture based on self-attention mechanism).

[0054] Step 23: Obtain the operating parameters of the permanent magnet synchronous motor to get a training data set. Among them, the operating parameters of the permanent magnet synchronous motor include current, voltage, and temperature of the permanent magnet synchronous motor under different loads and different speeds; it should be noted that the operating parameters of the permanent magnet synchronous motor are the operating parameters of the permanent magnet synchronous motor in the preset open-source motor database, the actual operating monitoring data of various permanent magnet synchronous motors, or the historical experimental record data of various permanent magnet synchronous motors.

[0055] Step 24: Divide the training data set into a training set and a validation set according to a preset division ratio.

[0056] Step 25: Use the training set to train the initial black-box model to obtain a trained black-box model. During the training process, by adjusting the preset parameters of the initial black-box model to minimize the error between the prediction result of the model and the actual data; among them, cross-validation or regularization techniques are introduced to prevent the model overfitting phenomenon and improve the generalization ability of the model; at the same time, using the sensitivity analysis method, analyze the influence degree of the preset parameters and input variables on the prediction result, obtain the key parameters that have a greater impact on the model performance, and conduct targeted optimization.

[0057] Specifically, when training the initial black-box model constructed by the large language model based on reinforcement learning, through the reinforcement learning algorithm, the initial black-box model learns the complex patterns and rules in the operating parameters of the permanent magnet synchronous motor through continuous trial and error and feedback; when training the initial black-box model constructed by the large language model based on deep learning, continuously adjust the hyperparameters of the initial black-box model to optimize the performance of the model; among them, the hyperparameters of the initial black-box model, such as learning rate, number of layers, or number of hidden units.

[0058] Step 26: Integrate the trained black-box model with the white-box model to obtain a grey-box model. Among them, in the grey-box model, the white-box model is used to provide the physical principle constraints of the permanent magnet synchronous motor. Specifically, the white-box model provides the physical principle constraints of the permanent magnet synchronous motor to ensure that the prediction results of the grey-box model conform to the basic physical theorems of the permanent magnet synchronous motor. Among them, the physical constraint equation of the permanent magnet synchronous motor is used as a hard constraint, and the physical implicit representation of the permanent magnet synchronous motor is used as a soft constraint. Through the mutual constraint and complement of the hard constraint and the soft constraint, the grey-box model has both high precision and physical interpretability. The trained black-box model, through a data-driven approach, mines the potential information in the data to improve the adaptability of the grey-box model to complex working conditions. For example, when predicting the preset offline parameters of the motor to be identified, the white-box model is used as prior knowledge to constrain the output range of the trained black-box model. At the same time, the features and patterns learned by the trained black-box model are integrated into the white-box model, so that the grey-box model can more accurately reflect the characteristics of the motor during actual operation. Preferably, based on an adaptive weight mechanism, the fusion parameters are dynamically adjusted Integrate the trained black-box model with the white-box model; among them, the fusion parameters are dynamically adjusted .

[0059] In this Embodiment 1, the physical principle of the permanent magnet synchronous motor is integrated into the trained black-box model in the form of physical constraint equations and physical implicit representations to provide the physical principle constraints of the permanent magnet synchronous motor. For example, when predicting the permanent magnet flux linkage of the motor to be identified, the physical principle constraints of the permanent magnet synchronous motor are constructed by using Faraday's law of electromagnetic induction and Ampere's law, so that the prediction results of the grey-box model conform to the physical laws, realizing both the powerful data fitting ability of the large language model and ensuring the rationality of the prediction results in terms of physical principles, and enhancing the accuracy and reliability of the offline parameter identification of the permanent magnet synchronous motor.

[0060] Step 27: Verify the grey-box model using the validation set to obtain a grey-box model for predicting the offline parameters of the motor. It should be noted that when using the validation set to verify the grey-box model, the accuracy, precision and generalization ability of the model are evaluated by comparing the prediction results of the model with the actual data. If the model performs poorly on the validation set, such as overfitting or underfitting, the parameters of the model are adjusted, or the architecture of the initial black-box model is re-established or the training algorithm is re-selected.

