A multi-objective optimization method and its control system for a five-phase permanent magnet motor

Abstract

The present invention discloses a multi-objective optimization method and its control system for a five-phase permanent magnet motor, belonging to the technical fields of motor body design optimization and motor control technology. The multi-objective optimization method for the five-phase permanent magnet motor of the present invention obtains the optimal optimization values of motor parameters based on genetic aggregation response surface and multi-objective genetic algorithm, comprehensively considers motor design variables and improves optimization accuracy; a control system for a five-phase permanent magnet fault-tolerant motor proposed by the present invention uses iterative learning control as a current control technology to restore the performance of the five-phase permanent magnet motor under fault conditions, and combines the advantages of iterative learning control and back electromotive force control, can ensure the high-performance operation of the motor under fault conditions, achieve ripple-free torque output, and minimize ohmic losses; the fault diagnosis module of the control system uses a time series neural network and a Kalman filter to diagnose short-circuit faults and open-circuit faults, and has real-time performance and strong adaptability.

Description

Technical Field

[0001] The present invention relates to the technical fields of motor body design optimization and motor control technology, and particularly relates to a multi-objective optimization method for a five-phase permanent magnet synchronous motor and its control system. Background Art

[0002] Five-phase permanent magnet motors play an important role in many industrial applications. However, during their design process, multiple objectives need to be considered simultaneously, such as average torque, efficiency, and torque ripple, to improve the performance of the motor. Traditional optimization methods have problems such as high computational cost, low accuracy, or difficulty in finding the global optimal solution.

[0003] In addition to the optimization method for the motor body design, the safety and reliability of the electric drive system are also crucial for the motor. During the operation of a five-phase permanent magnet motor, short-circuit or open-circuit faults may occur, which will seriously affect the performance and reliability of the motor and even cause the system to stop. Therefore, fault diagnosis and fault-tolerant control are essential to ensure the safe and reliable operation of the five-phase permanent magnet motor.

[0004] Traditional fault diagnosis methods have problems such as being vulnerable to noise interference, being insensitive to early fault diagnosis, and difficult feature extraction. In response to this, in recent years, some new fault diagnosis methods have been proposed by various universities and research institutes, but there are still more or less problems. For example, the document "A Method for Diagnosing Inter-turn Short Circuit Faults in Five-Phase Permanent Magnet Motors" (authorized publication number: CN116626491B) discloses a method for diagnosing inter-turn short circuit faults in five-phase permanent magnet motors using a multi-scale convolutional residual network with an attention mechanism. Although it has relatively high diagnostic accuracy, it relies on the Bayesian optimization algorithm to automatically select the optimal hyperparameter combination, there is a risk of unstable algorithm convergence, and its use of a specific equally spaced sliding window data augmentation method to extract features has certain limitations and cannot adapt to all data characteristics and fault modes.

[0005] Therefore, a fault diagnosis method that can overcome existing defects, has real-time performance, and high computational efficiency is needed to determine the fault type and perform fault-tolerant control. Five-phase permanent magnet motors have advantages in fault-tolerant operation, but traditional fault-tolerant control schemes have limitations. They usually need to rely on an accurate back-electromotive force model and complex fault detection, and need to consider torque and current measurement errors, etc. Therefore, learning and repetitive control algorithms have gradually attracted attention. Among them, iterative learning control has great potential in dealing with periodic torque ripple under motor fault conditions, providing a new idea for the fault-tolerant control of motors. Summary of the Invention

[0006] Aiming at the deficiencies of the existing technology in the above background art, the purpose of the present invention is to provide a multi-objective optimization method and its control system for a five-phase permanent magnet motor, so as to solve the problems of high calculation cost, low accuracy, and difficulty in finding the global optimal solution of the five-phase permanent magnet motor optimization method, and improve the safety and reliability of the five-phase permanent magnet motor control system.

