A permanent magnet synchronous motor model predictive control system, control method and permanent magnet synchronous motor based on Gaussian process

Abstract

The present invention discloses a model predictive control system for a permanent magnet synchronous motor based on a Gaussian process, which comprises: a speed controller, a current model predictive controller, a current detection module, a mismatch detection module and a Gaussian process parameter optimization module. The Gaussian process parameter optimization module predicts system parameters for the detection data input by the mismatch detection module, and inputs the prediction results into the current model predictive controller to update the mismatched parameters. The present invention also discloses a control method for a model predictive control system for a permanent magnet synchronous motor based on a Gaussian process and a permanent magnet synchronous motor.

Description

Technical Field

[0001] The present invention relates to the technical field of motor control, and in particular to a permanent magnet synchronous motor model prediction control system and a control method based on a Gaussian process, and a permanent magnet synchronous motor. Background Art

[0002] Motor parameters play a decisive role in the precise control of the motor, so they need to be accurately estimated in the current motor control system. The accuracy of the parameters determines the effect of system control. During the operation of the motor, due to external interference and long-term effects of the environment such as temperature, the motor parameters may change in real time and differ from the initial values. Therefore, certain technical means are needed to predict and optimize the control of these changing parameters to ensure the effective operation of the motor.

[0003] In the model-based predictive control strategy, the process model plays an important role. However, in practical applications, due to the uncertainty of the system, the mismatch between the model and the actual system is inevitable, which causes model mismatch. In the field of motor control, model mismatch can lead to a series of problems such as torque pulsation. For model predictive current control, an intuitive manifestation is that the current control effect is poor. Therefore, it is very necessary to accurately estimate the parameters of the motor to reduce the impact of model mismatch.

[0004] At present, there are a large number of literatures related to permanent magnet synchronous motor parameter estimation. These techniques are generally divided into offline estimation methods and online estimation methods. Offline estimation methods are further divided into frequency domain and time domain methods. In addition, simulation analytical methods, especially finite element analysis, are also classified as offline parameter estimation techniques. Online evaluation methods are divided into numerical methods, observer-based methods, and machine learning-based methods. Summary of the invention

[0005] The present invention aims to overcome the defects of the prior art, and the present invention adopts the following technical solutions:

[0006] In one aspect, the present invention provides a permanent magnet synchronous motor model predictive control system based on Gaussian process. The permanent magnet synchronous motor model predictive control system based on Gaussian process includes: a speed controller, a current model predictive controller, a current detection module, a mismatch detection module and a Gaussian process parameter optimization module;

[0007] The speed controller is used to control the speed of the motor and generate a current reference value;

[0008] The current model predictive controller is used to track the current and select the voltage vector;

[0009] The current detection module is used to detect the current and generate current detection data;

[0010] The mismatch detection module is used to determine whether the system is mismatched according to the current detection data. If it is determined that the system is not mismatched, the system continues to operate normally. If it is determined that the system is mismatched, the current detection data is used as an input of the Gaussian process parameter optimization module to predict system parameters;

[0011] The Gaussian process parameter optimization module is used to predict the system parameters of the detection data input by the mismatch detection module, and input the prediction results into the current model prediction controller to update the mismatched parameters.

[0012] In some embodiments, the current model predictive controller selects a voltage vector that minimizes a cost function, and the voltage vector is applied to the entire current sampling period.

[0013] In some embodiments, the Gaussian process parameter optimization module predicts system parameters for the detection data input by the mismatch detection module, specifically including:

[0014] Setting a predictive current control model, and acquiring training data and test data for Gaussian process regression based on the predictive current control model;

[0015] Perform training based on the training data and the test data to obtain a Gaussian process model;

[0016] An online mismatch detection mechanism for system parameters is set and the system parameters are predicted through the Gaussian process model.

[0017] In some embodiments, the control system further comprises: a data preprocessing module;

[0018] The data preprocessing module receives the current detection data generated by the current detection module,

[0019] The data is pre-processed and output as current fluctuation and current deviation, and the current fluctuation and current deviation are output to the mismatch detection module.

[0020] In some embodiments, the mismatch detection module determines the system mismatch status by analyzing the input and output data. If the current fluctuation or current deviation exceeds a predetermined threshold, the system is determined to be mismatched; otherwise, the system is determined to be not mismatched.