[0061] It should be noted that in the actual application process, by obtaining the operating parameters of the new permanent magnet synchronous motor and using the operating parameters of the new permanent magnet synchronous motor, the grey box model for predicting the offline parameters of the motor is updated or retrained according to a preset period, so that the model can adapt to the changes in the operating state of the permanent magnet synchronous motor and new working conditions; through continuous learning and updating, the prediction and optimization capabilities of the model will be continuously enhanced, thereby improving the accuracy and reliability of the identification results of the offline parameters of the permanent magnet synchronous motor.

[0062] Step 3: Based on the preset offline parameters of the motor to be identified, fit the preset motor control strategy curve to obtain the control strategy curve of the motor to be identified. The specific process is as follows: Step 31: Construct a target curve model; among them, the target curve model is the MTPA target curve model of the motor to be identified or the MTPL target curve model of the motor to be identified; the MTPA target curve model of the motor to be identified is the MTPA target curve model with electromagnetic torque as the optimization target, and the MTPL target curve model of the motor to be identified is the MTPL target curve model with torque loss as the optimization target.

[0063] Specifically, the MTPA target curve model with electromagnetic torque as the optimization target is as follows: 。

[0064] The MTPL target curve model with torque loss as the optimization target is as follows:

[0065] Among them, is the torque loss; is the copper loss; is the iron loss; is the mechanical loss.

[0066] Step 32: Based on the preset offline parameters of the motor to be identified, fit the target curve model to obtain the control strategy curve of the motor to be identified. Specifically, based on the preset offline parameters of the motor to be identified, use a preset curve fitting model or algorithm to fit the target curve model to obtain the control strategy curve of the motor to be identified; among them, the control strategy curve of the motor to be identified is the MTPA control curve or MTPL control curve of the motor to be identified, and the preset curve fitting model or algorithm is, for example, the Kolmogorov - Arnold network.

[0067] It should be noted that by analyzing and applying the MTPA control curve, the maximum torque of the motor can be output under the given current conditions, thereby improving the operating efficiency and performance of the motor; in practical applications, according to the real-time operating state of the motor and referring to the MTPA control curve, adjusting the control parameters of the motor can achieve energy-saving operation and efficient drive of the motor; the MTPL control curve is used to reflect the operating state in which the motor can achieve the maximum torque loss ratio under different working conditions, and it can comprehensively consider the torque output and energy loss of the motor; in practical applications, when controlling the motor following the MTPL control curve, it can minimize the energy loss of the motor while ensuring that the motor outputs sufficient torque, and improve the overall efficiency of the motor.

[0068] Embodiment 2 As shown in the Figure 2 accompanying figure, Embodiment 2 provides a permanent magnet synchronous motor static state offline parameter identification system, which includes an information acquisition module and a parameter identification module.

[0069] The information acquisition module is used to acquire the nameplate information of the motor to be identified.

[0070] The parameter identification module is used to input the nameplate information of the motor to be identified into the gray box model for predicting the offline parameters of the motor, and obtain the preset offline parameters of the motor to be identified as the identification result of the static state offline parameters of the motor to be identified; among them, the gray box model for predicting the offline parameters of the motor is a large language model introduced with the physical principle constraints of the permanent magnet synchronous motor.

[0071] Optionally, the permanent magnet synchronous motor static state offline parameter identification system described in Embodiment 2 further includes a curve fitting module; the curve fitting module is used to fit the preset motor control strategy curve based on the preset offline parameters of the motor to be identified, and obtain the control strategy curve of the motor to be identified.

[0072] Optionally, in Embodiment 2, the nameplate information of the motor to be identified includes the bus voltage, rated current, rated speed, rated power, number of pole pairs, efficiency and power factor of the motor to be identified.

[0073] Optionally, the construction process of the gray box model for predicting the offline parameters of the motor includes: Based on the physical principles of a permanent magnet synchronous motor, a white-box model is constructed; wherein, the white-box model is used to describe the internal electromagnetic relationship and energy conversion process of the permanent magnet synchronous motor; a large language model based on reinforcement learning or deep learning is constructed to obtain an initial black-box model; the operating parameters of the permanent magnet synchronous motor are acquired to obtain a training data set; according to a preset division ratio, the training data set is divided into a training set and a validation set; the initial black-box model is trained using the training set to obtain a trained black-box model; the trained black-box model is fused with the white-box model to obtain a grey-box model; wherein, in the grey-box model, the white-box model is used to provide the physical principle constraints of the permanent magnet synchronous motor; the grey-box model is verified using the validation set to obtain a grey-box model for predicting the offline parameters of the motor.

