Permanent magnet synchronous motor data driving prediction current modeling method and device, medium and equipment

Abstract

The embodiment of the invention discloses a permanent magnet synchronous motor data driving prediction current modeling method and device, a medium and equipment, relates to the technical field of converters, and aims to solve the problem that prediction precision is reduced due to the fact that a prediction current model in the prior art is susceptible to noise interference. According to the method, the influence of the cross saturation effect on electromagnetism under the actual condition is considered, a data driving current prediction model of the motor is obtained, a ridge regression-based calculation model of parameter vectors in the model is constructed through historical data, and ridge parameter dynamic adjustment is established by evaluating the severity of noise in the data, so that the motor driving current prediction accuracy is improved. Self-adaptive penalty of data noise is realized, a target solution of a penalty term is determined, and a final prediction model is obtained by further backstepping a parameter vector, so that the current prediction precision under the noise working condition is improved.

Description

Technical Field

[0001] The present application relates to the technical field of converters, and in particular to a method, device, medium and equipment for data-driven predictive current modeling of a permanent magnet synchronous motor. Background Art

[0002] Model predictive control (MPC) has received extensive attention in the field of motor drives due to its advantages such as fast dynamic response and strong control flexibility. It is a promising alternative to traditional control methods. Traditional MPC is based on motor models to predict system behavior, which means that the controller requires accurate motor parameters to achieve satisfactory control performance. However, in actual working conditions, key motor parameters are highly sensitive, and data-driven technology is currently receiving increasing attention in solving the MPC parameter dependency problem.

[0003] Among them, the least squares method has been proven to be a potential alternative to traditional MPC. The basic principle of the least squares method is to find the optimal estimate of the model parameters by minimizing the sum of the squares of the errors between the predicted value and the actual value. The core idea is to match the model's prediction results with the observed data as much as possible. Therefore, this data-based solution can identify a more accurate current prediction model in real time, thereby improving the predictive control performance. Due to the potential noise in current sensor measurements, the least squares method's reliance on system input and output data poses a challenge. The predicted current model established by the least squares method under noise interference is susceptible to interference, resulting in poor prediction current accuracy, which in turn affects control performance. Summary of the invention

[0004] The main purpose of the present application is to provide a method, device, medium and equipment for data-driven predictive current modeling of a permanent magnet synchronous motor, aiming to solve the problem that the predictive current model in the prior art is easily affected by noise, resulting in reduced prediction accuracy.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of the present application are as follows:

[0006] In a first aspect, an embodiment of the present application provides a data-driven prediction current modeling method for a permanent magnet synchronous motor, comprising the following steps:

[0007] Obtaining a data-driven current prediction model of a target motor based on a cross-saturation effect; wherein the data-driven current prediction model includes a parameter vector;

[0008] According to the historical data collected during the historical control period, a calculation model of the parameter vector based on ridge regression is established; wherein the calculation model includes a penalty term;

[0009] Determine the target solution of the penalty term based on the severity of the noise in the historical data;

[0010] The target penalty term and the target parameter vector are obtained according to the target solution to establish a target data driven current prediction model.

[0011] In a possible implementation manner of the first aspect, before determining a target solution of the penalty term according to the noise severity of the historical data, the method further includes:

[0012] Construct matrices for the data corresponding to the input data and output data in the historical data;

[0013] According to the matrix, the residual sum of squares and the total sum of squares are obtained;

[0014] According to the residual sum of squares and the total sum of squares, the multicollinearity of the input data is obtained to characterize the severity of the noise of the historical data.

[0015] In a possible implementation of the first aspect, determining a target solution for the penalty term according to the noise severity of the historical data includes:

[0016] According to the positive correlation between multicollinearity and the severity of noise in historical data, the relationship between multicollinearity and penalty term is obtained;

[0017] The relationship between multicollinearity and penalty terms is mapped based on the mapping function, and the target solution of the penalty term is determined.

[0018] In a possible implementation of the first aspect, obtaining multicollinearity of input data according to the residual sum of squares and the total sum of squares to characterize the severity of noise in the historical data includes:

[0019] According to the residual sum of squares and the total sum of squares, the variance inflation factor of the input data is obtained to measure the multicollinearity of the input data to characterize the severity of the noise of the historical data.