[0021] In some embodiments, when the mismatch detection module determines that there is a mismatch, the Gaussian process parameter optimization module uses the current fluctuation and the current offset as inputs of the Gaussian process parameter optimization module to predict and update system parameters, obtains the system parameters as updated nominal values ​​of the model predictive controller, and the system continues to operate;

[0022] When the mismatch detection module determines that the system is not mismatched, the system continues to operate with the original nominal value of the current model predictive controller.

[0023] In some embodiments, the predetermined threshold value of the current fluctuation degree is 1.5; the predetermined threshold value of the current deviation degree is 0.7.

[0024] In some embodiments, the speed controller is a speed PI controller.

[0025] In a second aspect, the present invention further provides a control method for a permanent magnet synchronous motor model predictive control system based on a Gaussian process, wherein the control system is a permanent magnet synchronous motor model predictive control system based on a Gaussian process as described above, and the control method comprises the steps of:

[0026] S1, controlling the speed controller to generate a current reference value;

[0027] S2, the current model predictive controller tracks the current and selects a voltage vector;

[0028] S3, the current detection module detects the current and generates current detection data;

[0029] S4, the mismatch detection module determines whether the system is mismatched according to the current detection data. If it is determined that the system is not mismatched, the system continues to operate normally. If it is determined that the system is mismatched, the current detection data is used as the input of the Gaussian process parameter optimization module to predict system parameters;

[0030] S5, the Gaussian process parameter optimization module predicts the system parameters of the detection data input by the mismatch detection module, and inputs the prediction results into the current model prediction controller to update the mismatched parameters.

[0031] In a third aspect, the present invention further provides a permanent magnet synchronous motor, which includes the permanent magnet synchronous motor model predictive control system based on Gaussian process as described above.

[0032] Technical effect of the present invention: The model predictive control system and control method of permanent magnet synchronous motor based on Gaussian process and the permanent magnet synchronous motor disclosed in the present invention can realize the optimization control of the online system parameters of the motor through the cooperation among the speed controller, the current model predictive controller, the current detection module, the mismatch detection module and the Gaussian process parameter optimization module. The model predictive control system of permanent magnet synchronous motor based on Gaussian process realizes the stable control of the current loop of permanent magnet synchronous motor through the Gaussian process parameter optimization module when the motor parameters fluctuate. Compared with the traditional model predictive current control, the present invention increases the stability of control through the overall cooperation between the mismatch detection module and the control system, and overcomes the system model mismatch problem. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0034] Figure 1 A schematic diagram of the structure and principle of a permanent magnet synchronous motor model predictive control system based on Gaussian process according to an embodiment of the present invention;

[0035] Figure 2 is a parameter prediction curve under different nominal value conditions according to an embodiment of the present invention;

[0036] Figure 3 is a predicted variance curve under different nominal value conditions according to an embodiment of the present invention;

[0037] Figure 4 is a parameter prediction curve under the same nominal value conditions according to an embodiment of the present invention;

[0038] Figure 5 is a predicted variance curve under the same nominal value conditions according to an embodiment of the present invention;

[0039] Figure 6 is a Gaussian process regression curve under the same nominal value conditions according to an embodiment of the present invention;

[0040] Figure 7 An online mismatch detection mechanism for system parameters based on Gaussian process according to an embodiment of the present invention;

[0041] Figure 8 is a FCS-MPC current curve when the current fluctuation exceeds a threshold according to an embodiment of the present invention;

[0042] Fig. 9 is a GP-MPC current curve when the current fluctuation exceeds a threshold according to an embodiment of the present invention;

[0043] Fig.10 is a current curve of FCS-MPC when the current deviation exceeds a threshold according to an embodiment of the present invention;

[0044] Fig.11 is a current curve of a current deviation exceeding a threshold value GP-MPC according to an embodiment of the present invention;

[0045] Fig.12The present invention is a flowchart of a Gaussian process-based permanent magnet synchronous motor model predictive control method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and do not constitute a limitation of the present invention.

[0047] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0048] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0049] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0050] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0051] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0052] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0053] The present invention will be described in detail below in conjunction with the various embodiments shown in the accompanying drawings. However, these embodiments do not limit the present invention, and any structural, methodological, or functional changes made by a person skilled in the art based on these embodiments are all within the scope of protection of the present invention.

[0054] Gaussian process is a new type of machine learning method with strong generalization ability. Compared with neural networks and support vector machines, Gaussian process is easier to implement, has adaptive hyperparameter acquisition, flexible non-parametric inference, and output has probabilistic significance.