[0007] The technical solution for achieving the purpose of the present invention is as follows:

[0008] A multi-objective optimization method for a five-phase permanent magnet motor, the multi-objective optimization method for the five-phase permanent magnet motor includes the following steps:

[0009] Step S1-1: Define the optimization objectives of the five-phase permanent magnet motor, including average torque, efficiency, and torque ripple performance parameters, and determine the corresponding objective functions and constraint conditions; the objective functions are used to maximize efficiency, minimize torque ripple, and increase average torque; the constraint conditions include the number of turns of the stator winding, the thickness of the permanent magnet, the air gap length, the number of rotor pole pairs, inductance, and resistance;

[0010] Step S1-2: On the basis of the optimization objectives, use the central composite design method to generate sample points, determine the number and positions of the design points, and record the data of the relevant parameters of each design point;

[0011] Step S1-3: Use GARS to perform sensitivity analysis on the generated sample points, quantify the sensitivity of the motor response to each design feature, and evaluate the sensitivity index of the design variables to the optimization objectives; the GARS is a genetic aggregation response surface; the design features are various factors affecting the motor performance, including the outer diameter of the stator, the thickness of the permanent magnet, the air gap length, the centrifugal height, and the slot opening depth; the design variables are the specific parameters that quantify these design features;

[0012] Step S1-4: For the results of the sensitivity analysis, construct a response surface model based on the weighted average of GARS. This model contains multiple different meta-models to accurately describe the relationship between the design variables in the design space; through the response surface model, characterize the influence of different design variable combinations on the optimization objectives, and provide a basis for multi-objective optimization; the design space is a set composed of the value ranges of all design variables;

[0013] Step S1-5: Based on the NSGA-II algorithm, perform multi-objective optimization on the average torque, efficiency, and torque ripple of the five-phase permanent magnet motor, generate a non-dominated solution set under the satisfaction of the constraint conditions, achieve the balance of the optimization objectives, and verify the optimization results through finite element analysis; the NSGA-II is a non-dominated genetic algorithm.

[0014] Further, the central composite design method in step S1-2 specifically includes the following steps:

[0015] Step S1-2-1: Determine the design variables related to the performance of the five-phase permanent magnet motor and their value ranges;

[0016] Step S1-2-2: Select the design points for the center point, axial points, and star points; the center point is located at the center of the design space and is used to estimate the experimental error to determine the performance of the reference motor; the axial points are located at the boundaries of the value ranges of the design variables to ensure full consideration of the boundary conditions of the motor performance; the star points are determined by setting the positions of the star arms and are used to estimate the non-linear response of the design variables and evaluate the influence of the curvature of the design variables on the motor performance;

[0017] Step S1-2-3: Generate corresponding sample points based on the design points of the center point, axial points, and star points selected in Step S1-2-2; the sample points can cover the design space and are used for experiments and simulations to obtain motor performance data, and then analyze the relationship between the design variables and the motor performance to provide data support for motor optimization.

[0018] Further, in Step S1-3, the minimum-maximum search algorithm is used to search for the minimum and maximum values of each output parameter and its corresponding input parameters to comprehensively evaluate the response values of all variables, so as to evaluate the influence of the design variables on the sensitivity index of the output parameters;

[0019] Further, the functional relationship between the global objective function and the constraint function in the response surface design space in Step S1-4 is:

[0020]

[0021] where y(x) represents the relationship between the global objective function and the constraint function, represents the basic function, α i represents the weighting parameter, N m represents the number of metamodels;

[0022] The response surface model solves the complex non-linear relationship between the design variables and the average efficiency, torque, and torque ripple through the quadratic approximation method. The prediction of the i-th response of the response surface model is expressed as:

[0023]

[0024] where, represents the predicted value of the i-th response, a0 represents the reference value of the response variable when all independent variables are zero, a i represents the degree of linear influence of the i-th independent variable on the response, a ii represents the degree of non-linear influence of the square term of the i-th independent variable on the response, a ijrepresents the influence degree of the interaction between the $i$-th independent variable and the $j$-th independent variable on the response, and all $a$ are determined by least squares regression:

[0025] $a=(X^{ T X)^{ -1 X^{ T y^{

[0026] The GARS used in the steps S1 - 4 is represented as a set by the weighted average of several different meta - models:

[0027]

[0028] where $w^{ i satisfies:

[0029]

[0030] Furthermore, the NSGA - II algorithm in the step S1 - 5 includes the following steps:

[0031] Step S1 - 5 - 1: Generate the parent population $P_0$ with a size of $N^{ P ; then, generate the offspring population $Q_0$ through crossover and mutation operations; the subsequent stage is represented as the $n$-th generation;