[0020] In a possible implementation manner of the first aspect, before obtaining the data-driven current prediction model of the target motor based on the cross-saturation effect, the method further includes:

[0021] According to the stator voltage and the stator current in the current control of the target motor, input data and output data are obtained respectively;

[0022] According to the input data, output data and parameter vector, a data driven current prediction model of the target motor based on the cross saturation effect is established.

[0023] In a possible implementation of the first aspect, a calculation model of a parameter vector based on ridge regression is established according to historical data collected during a historical control period, including:

[0024] According to the historical data collected during the historical control period, historical input data and historical output data are obtained;

[0025] According to the historical input data and the historical output data, construct the past subset and the future subset respectively;

[0026] According to the past subset and the future subset, a calculation model of the parameter vector based on ridge regression is established.

[0027] In a possible implementation of the first aspect, a calculation model of a parameter vector based on ridge regression is established according to the past subset and the future subset, including:

[0028] Based on the past subset and the future subset, the parameter vector is estimated by applying the solution of the least square method to establish a computational model of the parameter vector based on ridge regression.

[0029] In a second aspect, an embodiment of the present application provides a data-driven prediction current modeling device for a permanent magnet synchronous motor, comprising:

[0030] An acquisition module, the acquisition module is used to obtain a data-driven current prediction model of a target motor based on a cross-saturation effect; wherein the data-driven current prediction model includes a parameter vector;

[0031] Establishing a module, the establishing module is used to establish a calculation model of a parameter vector based on ridge regression according to historical data collected during the historical control period; wherein the calculation model includes a penalty term;

[0032] A determination module is used to determine a target solution of a penalty term according to the severity of noise in historical data;

[0033] The target module is used to obtain the target penalty term and the target parameter vector according to the target solution to establish the target data driven current prediction model.

[0034] In a third aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program. When the computer program is loaded and executed by a processor, the permanent magnet synchronous motor data-driven predicted current modeling method provided in any one of the first aspects above is implemented.

[0035] In a fourth aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, wherein:

[0036] The memory is used to store computer programs;

[0037] The processor is used to load and execute a computer program so that the electronic device executes the permanent magnet synchronous motor data-driven predictive current modeling method provided in any one of the first aspects above.

[0038] Compared with the prior art, the beneficial effects of this application are:

[0039] The embodiment of the present application proposes a data-driven prediction current modeling method, device, medium and equipment for permanent magnet synchronous motor, the method comprising: obtaining a data-driven current prediction model based on the cross-saturation effect of the target motor; wherein the data-driven current prediction model includes a parameter vector; according to the historical data collected in the historical control cycle, a calculation model of the parameter vector based on ridge regression is established; wherein the calculation model includes a penalty term; according to the noise severity of the historical data, the target solution of the penalty term is determined; according to the target solution, the target penalty term and the target parameter vector are obtained to establish the target data-driven current prediction model. The present application firstly takes into account the influence of the cross-saturation effect on the electromagnetic field in actual situations, obtains the data-driven current prediction model of the motor, and then constructs a calculation model based on ridge regression of the parameter vector in the model through historical data, and then evaluates the severity of the noise in the data, establishes a dynamic adjustment of the ridge parameter, realizes the adaptive penalty of the data noise, determines the target solution of the penalty term and further reverses the parameter vector to obtain the final prediction model, thereby improving the current prediction accuracy under noise conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 Schematic diagram of least squares overfitting caused by noise;

[0041] Figure 2 It is the fitting diagram of ridge regression;

[0042] Figure 3 Schematic diagram of the optimal solution space for ridge regression;

[0043] Figure 4 A schematic diagram of the structure of an electronic device of a hardware operating environment involved in an embodiment of the present application;

[0044] Figure 5 A flow chart of a data-driven prediction current modeling method for a permanent magnet synchronous motor provided in an embodiment of the present application;

[0045] Figure 6 It is a schematic diagram for comparing the waveforms of the dq axis predicted current, the dq axis actual current, and the dq axis predicted current residual based on the least squares method;

[0046] Figure 7 A schematic diagram comparing the dq-axis predicted current, the dq-axis actual current, and the dq-axis predicted current residual waveforms of the permanent magnet synchronous motor data-driven predicted current modeling method provided in an embodiment of the present application;