[0055] Based on the above advantages, the embodiment of the present invention provides a Gaussian process-based permanent magnet synchronous motor model predictive control system. The structural principle block diagram of the control system is shown in FIG. Figure 1 shown.

[0056] The permanent magnet synchronous motor model predictive control system based on Gaussian process includes: a speed controller, a current model predictive controller, a current detection module, a mismatch detection module and a Gaussian process parameter optimization module;

[0057] The speed controller is used to control the speed of the motor and generate a current reference value;

[0058] The current model predictive controller is used to track the current and select the voltage vector;

[0059] The current detection module is used to detect the current and generate current detection data;

[0060] The mismatch detection module is used to determine whether the system is mismatched according to the current detection data. If it is determined that the system is not mismatched, the system continues to operate normally. If it is determined that the system is mismatched, the current detection data is used as an input of the Gaussian process parameter optimization module to predict system parameters;

[0061] The Gaussian process parameter optimization module is used to predict the system parameters of the detection data input by the mismatch detection module, and input the prediction results into the current model prediction controller to update the mismatched parameters.

[0062] In some embodiments, the current model predictive controller selects a voltage vector that minimizes a cost function, and the voltage vector is applied to the entire current sampling period.

[0063] In some embodiments, the Gaussian process parameter optimization module predicts system parameters for the detection data input by the mismatch detection module, specifically including:

[0064] Setting a predictive current control model, and acquiring training data and test data for Gaussian process regression based on the predictive current control model;

[0065] Perform training based on the training data and the test data to obtain a Gaussian process model;

[0066] An online mismatch detection mechanism for system parameters is set and the system parameters are predicted through the Gaussian process model.

[0067] In some embodiments, the control system further comprises: a data preprocessing module;

[0068] The data preprocessing module receives the current detection data generated by the current detection module,

[0069] The data is pre-processed and output as current fluctuation and current deviation, and the current fluctuation and current deviation are output to the mismatch detection module.

[0070] In some embodiments, the mismatch detection module determines the system mismatch status by analyzing the input and output data. If the current fluctuation or current deviation exceeds a predetermined threshold, the system is determined to be mismatched; otherwise, the system is determined to be not mismatched.

[0071] In some embodiments, when the mismatch detection module determines that there is a mismatch, the Gaussian process parameter optimization module uses the current fluctuation and the current offset as inputs of the Gaussian process parameter optimization module to predict and update system parameters, obtains the system parameters as updated nominal values ​​of the model predictive controller, and the system continues to operate;

[0072] When the mismatch detection module determines that the system is not mismatched, the system continues to operate with the original nominal value of the current model predictive controller.

[0073] In some embodiments, the predetermined threshold value of the current fluctuation degree is 1.5; the predetermined threshold value of the current deviation degree is 0.7.

[0074] In some embodiments, the speed controller is a speed PI controller.

[0075] The following mainly describes the specific situation that the Gaussian process parameter optimization module predicts the system parameters of the detection data input by the mismatch detection module, which specifically includes:

[0076] 1. Setting a predictive current control model, and obtaining training data and test data for Gaussian process regression based on the predictive current control model;

[0077] 2. Perform training based on the training data and the test data to obtain a Gaussian process model;

[0078] 3. Set up an online mismatch detection mechanism for system parameters and predict system parameters through the Gaussian process model.

[0079] Among them, 1. Setting a predictive current control model, and obtaining training data and test data for Gaussian process regression based on the predictive current control model can be elaborated in detail as follows:

[0080] The Gaussian process-based permanent magnet synchronous motor model predictive control system model is designed through a finite set model predictive current control model. The finite set MPC current controller requires the following current model to predict the dynamics of the motor:

[0081]

[0082] where v d and i d are the d-axis voltage and current, v q and i q are the q-axis voltage and current, R s is the stator resistance, L d and L q are the d-axis and q-axis inductances, ψ m is the stator flux, w r is the angular velocity of the motor.

[0083] Discretization using the Euler method:

[0084]

[0085] Where T s is the sampling time, i[k+1] is the current value at time k+1, and i[k] is the current value at time k.

[0086] The predicted stator current expression can be obtained from expressions (1) and (2):

[0087]

[0088] The above expression can predict the stator current of each of the 7 voltage vectors generated by the inverter. The current model predictive controller will track the current, select the voltage vector that minimizes the cost function as the control signal, and apply it to the next cycle. The designed cost function CF n The expression is:

[0089]

[0090] in, and Respectively represent the d-axis and q-axis current reference values, V 0 ~V 6 Represents the 7 voltage vectors generated by the inverter.