[0074] Optionally, the process of fitting a preset motor control strategy curve based on the preset offline parameters of the motor to be identified is as follows: A target curve model is constructed; wherein, the target curve model is the MTPA target curve model of the motor to be identified or the MTPL target curve model of the motor to be identified; the MTPA target curve model of the motor to be identified is the MTPA target curve model with electromagnetic torque as the optimization target, and the MTPL target curve model of the motor to be identified is the MTPL target curve model with torque loss as the optimization target; based on the preset offline parameters of the motor to be identified, the target curve model is fitted to obtain the control strategy curve of the motor to be identified; wherein, the control strategy curve of the motor to be identified is the MTPA control curve or the MTPL control curve of the motor to be identified.

[0075] Embodiment 3 As shown in the appendix Figure 3 This Embodiment 3 provides an electronic device, including: a memory for storing a computer program; a processor for implementing the steps of the method for identifying the offline parameters of a permanent magnet synchronous motor in a stationary state when executing the computer program; or, the processor implements the functions of each module in the above-mentioned system for identifying the offline parameters of a permanent magnet synchronous motor in a stationary state when executing the computer program.

[0076] Exemplarily, the computer program can be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of completing preset functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0077] The electronic device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above are examples of electronic devices and do not constitute a limitation on the electronic device. It may include more components than the above, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0078] The so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may also be any conventional processor, etc. The processor is the control center of the electronic device and connects various parts of the entire electronic device through various interfaces and lines.

[0079] The memory can be used to store the computer program and / or module. The processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and by calling the data stored in the memory.

[0080] The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0081] Embodiment 4 Embodiment 4 of the present invention also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the method for identifying the static state offline parameters of a permanent magnet synchronous motor are realized.

[0082] If the modules / units integrated in the off-line parameter identification system for the permanent magnet synchronous motor in the stationary state are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.

[0083] Based on such an understanding, to implement all or part of the processes in the above-mentioned off-line parameter identification method for the permanent magnet synchronous motor in the stationary state of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned off-line parameter identification method for the permanent magnet synchronous motor in the stationary state can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or preset intermediate form, etc.

[0084] The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0085] For the off-line parameter identification method for the permanent magnet synchronous motor in the stationary state of the present invention, only the nameplate information of the motor to be identified needs to be input into the gray-box model for predicting the off-line parameters of the motor, and the off-line parameter identification of the permanent magnet synchronous motor in the stationary state is carried out by using the gray-box model for predicting the off-line parameters of the motor, and the control strategy curve is fitted in combination with the identification result; it has the advantages of improving the accuracy and efficiency of parameter identification, optimizing the motor control strategy, and reducing the R & D cost and time, and is of great significance for improving the performance of the motor, reducing the operation cost, and accelerating the product development cycle.

[0086] The above embodiments are only one of the implementation manners capable of implementing the technical solution of the present invention. The scope of protection required by the present invention is not limited only by this embodiment, but also includes any changes, substitutions, and other implementation manners that are easily conceivable by those skilled in the art within the technical scope disclosed by the present invention.

Claims

1. A method for offline parameter identification of a permanent magnet synchronous motor in a stationary state, characterized in that: include: Get the nameplate information of the motor to be identified; The nameplate information of the motor to be identified is input into a gray box model for predicting the motor's offline parameters, and the preset offline parameters of the motor to be identified are obtained as the offline parameter identification result of the motor to be identified in the static state; wherein, the gray box model for predicting the motor's offline parameters is a large language model that introduces the physical principle constraints of the permanent magnet synchronous motor.

2. The method for offline parameter identification of a permanent magnet synchronous motor in a stationary state according to claim 1 is characterized in that: The nameplate information of the motor to be identified includes the bus voltage, rated current, rated speed, rated power, number of pole pairs, efficiency and power factor of the motor to be identified.