[0047] Figure 8 It is a comparison diagram of the rotation speed, the actual current of the dq axis, and the a-phase current waveform based on the least squares method;

[0048] Fig. 9A schematic diagram comparing the speed, actual current of the dq axes, and the a-phase current waveform of the permanent magnet synchronous motor data-driven predictive current modeling method provided in an embodiment of the present application;

[0049] Fig.10 A schematic diagram of a module of a data-driven predictive current modeling device for a permanent magnet synchronous motor provided in an embodiment of the present application;

[0050] Markings in the figure: 101 - processor, 102 - communication bus, 103 - network interface, 104 - user interface, 105 - memory. DETAILED DESCRIPTION

[0051] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0052] The main solution provided by the embodiment of the present application is: obtaining a data-driven current prediction model of the target motor based on the cross-saturation effect; wherein the data-driven current prediction model includes a parameter vector; establishing a calculation model of the parameter vector based on ridge regression according to historical data collected during historical control cycles; wherein the calculation model includes a penalty term; determining a target solution for the penalty term according to the severity of noise in the historical data; obtaining a target penalty term and a target parameter vector according to the target solution to establish a target data-driven current prediction model.

[0053] Model predictive control (MPC) has attracted extensive attention in the field of motor drives due to its advantages such as fast dynamic response and strong control flexibility. It is a promising alternative to traditional control methods such as field-oriented control and direct torque control. Traditional MPC is based on the motor model to predict the system behavior, which means that the controller needs accurate motor parameters to achieve satisfactory control performance. However, in actual working conditions, key motor parameters are highly sensitive. For example, the resistance of a permanent magnet synchronous motor (PMSM) may change due to temperature changes, and the value of the inductance may also be affected by magnet saturation and cross-saturation effects. In practical applications, this interference makes it difficult to accurately model the motor and obtain accurate parameters. Therefore, traditional MPC considering fixed motor parameters has parameter mismatch problems, resulting in performance degradation.

[0054] In the context of digitalization, networking and intelligence, data-driven technology has attracted widespread attention due to its deep integration of the concept of new generation information technology and mathematical models, and provides an effective solution for the modeling of strongly coupled time-varying systems. Among them, the least squares technology is widely used in system identification and intelligent control to predict and explain the relationship between variables. In general, different solutions have been proposed to improve the robustness of MPC parameters of PMSM drives. Among them, the least squares method (LS) has been proven to be a potential alternative to traditional MPC. The basic principle of the least squares method is to find the optimal estimate of the model parameters by minimizing the sum of squares of the error between the predicted value and the actual value. The core idea is to make the model's prediction results match the observed data as much as possible. Therefore, this data-based solution can identify a more accurate current prediction model in real time, thereby improving the predictive control performance.

[0055] Anti-interference performance is a key issue facing data-driven technology. Due to the potential noise in current sensor measurements, the reliance of least squares methods on system input and output data poses a challenge. The sources of noise are diverse, including manufacturing errors, temperature changes, and sensor aging. On the other hand, the electromagnetic fields in the working environment of the motor can interfere with the transmission of the signal, resulting in noise in the sampled signal. These interferences can come from the electromagnetic emissions of the motor itself or from electromagnetic interference caused by other equipment. In many industrial applications, motors often operate in environments with significant electromagnetic noise, which can easily couple with the sampled signal, resulting in persistent measurement errors and affecting model performance. Therefore, in order to ensure the robustness of the control system, the uncertainty of the observed data in the least squares method must be considered.

[0056] The schematic diagram of least squares overfitting caused by noise is shown in the attached figure. Figure 1 As shown, the embodiment of the present application applies the ridge regression technology to the field of permanent magnet synchronous motor drive, as shown in the attached Figure 2 The following is a schematic diagram of the ridge regression fitting. Figure 3 The figure shows a schematic diagram of the optimal solution space of ridge regression, which evaluates the severity of noise and applies dynamic ridge coefficient adjustment to achieve adaptive penalty for data noise, thereby improving robustness.