[0091] Ideally, there is no model mismatch in the motor parameters, so the predictive control strategy described in expressions (3) and (4) is effective, but in reality, the motor parameters are unknown or inaccurate.

[0092] When the motor parameters are inaccurate, the motor parameters of the predicted current control model and the actual motor parameters will inevitably mismatch. Therefore, we preprocess the motor model mismatch degree and the quantified value of the current performance, and use this data as the basis for Gaussian process regression training and testing.

[0093] Taking the d-axis and q-axis inductance of a surface-mounted permanent magnet synchronous motor as an example, when the actual motor parameters are lower than the nominal inductance value, the q-axis current fluctuates more and more as the mismatch increases. When the actual motor parameters are higher than the nominal inductance value, the current fluctuation decreases as the mismatch increases, but the q-axis current deviates more and more from the current reference value.

[0094] The current offset and current fluctuation are the quantitative values ​​of the current performance. This quantitative value data is obtained through the model prediction current control model. According to the above analysis, there is a certain functional relationship between the current offset, current fluctuation and the model mismatch degree. Under the condition that this functional relationship is known, the model mismatch degree can be obtained. The model mismatch degree is the offset of the nominal parameter value to the actual parameter value. The nominal parameter value is known, so the actual parameter value of the system can be obtained. The acquisition of the functional relationship requires the training of the Gaussian process regression model.

[0095] Among them, 2. The Gaussian process model is obtained by training based on the training data and the test data, which can be elaborated as follows:

[0096] In this step, the Gaussian process model regression is mainly performed through system data. This Gaussian process regression model is a multi-input single-output model. It is assumed that the nominal value of the inductor γ, the current fluctuation α and the current offset β are used as model inputs, and the actual inductor parameter y is the model output. The training data set D contains n samples as follows:

[0097]

[0098] y * ,z * =(α * ,β * ,γ * ) represents the test data, so the joint distribution of the training sample and a test point is:

[0099]

[0100] Where z is the vector of training samples, subject to the mean vector μ 1 , Gaussian distribution of covariance matrix K. Test data z * Subject to the mean vector μ 2 , covariance matrix K ** Gaussian distribution.

[0101] And K, K * and K ** The following conditions must be met:

[0102]

[0103] The above covariance matrix is ​​calculated using the following kernel function:

[0104]

[0105] where σ f ,α,i is a hyper parameter.

[0106] In this embodiment, the mean function of the Gaussian process model is a constant mean function, and the likelihood function is a Gaussian likelihood. The core prediction formula can be obtained by using the conditional distribution property of the Gaussian distribution:

[0107]

[0108] Among them, μ z*|z is the predicted mean, K z*|z is the prediction variance.

[0109] Based on the Gaussian process algorithm designed above, online training is performed using training data, and prediction accuracy analysis is performed using test data.

[0110] Figure 2This is a comparison between the predicted values ​​and the true values ​​of ten random data sets. Figure 3 is the prediction accuracy of these ten sets of data. By analyzing the prediction variance, the accuracy can reach 10 -3 .

[0111] In order to show the regression curve more intuitively, ten sets of data are tested under the condition that the nominal value of motor inductance is 0.01, and the comparison between the parameter prediction value and the actual value is shown in Figure 2. Figure 4 As shown in Figure 2, the prediction accuracy of these ten sets of data is shown in Figure 5 ,Depend on Figure 4 and Figure 5 It can be seen that the prediction variance of this set of tests reaches 10 -4 . Figure 7 The figure is a three-dimensional schematic diagram of the Gaussian process regression curve under the above conditions. The circle represents the true value of the test, the dark gray curve is the regression curve, and the middle part of the two light gray curves represents the interval above the 95% confidence level of the predicted value. From a probability perspective, the probability of obtaining the predicted value is above 95%.

[0112] Through the above analysis, the motor parameter prediction accuracy fully meets the model accuracy requirements, and the Gaussian process model training is initially completed; in order to further improve the efficiency, the Gaussian process model parameter optimization module also requires a startup mechanism, namely, the system parameter online mismatch detection mechanism.

[0113] Among them, 3. Setting the system parameter online mismatch detection mechanism and predicting the system parameters through the Gaussian process model can be elaborated as follows:

[0114] The motor parameter mismatch is determined based on the current fluctuation, and the quantified data of the current fluctuation is also the input of the Gaussian process regression algorithm. Therefore, online mismatch detection and online parameter optimization can be embedded in the control system at the same time.