[0032] Step S1 - 5 - 2: Generate the combined population $R^{ n =P^{ n \cup Q^{ n , and the size of the population $R^{ n is $2N^{ P ;

[0033] Step S1 - 5 - 3: Decode the combined population $R^{ n and determine the fitness of the objective function; sort the population $R^{ n using the non - dominated solution sets $L_1$, $L_2$, $L_3$; the solutions belonging to the best non - dominated solution set $L_1$ are the best solutions, followed by the solutions in the set $L_2$, and the solutions selected from the set $L_3$ are ranked last;

[0034] Step S1 - 5 - 4: When the total number of members in the selected set is equal to or exceeds $N^{ P , select the initial set; calculate the crowding distance of each member in the selected set; for the next generation $P^{ n +1$, select the first $k_1$ sets according to the elitist principle; sort the $k$-th set according to the crowding distance, select the members with larger crowding distances and add them to the $P^{ n +1$ generation until the population reaches $N^{ P; The elitist principle is a commonly used strategy in genetic algorithms, aiming to retain individuals with higher fitness in each generation to ensure that excellent genes can be passed on to the next generation, thereby accelerating the convergence speed of the algorithm and improving its performance;

[0035] The rule for selecting the initial set is given by the following formula:

[0036] g < h, if (g rank < h rank ) or (g rank < h rank and (g dist < h dist ))

[0037] where g and h represent two individuals used for comparison and selection in the algorithm, and g rank and h rank represent the non - dominated ranks of members g and h respectively, and g dist and h dist represent the crowding distances of members g and h respectively;

[0038] Step S1 - 5 - 5: If the iteration number limit is reached, the program ends and the fitness of the objective function and the non - dominated solutions are found; if not, go to step S1 - 5 - 6;

[0039] Step S1 - 5 - 6: Perform crossover and mutation operations on the new population P n +1 to generate a new population Q n +1, then go to step S1 - 5 - 2, and loop through steps S1 - 5 - 2 to S1 - 5 - 5 until the fitness of the objective function and the non - dominated solutions are output.

[0040] A control system for controlling a five - phase permanent - magnet motor optimized by the multi - objective optimization method includes: a data acquisition module, a signal processing module, a rectifier, an inverter, a fault diagnosis module, a back - electromotive force model module, an iterative learning controller module, a current controller module, and a five - phase permanent - magnet motor;

[0041] The stator of the five - phase permanent - magnet motor uses a pole - slot combination of 10 slots and 8 poles, the winding is a double - layer fractional - slot concentrated winding structure, and the rotor is a surface - mounted permanent - magnet rotor structure with magnets using a centrifugal structure;

[0042] The control strategy of the five - phase permanent - magnet motor control system includes the following steps:

[0043] Step S5-1: In the data acquisition module, the signal parameter values of the five-phase permanent magnet motor are obtained in real time, including the current, voltage, rotor position, and torque signals of each phase. The stray magnetic flux around the motor is monitored by a fluxgate sensor, and the back electromotive force of the motor under different states is obtained through two-dimensional finite element operation on the motor. Finally, the collected data is subjected to filtering and normalization preprocessing operations;

[0044] Step S5-2: The collected current signal parameters are input into the signal processing module, and the alternating components of the current on the αβ coordinate axes are obtained through coordinate transformation, and the transformed current is preprocessed; the preprocessing includes normalization processing and window segmentation;

[0045] Step S5-3: The preprocessed current is input into the fault diagnosis module, and the current is predicted respectively through the transformer neural network and the model-based method and compared with the actual current to judge the operating state of the motor; the operating states include normal operating state, open-circuit fault state, and short-circuit fault state;

[0046] Step S5-4: When the motor operates in a fault state, an electromotive force model module is established according to the back electromotive force signal in Step S5-1. According to different objective functions of open-circuit faults and short-circuit faults, the optimal current value is calculated to provide the initial optimal reference current;

[0047] Step S5-5: The iterative learning controller module updates the torque error calculated according to the optimal reference current in Step S5-4 and the torque signal in Step S5-1 and the healthy phase current;

[0048] Step S5-6: The updated current is input into the current controller, so as to generate the gate drive signal of the voltage source inverter, so that the stator phase current can follow the optimal reference current;

[0049] Step S5-7: Through two-dimensional finite element analysis of the motor, the torque ripple, current distribution, and ohmic loss data of the motor under different fault conditions are obtained, and the data is used to evaluate the effect of the control scheme.