[0057] Therefore, the present application provides a means, firstly, taking into account the influence of electromagnetic cross-saturation effect in actual situations, obtaining the data-driven current prediction model of the motor, and secondly constructing a ridge regression-based calculation model of the parameter vector in the model through historical data, and then evaluating the severity of the noise in the data, establishing a dynamic adjustment of the ridge parameter, realizing adaptive penalty for data noise, determining the target solution of the penalty term and further inferring the parameter vector to obtain the final prediction model, thereby improving the current prediction accuracy under noisy conditions.

[0058] See attached Figure 4 , attached Figure 4 This is a schematic diagram of the structure of an electronic device of the hardware operating environment involved in the embodiment of the present application. The electronic device may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. Among them, the communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 105 may optionally be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed random access memory (RAM) memory, or it may be a stable non-volatile memory (NVM), such as at least one disk storage; the processor 101 may be a general-purpose processor, including a central processing unit, a network processor, etc., or it may be a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component.

[0059] Those skilled in the art will appreciate that Figure 4 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0060] As attached Figure 4 As shown, the memory 105 as a storage medium may include an operating system, a network communication module, a user interface module, and a permanent magnet synchronous motor data driven predictive current modeling device.

[0061] In the attached Figure 4 In the electronic device shown, the network interface 103 is mainly used for data communication with a network server; the user interface 104 is mainly used for data interaction with a user; the processor 101 and the memory 105 in the present application can be set in the electronic device, and the electronic device calls the permanent magnet synchronous motor data-driven predicted current modeling device stored in the memory 105 through the processor 101, and executes the permanent magnet synchronous motor data-driven predicted current modeling method provided in the embodiment of the present application.

[0062] See attached Figure 5Based on the hardware device of the aforementioned embodiment, an embodiment of the present application provides a data-driven prediction current modeling method for a permanent magnet synchronous motor, comprising the following steps:

[0063] S10: Obtaining a data-driven current prediction model of the target motor based on the cross-saturation effect; wherein the data-driven current prediction model includes a parameter vector.

[0064] In the specific implementation process, the target motor is a permanent magnet synchronous motor for which a data-driven current prediction model needs to be established. Cross-saturation refers to the uneven distribution of magnetic flux in the motor magnetic circuit, which causes some magnetic flux lines to reach magnetic saturation at the same time while other lines do not reach saturation. Data-driven refers to the process of using collected, analyzed and interpreted data to guide decision-making, optimize processes and achieve goals.

[0065] In one embodiment, before obtaining the data-driven current prediction model of the target motor based on the cross-saturation effect, the method further includes:

[0066] According to the stator voltage and the stator current in the current control of the target motor, input data and output data are obtained respectively;

[0067] According to the input data, output data and parameter vector, a data driven current prediction model of the target motor based on the cross saturation effect is established.

[0068] In the specific implementation process, in the current control of the permanent magnet synchronous motor, the stator voltage and the stator current are the input and output of the system respectively. The state space considering the cross saturation effect is expressed as:

[0069] y(k+1)=θx(k+1)

[0070]

[0071] Among them, k is the sampling time, x is the regression matrix, u=[u d ,u q ] T is the system input voltage, y=[i d ,i q ] T is the system output current, θ is the parameter vector, a, b and e are the elements in the parameter vector, corresponding to the coefficients of the current term and voltage term under the dq axis and the constant term respectively.

[0072] S20: Establishing a calculation model of a parameter vector based on ridge regression according to historical data collected during the historical control period; wherein the calculation model includes a penalty term.

[0073] In the specific implementation process, the parameter vector is estimated based on the historical data collected in the past multiple control cycles. In the predictive current control environment of the PMSM drive, the dq axis voltage applied in each control cycle is determined by the controller and is therefore stored as input data. On the other hand, the dq axis current sampled at the beginning of each control cycle is stored as output data. That is, the historical data is divided into historical input data and historical output data. According to the historical data collected in the historical control cycle, a calculation model of the parameter vector based on ridge regression is established, including:

[0074] According to the historical data collected during the historical control period, historical input data and historical output data are obtained;

[0075] According to the historical input data and the historical output data, construct the past subset and the future subset respectively;

[0076] According to the past subset and the future subset, a calculation model of the parameter vector based on ridge regression is established.