3. The method for offline parameter identification of a permanent magnet synchronous motor in a stationary state according to claim 1, characterized in that: The construction process of the grey-box model for predicting the motor offline parameters includes: Based on the physical principle of permanent magnet synchronous motor, a white box model is constructed; the white box model is used to describe the internal electromagnetic relationship and energy conversion process of the permanent magnet synchronous motor; Build a large language model based on reinforcement learning or deep learning to obtain an initial black box model; Obtaining operating parameters of the permanent magnet synchronous motor to obtain a training data set; wherein the operating parameters of the permanent magnet synchronous motor include current, voltage and temperature of the permanent magnet synchronous motor under different loads and different speeds; Divide the training data set into training set and validation set; The initial black box model is trained using the training set to obtain a trained black box model; The trained black box model is integrated with the white box model to obtain a gray box model; wherein, in the gray box model, the white box model is used to provide physical principle constraints of the permanent magnet synchronous motor; The grey-box model is validated using the validation set to obtain a grey-box model for predicting the motor offline parameters.

4. The method for offline parameter identification of a permanent magnet synchronous motor in a stationary state according to claim 3 is characterized in that: The white-box model includes the physical constraint equations and physical implicit representation of the permanent magnet synchronous motor; The physical constraint equations of the permanent magnet synchronous motor include the voltage equation, flux equation and torque equation of the permanent magnet synchronous motor; The physical implicit representation of the permanent magnet synchronous motor is a non-causal model established based on the physical characteristic parameter set and the operating space parameter set of the permanent magnet synchronous motor; wherein, the physical characteristic parameter set of the permanent magnet synchronous motor includes the direct-axis inductance, quadrature-axis inductance, pole pair number, permanent magnet flux linkage and stator resistance of the permanent magnet synchronous motor; the operating space parameter set of the permanent magnet synchronous motor includes the bus voltage, input current and mechanical angular velocity of the permanent magnet synchronous motor.

5. The method for offline parameter identification of a permanent magnet synchronous motor in a stationary state according to claim 1, characterized in that: The preset offline parameters of the motor to be identified include the direct-axis inductance, quadrature-axis inductance, stator resistance and permanent magnet flux linkage of the motor to be identified.

6. The method for offline parameter identification of a permanent magnet synchronous motor in a stationary state according to claim 1, characterized in that: It also includes a control strategy curve fitting step; The control strategy curve fitting steps are as follows: Based on the preset offline parameters of the motor to be identified, a preset motor control strategy curve is fitted to obtain the control strategy curve of the motor to be identified.

7. The method for offline parameter identification of a permanent magnet synchronous motor in a stationary state according to claim 6, characterized in that: The process of fitting a preset motor control strategy curve based on preset offline parameters of the motor to be identified to obtain the control strategy curve of the motor to be identified includes: Constructing a target curve model; wherein the target curve model is an MTPA target curve model of the motor to be identified or an MTPL target curve model of the motor to be identified; the MTPA target curve model of the motor to be identified is an MTPA target curve model with electromagnetic torque as the optimization target, and the MTPL target curve model of the motor to be identified is an MTPL target curve model with torque loss as the optimization target; Based on the preset offline parameters of the motor to be identified, the target curve model is fitted to obtain the control strategy curve of the motor to be identified; wherein the control strategy curve of the motor to be identified is the MTPA control curve or the MTPL control curve of the motor to be identified.

8. A permanent magnet synchronous motor static state offline parameter identification system, characterized in that: include: An information acquisition module, used to acquire the nameplate information of the motor to be identified; The parameter identification module is used to input the nameplate information of the motor to be identified into the gray box model used to predict the motor's offline parameters, and obtain the preset offline parameters of the motor to be identified as the offline parameter identification result of the motor to be identified in the static state; wherein the gray box model used to predict the motor's offline parameters is a large language model that introduces the physical principle constraints of the permanent magnet synchronous motor.

9. An electronic device, characterized in that: include: a processor suitable for executing a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the method for offline parameter identification of a permanent magnet synchronous motor in a stationary state as described in any one of claims 1 to 7 is executed.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for offline parameter identification of a permanent magnet synchronous motor in a stationary state as described in any one of claims 1 to 7 is implemented.

Images