[0050] Furthermore, the fault diagnosis module in Step S5-3 includes a short-circuit fault diagnosis module and an open-circuit fault diagnosis module;

[0051] The overall process of the short - circuit fault diagnosis module is as follows: Input the pre - processed current signal into the diagnosis model based on TNN. The diagnosis model includes multiple encoders, and each encoder includes an MHA module and an FF module; encode the input signal through the MHA module and the FF module. After hierarchical processing by multiple encoders, an output tensor is obtained; use the output tensor to estimate the number of short - circuited coils and the short - circuit current, then use the third - harmonic component of stray magnetic flux to detect and locate the short - circuit fault. Finally, comprehensively estimate the number of short - circuited coils, the amplitude of the short - circuit current, and the analysis result of stray magnetic flux to judge the short - circuit fault and its degree; the TNN is a transformer neural network module, the MHA is a multi - head attention module, and the FF is a fully - connected feed - forward network module;

[0052] The calculation process of the MHA module is as follows:

[0053] Step S6 - 1 - 1: Through linear transformation of the input sequence, obtain the query matrix Q = XW Q 、the key matrix K = XW K and the value matrix V = XW V , where is the input vector matrix, is the trainable weight matrix, d feat is the number of input features, T m is the time step;

[0054] Step S6 - 1 - 2: Calculate the self - attention according to the formula, and its function is used to normalize the attention scores;

[0055] Step S6 - 1 - 3: Calculate through multiple parallel self - attention layers, that is, multiple heads, and splice and linearly transform the results to obtain the output of the MHA module;

[0056] The FF module specifically includes two linear transformation layers, and residual connection and normalization are performed before and after each linear layer respectively;

[0057] The calculation process of the FF module is as follows:

[0058] Step S6 - 2 - 1: The input of the first linear transformation layer is X e ', and the output is GELU(X e 'W FF1 +b FF1 ), where is the trainable weight of the fully - connected feed - forward network, is the bias of the fully - connected feed - forward network, and GELU is the Gaussian error linear unit activation function;

[0059] Step S6-2-2: The input of the second linear transformation layer is the output of the first linear transformation layer, and the output is GELU(X e 'W FF1 +b FF1 )W FF2 +b FF2 , where are the trainable weights of the fully connected feedforward network, are the biases of the fully connected feedforward network;

[0060] The overall process of the open - circuit fault diagnosis module is as follows: Use a model - based method for fault detection, specifically including using an extended Kalman filter to estimate the current of the motor and establishing a discretized state - space model;

[0061] The open - circuit fault diagnosis steps are as follows:

[0062] Step S6-3-1: Use an extended Kalman filter to estimate the current of the motor;

[0063] Step S6-3-2: Establish a discretized state - space model, which is divided into a prediction module and an update module:

[0064] In the prediction module: is the state estimate value from time k - 1 to time k; where is the state estimate value at time k - 1, u k-1 is the input at time k - 1; is the state transition function, is the estimated error covariance matrix from time k - 1 to time k, where I is the identity matrix, is the system matrix, where L d , L q are the direct - axis inductance and quadrature - axis inductance respectively, λ PM is the permanent - magnet flux linkage, T s is the sampling time, F k is the Jacobian matrix of A, P k-1|k-1 is the estimated error covariance matrix at time k - 1, Q k-1 is the covariance matrix of the process noise;

[0065] In the update module: is the Kalman gain, where H k is the measurement matrix, R k is the covariance matrix of the measurement noise; is the updated state estimate value at time k, where h(x) is the measurement function, y k is the measurement value at time k; P k|k =(I - K k Hk )P k|k-1 is the estimated error covariance matrix updated at time k; where x = [i d i q T , u = [V d V q ω e T , h(x (k) ) = Cx (k) , i d and i q are the direct-axis current and quadrature-axis current respectively, V d , V q are the direct-axis voltage and quadrature-axis voltage, ω e is the electrical angular velocity, is the transformation matrix; calculate the residual: and apply it to the CUSUM algorithm for fault detection. The CUSUM algorithm detects the occurrence of faults by accumulating the changes in the residuals; at the same time, use the whiteness test to judge whether the sensor is faulty. The whiteness test calculates the autocorrelation function of the residuals and the normalized ACF: where N is the number of data samples, ε t is the residual at time t, is the mean value of the residuals; if the residual exceeds the set threshold or the whiteness test shows an anomaly, it is judged that there is a fault; the CUSUM algorithm is the cumulative sum algorithm.