[0077] In the specific implementation process, the data sets of historical input data and historical output data are respectively denoted as U ds and Y ds , a set of subsets can be constructed to define two past subsets and a future subset for the input and output data:

[0078] U p =[u1 u2 ... u N-1 ]

[0079] U f =[u2 u3 ... u N ]

[0080] Y p =[y1 y2 ... y N-1 ]

[0081] Y f =[y2 y3 ... y N ]

[0082] The subscripts p and f represent the past and future respectively. p is the past subset of historical input data, U f is the future subset of historical input data, Y p is the past subset of historical output data, Y f For the future subset of historical output data, the number of columns of these matrices is N-1. At sampling time k, based on the collected data, the calculation formula of the ridge regression parameter vector θ can be established, that is, the calculation model:

[0083] θ=Y f H T (HHT +λI) -1

[0084] in:

[0085]

[0086] I is the identity matrix, H T is the transpose of H. If HH T is a singular matrix, then adding a λI term ensures that HH T +λI is full rank, making the matrix invertible while suppressing the influence of noise.

[0087] In one embodiment, a calculation model of a parameter vector based on ridge regression is established according to the past subset and the future subset, including:

[0088] Based on the past subset and the future subset, the parameter vector is estimated by applying the solution of the least square method to establish a computational model of the parameter vector based on ridge regression.

[0089] In the specific implementation process, the constructed past subset and future subset are used to apply the least squares solution to estimate the parameter vector. Generally speaking, the goal of least squares is to achieve global fitting optimization, which can give accurate unbiased estimates without noise. However, data is not always ideal in practical applications. In permanent magnet synchronous motor drives, measurement noise is generated due to current induction. This noise effect is more prominent in some low-speed and low-load conditions. In this case, data noise can cause multicollinearity problems. Traditional least squares methods can lead to unreliable results due to overfitting. Therefore, the sensitivity of least squares to noisy data will reduce the current prediction accuracy of PMSM drives. Ridge regression is introduced to solve the above multicollinearity problem. By adding a regularization term to the loss function, the problem of high correlation between independent variables is solved, making the prediction performance of the model more stable:

[0090] In traditional LS regression, the loss function J is defined as:

[0091] J(θ)=||Y f -θH|| 2

[0092] In the ridge regression model, the L2 norm penalty term is added to the loss function to solve the multicollinearity problem

[0093] J(θ)=||Y f -θH|| 2 +λ||θ 2

[0094] Among them, λ∈[0,∞] is the ridge coefficient for adjusting the penalty. The main idea of ​​ridge regression is to add an additional penalty reduction term to the traditional LS loss function, and then narrow the optimal solution space. The above formula can be further written as:

[0095] J(θ)=(Y f -θH) T (Y f -θH)+λθ T θ

[0096] =Y f T Y f -Y f T θH-H T θ T Y f +H T θ T θH+λθ T θ

[0097] To minimize J(θ), the relation Find the minimum point, and then derive the following relationship:

[0098] 0-H T Y f -H T Y+2HH T θ+2λθ=0

[0099] The parameter vector under ridge regression can be expressed as:

[0100] θ=Y f H T (HH T +λI) -1

[0101] S30: Determine a target solution for the penalty term based on the severity of the noise in the historical data.

[0102] In the specific implementation process, the final solution of the model is converted into the final solution of the parameter vector by establishing a prediction model, and then adjusted according to the severity of the noise, and the final solution of the model is converted into the final solution of the penalty term. Specifically: According to the severity of the noise of the historical data, the target solution of the penalty term is determined, including:

[0103] According to the positive correlation between multicollinearity and the severity of noise in historical data, the relationship between multicollinearity and penalty term is obtained;

[0104] The relationship between multicollinearity and penalty terms is mapped based on the mapping function, and the target solution of the penalty term is determined.

[0105] In the specific implementation process, the ridge coefficient is introduced to compensate for the multicollinearity caused by data noise. Since multicollinearity is positively correlated with the severity of data noise, the larger the multicollinearity, the larger the λ should be used to increase the penalty intensity. Therefore, the penalty intensity λ is related to the multicollinearity severity VIF. iq The relationship between can be mapped by a sigmoid function. Therefore, the optimal λ, that is, the target solution of the penalty term, can be obtained online based on the evaluation results of data noise, and the relationship is given as:

[0106]

[0107] Among them, e is a natural constant, and α and β are fixed coefficients used to stretch the sigmoid function horizontally and vertically. The optimal values ​​of α and β can be searched by offline cross-validation of experimental data to skip the undesirable penalty range with relatively low severity of multicollinearity and limit the penalty intensity to an appropriate range.