[0115] The online mismatch detection mechanism of system parameters based on Gaussian process is as follows: Figure 7 As shown. During the operation of the system, the current is detected in real time, and the detection results are used as the input of the data preprocessing algorithm. The data preprocessing output is the current fluctuation and current offset. The system mismatch state is judged by the input and output data. If the current fluctuation B exceeds 1.5 or the current offset P exceeds 70%, the system judges that there is a mismatch, otherwise the system judges that there is no mismatch.

[0116] When it is judged that the system is mismatched, the current fluctuation and current offset are used as the input of the Gaussian process parameter optimization module to predict and update the system parameters, and the system parameters are used as the updated nominal values ​​of the model predictive controller, and the system continues to operate. When it is judged that the system is not mismatched, the system continues to operate with the original nominal value of the current model predictive controller.

[0117] This mismatch detection mechanism is a closed-loop mechanism. During the operation of the control system, this detection mechanism runs synchronously and continuously monitors the mismatch status of the system. However, the Gaussian process parameter optimization module does not run all the time. It will only start when the system detects a mismatch signal. Therefore, the mismatch detection mechanism reduces the computing power of the entire system by 50%, thereby improving the online operation efficiency.

[0118] In order to verify the parameter optimization control effect based on Gaussian process proposed in the present invention, the control strategy proposed in this patent is compared by predicting the current control strategy of the finite set model when the nominal inductance is 0.01 and the actual motor parameters fluctuate randomly between 0.005 and 0.05. Figure 8 and Fig.10 This is the q-axis current curve of the finite set model predictive control (FCS-MPC). When the actual parameters of the motor are constantly changing, the current fluctuation gradually increases with the increase of the mismatch degree, and it cannot meet the control performance requirements. Fig. 9 and Fig.11 It is the q-axis current curve of Gaussian process-based model predictive control (GP-MPC). When the mismatch degree reaches the predetermined threshold, the system parameters are adjusted and optimized in time, and the current data curve remains stable.

[0119] In a second aspect, the present invention further provides a control method for a permanent magnet synchronous motor model predictive control system based on a Gaussian process, wherein the control system is the permanent magnet synchronous motor model predictive control system based on a Gaussian process as described above. Fig.12 As shown, the control method comprises the steps of:

[0120] S1, controlling the speed controller to generate a current reference value;

[0121] S2, the current model predictive controller tracks the current and selects a voltage vector;

[0122] S3, the current detection module detects the current and generates current detection data;

[0123] S4, the mismatch detection module determines whether the system is mismatched according to the current detection data. If it is determined that the system is not mismatched, the system continues to operate normally. If it is determined that the system is mismatched, the current detection data is used as the input of the Gaussian process parameter optimization module to predict system parameters;

[0124] S5, the Gaussian process parameter optimization module predicts the system parameters of the detection data input by the mismatch detection module, and inputs the prediction results into the current model prediction controller to update the mismatched parameters.

[0125] In a third aspect, the present invention further provides a permanent magnet synchronous motor, which includes the permanent magnet synchronous motor model predictive control system based on Gaussian process as described above.

[0126] The control method of the permanent magnet synchronous motor model predictive control system based on Gaussian process and the beneficial effects of the permanent magnet synchronous motor are consistent with the above-mentioned permanent magnet synchronous motor model predictive control system based on Gaussian process, and will not be repeated here.

[0127] Beneficial effects of the embodiments of the present invention: The Gaussian process-based permanent magnet synchronous motor model prediction control system and control method and the permanent magnet synchronous motor disclosed in the embodiments of the present invention can realize online optimization control of the motor through the cooperation between the speed controller, the current model prediction controller, the current detection module, the mismatch detection module and the Gaussian process parameter optimization module. The Gaussian process-based permanent magnet synchronous motor model prediction control system combines the finite set model prediction controller of the Gaussian process-based permanent magnet synchronous motor model prediction control system model with the Gaussian process parameter optimization module to realize stable control of the permanent magnet synchronous motor current loop under the condition of motor parameter fluctuations. Compared with the traditional model prediction current control, the present invention increases the stability of control through the overall cooperation of the mismatch detection module and the control system, and overcomes the system model mismatch problem. Compared with other parameter optimization algorithms, the Gaussian process of the Gaussian process parameter optimization module of the present invention also provides the confidence of the prediction result, and the system algorithm can be monitored and optimized through this confidence. In addition, in the Gaussian process regression algorithm of the Gaussian process parameter optimization module of the control system during operation, the adaptive acquisition of hyperparameters also reduces the complexity of the algorithm and increases the practicality of the algorithm.