[0066] Further, the optimal current in step S5-4 is obtained by first taking the electromagnetic torque with no ripple and minimum ohmic loss generated under fault conditions as the optimization goal, and then using a closed-form equation to calculate the reference optimal current according to the back electromotive force model under the influence of the fault type represented by the look-up table;

[0067] The calculation of the optimal current in the open-circuit fault case is as follows:

[0068] The objective function for minimizing the ohmic loss is:

[0069]

[0070] where represents the phase current vector, k represents the back electromotive force vector with speed normalization, T* represents the desired torque, F represents the fault matrix, whose elements are used to represent the constraints imposed by the stator winding connection and the fault location, and p1 and p2 are the Lagrange multipliers;

[0071] The optimal current for the open-circuit fault is found to be:

[0072] ​​

[0073] Among them, F -1 is the left inverse of the matrix, defined as F -1 =(F T F) -1 F T , and F' is given by F'=(I n -FF l -1 );

[0074] The optimal current calculation under the short-circuit fault condition is as follows:

[0075] Extend the open-circuit fault tolerance control to the short-circuit fault, and the modified objective function is defined as:

[0076]

[0077] Among them, i sc is a new parameter introduced considering the influence of the short-circuit current;

[0078] The optimal current for the short-circuit fault is found as:

[0079]

[0080] Among them, F τ -T is the right inverse of the matrix, defined as F τ -T =F(F T F) -1 , and i sc represents that the short-circuit related current is equal to zero during healthy operation and is given by during a single-phase fault.

[0081] Furthermore, the specific method for updating the current in step S5-5 is to calculate based on the system equation, motor equation performance, error signal, and learning algorithm, and suppress the torque ripple with reference to the current update rule;

[0082] The system equation is:

[0083] y j (m)=P(q)u j (m)+d(m)

[0084] where m is the time index, j is the iteration index, q is the forward time shift operator qx(m)=x(m + 1), y j is the output, u j is the control input, and d is the repeated exogenous signal;

[0085] The motor equation is:

[0086] T m =kT i + T d

[0087] wherein, T m represents the output torque, and T d represents the oscillating torque disturbance;

[0088] The error signal is:

[0089] e j (m) = y d (m) - y j (m)

[0090] wherein, y d is the desired output;

[0091] The learning algorithm is:

[0092] u j+1 (m) = Q(q)[u j (m) + L(q)e j (m + 1)]

[0093] wherein, Q(q) and L(q) are respectively defined as the Q filter and the learning function, and e j = T* - T m,j , T m,j represents the motor output torque at the j-th iteration, and T* represents the desired torque;

[0094] The iterative learning current update formula is:

[0095] i * ILC,j+1 = i * ILC,j + β(F'k(k T F'k) -1 )(T* - T m,j )j

[0096] wherein, i * ILC,j represents the iterative learning current reference at the j-th iteration, and β is a constant.

[0097] Furthermore, the steps for the current controller in step S5 - 6 to achieve current tracking are as follows:

[0098] Step S5 - 6 - 1: The current controller monitors the actual value of the stator phase current in real time and compares it with the optimal reference current;

[0099] Step S5 - 6 - 2: According to the comparison result, the current controller adjusts the gate drive signal to ensure that the stator phase current quickly and accurately tracks the optimal reference current.

[0100] Further, the steps of the two-dimensional finite element analysis method in step S5-7 are as follows:

[0101] Step S5-7-1: Establish a two-dimensional geometric model according to the number of stator slots, inner diameter, outer diameter, rotor size, permanent magnet position, and size parameters in the actual structure of the motor.

[0102] Step S5-7-2: Define the material properties of each part of the motor, including the material of the stator core, permanent magnet, and winding.

[0103] Step S5-7-3: Perform mesh division on the model, and discretize the geometric model into 20,000 elements according to the accuracy requirements and calculation time limit.

[0104] Step S5-7-4: Apply boundary conditions to the geometric model, define the external boundary of the motor as a magnetic insulation boundary condition, simulate the air environment around the motor, apply permanent magnet excitation and updated current excitation to the motor to achieve fault tolerance control.