[0108] In one embodiment, before determining the target solution of the penalty term according to the noise severity of the historical data, the method further includes:

[0109] Construct matrices for the data corresponding to the input data and output data in the historical data;

[0110] According to the matrix, the residual sum of squares and the total sum of squares are obtained;

[0111] According to the residual sum of squares and the total sum of squares, the multicollinearity of the input data is obtained to characterize the severity of the noise of the historical data.

[0112] In the specific implementation process, in the data-driven current prediction model, the elements i in the input voltage and output current are involved. d 、i q 、u d and u q . Collect the data corresponding to each variable into a matrix, which can be represented as X, and then we can calculate i q The regression coefficient b is:

[0113]

[0114] Among them, X iq For X containing i q The row of data, X no_iq For not containing i q The remaining rows of data, and X iq and X no_iq The matrix transpose of . Then we get i qThe correlation coefficient with other variables. The residual sum of squares SSR can be expressed as:

[0115]

[0116] in, for The average value of the data. The total sum of squares SST can be expressed as:

[0117]

[0118] Therefore, q The variance inflation factor VIF can be expressed as

[0119]

[0120] Among them, R 2 =SSR / SST.

[0121] The VIF value indicates the severity of multicollinearity associated with data noise, that is, based on the residual sum of squares and the total sum of squares, the multicollinearity of the input data is obtained to characterize the severity of noise in the historical data, including:

[0122] According to the residual sum of squares and the total sum of squares, the variance inflation factor of the input data is obtained to measure the multicollinearity of the input data to characterize the severity of the noise of the historical data.

[0123] When VIF exceeds the threshold, traditional LS regression will be unreliable, and ridge regression is introduced to improve prediction accuracy. In the embodiment of the present application, the average value of VIF is used to evaluate the severity of data noise.

[0124] S40: Obtain a target penalty term and a target parameter vector according to the target solution to establish a target data driven current prediction model.

[0125] In the specific implementation process, according to the above steps, by determining the target solution of the penalty term, the penalty term can be determined and then the target solution of the parameter vector, that is, the target parameter vector, can be obtained by reverse calculation. Then the parameter vector in the initially established model is updated to obtain the final target data-driven current model.

[0126] In this embodiment, firstly, the influence of electromagnetic cross-saturation effect in actual situation is taken into consideration to obtain the data-driven current prediction model of the motor, and then a ridge regression-based calculation model of the parameter vector in the model is constructed through historical data. Then, by evaluating the severity of the noise in the data, a dynamic adjustment of the ridge parameter is established to achieve adaptive penalty for data noise, determine the target solution of the penalty term, and further infer the parameter vector to obtain the final prediction model, thereby improving the current prediction accuracy under noise conditions.

[0127] In order to verify the effectiveness of the method provided in the embodiment of the present application, the ridge regression and the least square method are compared under different noise levels, and the comparison of the dq axis predicted current residuals is shown in Table 1:

[0128] Table 1 Comparison of prediction residual variance at 300 rpm

[0129]

[0130] Among them: Under different noise levels, the prediction residuals of the present application method on the two indicators of rd(A) and rq(A) are significantly smaller than those of the traditional methods (MPC and LS), reflecting higher prediction accuracy and robustness. Furthermore, as data-driven methods, the LS method and the present application method can accurately identify the current prediction model online, and have significant advantages over the model-based MPC method without adding additional noise (var=0) and in low noise conditions (var=0.02). However, as the noise level increases (var=0.05), due to the negative impact of noise on the prediction model, the prediction residual of the LS method is greater than that of the MPC method, while the present application method can still maintain a significant advantage under the same conditions.