[0128] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0129] In the description of the present invention, it should be understood that the symbols such as parameters, variables and program names mentioned in the embodiments of the present invention can be replaced by any other codes that will not cause confusion.

[0130] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, “axial”, “radial”, “circumferential”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0131] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features.

[0132] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0133] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0134] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0135] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

[0136] The specific implementation of the present invention described above does not constitute a limitation on the protection scope of the present invention. Any other corresponding changes and modifications made based on the technical concept of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A permanent magnet synchronous motor model predictive control system based on Gaussian process, characterized in that: include: Speed ​​controller, current model predictive controller, current detection module, mismatch detection module and Gaussian process parameter optimization module; The speed controller is used to control the speed of the motor and generate a current reference value; The current model predictive controller is used to track the current and select the voltage vector; The current detection module is used to detect the current and generate current detection data; The mismatch detection module is used to determine whether the system is mismatched according to the current detection data. If it is determined that the system is not mismatched, the system continues to operate normally. If it is determined that the system is mismatched, the current detection data is used as an input of the Gaussian process parameter optimization module to predict system parameters; The Gaussian process parameter optimization module is used to predict the system parameters of the detection data input by the mismatch detection module, and input the prediction results into the current model prediction controller to update the mismatched parameters; The control system further comprises: a data preprocessing module; The data preprocessing module receives the current detection data generated by the current detection module, performs data preprocessing and outputs the data as current fluctuation and current offset, and outputs the current fluctuation and current offset to the mismatch detection module; When the mismatch detection module determines that there is a mismatch, the Gaussian process parameter optimization module uses the current fluctuation and the current offset as inputs of the Gaussian process parameter optimization module to predict and update the system parameters, and obtains the system parameters as the updated nominal values ​​of the model predictive controller, and the system continues to operate; When the mismatch detection module determines that the system is not mismatched, the system continues to operate with the original nominal value of the current model predictive controller.

2. The permanent magnet synchronous motor model predictive control system based on Gaussian process according to claim 1 is characterized in that: The current model predictive controller selects a voltage vector that can minimize a cost function, and the voltage vector is applied to the entire current sampling period.

3. The permanent magnet synchronous motor model predictive control system based on Gaussian process according to claim 1, characterized in that: The Gaussian process parameter optimization module predicts system parameters for the detection data input by the mismatch detection module, specifically including: Setting a predictive current control model, and acquiring training data and test data for Gaussian process regression based on the predictive current control model; Perform training based on the training data and the test data to obtain a Gaussian process model; An online mismatch detection mechanism for system parameters is set and the system parameters are predicted through the Gaussian process model.

4. The permanent magnet synchronous motor model predictive control system based on Gaussian process according to claim 1, characterized in that: The mismatch detection module determines the system mismatch state by judging the input and output data. If the current fluctuation or current deviation exceeds a predetermined threshold, it determines that the system is mismatched; otherwise, it determines that the system is not mismatched.

5. The permanent magnet synchronous motor model predictive control system based on Gaussian process according to claim 1, characterized in that: The predetermined threshold value of the current fluctuation degree is 1.5; the predetermined threshold value of the current deviation degree is 0.

7.

6. The permanent magnet synchronous motor model predictive control system based on Gaussian process according to claim 1, characterized in that: The speed controller is a speed PI controller.

7. A control method for a permanent magnet synchronous motor model predictive control system based on Gaussian process, characterized in that: The control system is the control system according to claim 1, and the control method comprises: S1, controlling the speed controller to generate a current reference value; S2, the current model predictive controller tracks the current and selects a voltage vector; S3, the current detection module detects the current and generates current detection data; S4, the mismatch detection module determines whether the system is mismatched according to the current detection data. If it is determined that the system is not mismatched, the system continues to operate normally. If it is determined that the system is mismatched, the current detection data is used as the input of the Gaussian process parameter optimization module to predict system parameters; S5, the Gaussian process parameter optimization module predicts the system parameters of the detection data input by the mismatch detection module, and inputs the prediction results into the current model prediction controller to update the mismatched parameters.

8. A permanent magnet synchronous motor, characterized in that: The permanent magnet synchronous motor includes the permanent magnet synchronous motor model predictive control system based on Gaussian process as described in any one of claims 1-6.

Images