[0105] Step S5-7-5: Use the two-dimensional finite element method to solve the partial differential equation of the motor electromagnetic field, obtain the distribution of electromagnetic field quantities inside the motor, including magnetic field distribution and magnetic flux density, so as to obtain torque ripple, current distribution, and ohmic loss data.

[0106] Compared with the prior art, the multi-objective optimization method and its control system for a five-phase permanent magnet motor of the present invention have the following beneficial effects:

[0107] 1. The multi-objective optimization method for a five-phase permanent magnet motor proposed by the present invention uses GARS for sensitivity analysis, which can more reliably determine important design factors, construct an accurate response surface model, and thus provide more accurate guidance for optimization. Compared with traditional methods, GARS takes into account the interaction between design variables, and through numerous response surfaces and cross-validation procedures, improves the reliability of the optimization design model.

[0108] 2. The multi-objective optimization method for a five-phase permanent magnet motor proposed by the present invention selects the NSGA-II algorithm for optimization. This algorithm performs better in finding multiple solutions and converging to the exact Pareto optimal set, can find a wider range of design solutions, and provides more choices for the design of five-phase permanent magnet motors.

[0109] 3. The fault diagnosis module of the control system for a five-phase permanent magnet motor proposed by the present invention performs short-circuit fault diagnosis based on TNN, has advantages in accuracy and adaptability, and has the advantages of real-time and high computational efficiency; performs open-circuit fault diagnosis based on a model-based method, uses existing current sensors, does not require additional hardware, and is easy to apply to various occasions.

[0110] 4. The five - phase permanent - magnet motor control system proposed by the present invention combines the advantages of back - electromotive - force control and iterative learning control, can ensure the high - performance operation of the motor under fault conditions, achieve ripple - free torque output, and minimize ohmic losses;

[0111] 5. The five - phase permanent - magnet motor control system proposed by the present invention does not require overly complex fault - detection and diagnosis algorithms, can quickly respond to faults, eliminate repetitive torque ripples caused by model mismatches, make the current close to the optimal solution, and at the same time ensure the fault - tolerance ability and stability of the system;

[0112] 6. The five - phase permanent - magnet motor control system proposed by the present invention can be extended to multi - phase permanent - magnet motors with any number of phases and any stator - winding connections, and has wide applicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0113] Figure 1 is the flowchart of the multi - objective optimization method for the five - phase permanent - magnet motor proposed by the present invention;

[0114] Figure 2 is the control - system topology diagram based on the combination of back - electromotive - force control and iterative learning control;

[0115] Figure 3 is the flowchart of the short - circuit fault - diagnosis method for the control system of the five - phase permanent - magnet motor proposed by the present invention;

[0116] Figure 4 is the flowchart of the open - circuit fault - diagnosis method for the control system of the five - phase permanent - magnet motor proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0117] The following describes the present invention based on specific embodiments, but the present invention is not limited to these specific embodiments. In the following detailed description of the present invention, some specific details are described in detail. Those skilled in the art can fully understand the present invention without the description of these details.

[0118] A multi - objective optimization method for a five - phase permanent - magnet motor, as Figure 1 shown, is the flowchart of the multi - objective optimization method for the five - phase permanent - magnet motor described in the present invention, and the method includes the following steps:

[0119] Step S1 - 1: Define the optimization objectives of the five - phase permanent - magnet motor, including average torque, efficiency, and torque - ripple performance parameters, and determine the corresponding objective functions and constraint conditions; the objective functions are used to maximize efficiency, minimize torque ripple, and increase average torque; the constraint conditions include the number of turns of the stator winding, the thickness of the permanent magnet, the air - gap length, the number of rotor pole pairs, inductance, and resistance;

[0120] Step S1-2: Based on the optimization objective, use the central composite design method to generate sample points, determine the number and positions of the design points, and record the data of the parameters related to each design point;

[0121] Step S1-3: Use GARS to perform sensitivity analysis on the generated sample points, quantify the sensitivity of the motor response to each design feature, and evaluate the sensitivity index of the design variables to the optimization objective; the GARS is the genetic aggregated response surface; the design features are various factors affecting the motor performance; the design variables are the specific parameters quantifying these design features;