[0131] See attached Figure 6 -Attached Fig. 9 , is a comparison between the least squares method and the method provided in the embodiment of the present application, wherein, Figure 6 It is a schematic diagram for comparing the waveforms of the dq axis predicted current, the dq axis actual current, and the dq axis predicted current residual based on the least squares method. Figure 7 A schematic diagram comparing the dq-axis predicted current, the dq-axis actual current, and the dq-axis predicted current residual waveforms of the permanent magnet synchronous motor data-driven predicted current modeling method provided in an embodiment of the present application, Figure 8 This is a comparison diagram of the speed, actual current of the dq axis, and the a-phase current waveform based on the least squares method. Fig. 9 A comparative schematic diagram of the speed, actual current of the dq axes, and the a-phase current waveform of the permanent magnet synchronous motor data-driven predicted current modeling method provided in the embodiment of the present application. Among them, Measured represents the actual measured data, and Predicted represents the predicted data. From the comparison of the accompanying drawings, it can be seen that under the working condition of noise interference, the method of the present application has better predicted current performance than the traditional least squares modeling, which is reflected in the predicted current closed-loop control, the current ripple is reduced, and the robustness is improved.

[0132] See attached Fig.10 Based on the same inventive concept as in the above-mentioned embodiment, the embodiment of the present application further provides a data-driven prediction current modeling device for a permanent magnet synchronous motor, comprising:

[0133] An acquisition module, the acquisition module is used to obtain a data-driven current prediction model of a target motor based on a cross-saturation effect; wherein the data-driven current prediction model includes a parameter vector;

[0134] Establishing a module, the establishing module is used to establish a calculation model of a parameter vector based on ridge regression according to historical data collected during the historical control period; wherein the calculation model includes a penalty term;

[0135] A determination module is used to determine a target solution of a penalty term according to the severity of noise in historical data;

[0136] The target module is used to obtain the target penalty term and the target parameter vector according to the target solution to establish the target data driven current prediction model.

[0137] Those skilled in the art should understand that the division of the various modules in the embodiment is only a division of logical functions, and can be fully or partially integrated into one or more actual carriers in actual application, and these modules can be all implemented in the form of software called by the processing unit, or all implemented in the form of hardware, or implemented in the form of a combination of software and hardware. It should be noted that the modules in the permanent magnet synchronous motor data-driven predicted current modeling device in this embodiment correspond one by one to the steps in the permanent magnet synchronous motor data-driven predicted current modeling method in the aforementioned embodiment. Therefore, the specific implementation method of this embodiment can refer to the implementation method of the aforementioned permanent magnet synchronous motor data-driven predicted current modeling method, which will not be repeated here.

[0138] Based on the same inventive concept as in the aforementioned embodiments, an embodiment of the present application also provides a computer-readable storage medium storing a computer program. When the computer program is loaded and executed by a processor, a permanent magnet synchronous motor data-driven predicted current modeling method as provided in an embodiment of the present application is implemented.

[0139] Based on the same inventive concept as in the above-mentioned embodiment, an embodiment of the present application further provides an electronic device, including a processor and a memory, wherein:

[0140] The memory is used to store computer programs;

[0141] The processor is used to load and execute a computer program so that the electronic device executes the permanent magnet synchronous motor data-driven predictive current modeling method provided in the embodiment of the present application.

[0142] In some embodiments, the computer readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories. The computer may be various computing devices including intelligent terminals and servers.

[0143] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0144] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0145] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices located at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0146] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0147] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0148] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a multimedia terminal device (which can be a mobile phone, a computer, a television receiver, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0149] In summary, the present application provides a data-driven prediction current modeling method, device, medium and equipment for permanent magnet synchronous motor, the method comprising: obtaining a data-driven current prediction model of the target motor based on the cross-saturation effect; wherein the data-driven current prediction model includes a parameter vector; according to the historical data collected during the historical control cycle, a calculation model of the parameter vector based on ridge regression is established; wherein the calculation model includes a penalty term; according to the noise severity of the historical data, the target solution of the penalty term is determined; according to the target solution, the target penalty term and the target parameter vector are obtained to establish the target data-driven current prediction model. The present application firstly takes into account the influence of the cross-saturation effect on the electromagnetic field in actual situations, obtains the data-driven current prediction model of the motor, and then constructs a ridge regression-based calculation model of the parameter vector in the model through historical data, and then evaluates the severity of the noise in the data, establishes a dynamic adjustment of the ridge parameter, realizes the adaptive penalty of the data noise, determines the target solution of the penalty term and further reverses the parameter vector to obtain the final prediction model, thereby improving the current prediction accuracy under noise conditions.

[0150] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A data-driven prediction current modeling method for a permanent magnet synchronous motor, characterized in that: The following steps are involved: Obtaining a data driven current prediction model of a target motor based on a cross saturation effect; wherein the data driven current prediction model includes a parameter vector; According to the historical data collected during the historical control period, a calculation model of the parameter vector based on ridge regression is established; wherein the calculation model includes a penalty term; Determining a target solution for the penalty term according to the noise severity of the historical data; A target penalty term and a target parameter vector are obtained according to the target solution to establish a target data driven current prediction model.

2. The data-driven prediction current modeling method for a permanent magnet synchronous motor according to claim 1 is characterized in that: Before determining the target solution of the penalty term according to the noise severity of the historical data, the method further includes: Construct matrices for the data corresponding to the input data and the output data in the historical data respectively; According to the matrix, the residual sum of squares and the total sum of squares are obtained; The multicollinearity of the input data is obtained according to the residual sum of squares and the total sum of squares to characterize the severity of noise of the historical data.

3. The data-driven prediction current modeling method for a permanent magnet synchronous motor according to claim 2 is characterized in that: The step of determining a target solution of the penalty term according to the noise severity of the historical data includes: According to the positive correlation between the multicollinearity and the noise severity of the historical data, the relationship between the multicollinearity and the penalty term is obtained; The relationship between the multicollinearity and the penalty term is mapped based on a mapping function, and a target solution for the penalty term is determined.

4. The data-driven prediction current modeling method for a permanent magnet synchronous motor according to claim 2 is characterized in that: The step of obtaining the multicollinearity of the input data according to the residual sum of squares and the total sum of squares to characterize the severity of noise in the historical data includes: According to the residual sum of squares and the total sum of squares, the variance inflation factor of the input data is obtained to measure the multicollinearity of the input data to characterize the severity of the noise of the historical data.

5. The data-driven prediction current modeling method for a permanent magnet synchronous motor according to claim 1, characterized in that: Before obtaining the data-driven current prediction model of the target motor based on the cross-saturation effect, the method further includes: According to the stator voltage and the stator current in the current control of the target motor, respectively obtaining input data and output data; A data driven current prediction model of the target motor based on the cross saturation effect is established according to the input data, the output data and the parameter vector.

6. The data-driven prediction current modeling method for a permanent magnet synchronous motor according to claim 1, characterized in that: The method of establishing a calculation model of the parameter vector based on ridge regression according to the historical data collected during the historical control period includes: According to the historical data collected during the historical control period, historical input data and historical output data are obtained; According to the historical input data and the historical output data, construct a past subset and a future subset respectively; A calculation model of the parameter vector based on ridge regression is established according to the past subset and the future subset.

7. The data-driven prediction current modeling method for a permanent magnet synchronous motor according to claim 6 is characterized in that: The step of establishing a calculation model of the parameter vector based on ridge regression according to the past subset and the future subset includes: The parameter vector is estimated by applying a solution of the least square method based on the past subset and the future subset to establish a computational model of the parameter vector based on ridge regression.

8. A data-driven prediction current modeling device for a permanent magnet synchronous motor, characterized in that: include: An acquisition module, the acquisition module is used to obtain a data-driven current prediction model of a target motor based on a cross-saturation effect; wherein the data-driven current prediction model includes a parameter vector; An establishment module, the establishment module is used to establish a calculation model of the parameter vector based on ridge regression according to historical data collected during the historical control cycle; wherein the calculation model includes a penalty term; A determination module, the determination module is used to determine a target solution of the penalty term according to the noise severity of the historical data; A target module is used to obtain a target penalty term and a target parameter vector according to the target solution to establish a target data driven current prediction model.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is loaded and executed by the processor, the permanent magnet synchronous motor data-driven predictive current modeling method as described in any one of claims 1-7 is implemented.

10. An electronic device, characterized in that: comprising a processor and a memory, wherein: The memory is used to store computer programs; The processor is used to load and execute the computer program so that the electronic device executes the permanent magnet synchronous motor data-driven predictive current modeling method according to any one of claims 1 to 7.

Images