[0122] Step S1-4: For the results of the sensitivity analysis, construct a response surface model based on the weighted average of GARS. This model contains multiple different meta-models to accurately describe the relationships between the design variables in the design space; through this response surface model, characterize the influence of different combinations of design variables on the optimization objective, providing a basis for multi-objective optimization; the design space is the set composed of the value ranges of all design variables;

[0123] Step S1-5: Based on the NSGA-II algorithm, perform multi-objective optimization on the average torque, efficiency, and torque ripple of the five-phase permanent magnet motor, generate a non-dominated solution set under the satisfaction of the constraint conditions, achieve the balance of the optimization objective, and verify the optimization results through finite element analysis; the NSGA-II is the non-dominated genetic algorithm;

[0124] Further, the central composite design method in Step S1-2 specifically includes the following steps:

[0125] Step S1-2-1: Determine the design variables related to the performance of the five-phase permanent magnet motor and their value ranges;

[0126] Step S1-2-2: Select the design points of the center point, axial points, and star points; the center point is located at the center of the design space, used to estimate the experimental error to determine the performance of the reference motor; the axial points are located at the boundaries of the value ranges of the design variables to ensure full consideration of the boundary conditions of the motor performance; the star points are determined by setting the positions of the star arms, used to estimate the non-linear response of the design variables and evaluate the influence of the curvature of the design variables on the motor performance;

[0127] Step S1-2-3: Based on the design points of the center point, axial points, and star points selected in Step S1-2-2, generate the corresponding sample points; the sample points can cover the design space, used for experiments and simulations to obtain motor performance data, and further analyze the relationship between the design variables and the motor performance, providing data support for motor optimization.

[0128] Further, in step S1-3, the minimum-maximum search algorithm is used to search for the minimum and maximum values of each output parameter and its corresponding input parameters to comprehensively evaluate the response values of all variables, so as to evaluate the influence of design variables on the sensitivity index of the output parameters;

[0129] In step S1-4, the functional relationship between the global objective function and the constraint function in the response surface design space is as follows:

[0130]

[0131] where y(x) represents the relationship between the global objective function and the constraint function, represents the basic function, α i represents the weighting parameter, N m represents the number of metamodels;

[0132] When solving the quadratic approximation problem, the second-order polynomial can be expressed as:

[0133]

[0134] The response surface model solves the complex nonlinear relationship between the design variables and the average efficiency, torque, and torque ripple through the quadratic approximation method. The prediction of the i-th response of the response surface model is expressed as:

[0135]

[0136] where, represents the predicted value of the i-th response, a0 represents the reference value of the response variable when all independent variables are zero, a i represents the degree of linear influence of the i-th independent variable on the response, a ii represents the degree of nonlinear influence of the square term of the i-th independent variable on the response, a ij represents the degree of influence of the interaction between the i-th independent variable and the j-th independent variable on the response in, and all a are determined by least squares regression:

[0137] a = (X T X) -1 X T y

[0138] In step S1-4, the GARS adopted uses the weighted average of several different metamodels to represent a set:

[0139]

[0140] where, w i satisfies:

[0141]

[0142] Furthermore, the NSGA-II algorithm in step S1-5 includes the following steps:

[0143] Step S1-5-1: Generate the parent population P0 with a size of N P ; then, generate the offspring population Q0 through crossover and mutation operations; subsequent generations are denoted as the nth generation;

[0144] Step S1-5-2: Generate the combined population R n = P n ∪ Q n , and the size of the population R n is 2N P ;

[0145] Step S1-5-3: Decode the combined population R n and determine the fitness of the objective function; use the non-dominated solution sets L1, L2, and L3 to sort the population R n ; the solutions belonging to the best non-dominated solution set L1 are the best solutions, followed by the solutions in set L2, and the solutions selected from set L3 are ranked last;

[0146] Step S1-5-4: When the total number of members in the selected set is equal to or exceeds N P , select the initial set; calculate the crowding distance of each member in the selected set; for the next generation P n + 1, select the first k1 sets according to the elitist principle; sort the kth set according to the crowding distance, select the members with larger crowding distances and add them to P n + 1 generation until the population reaches N P ; the elitist principle is a commonly used strategy in genetic algorithms, aiming to retain the individuals with higher fitness in each generation to ensure that excellent genes can be passed on to the next generation, thereby accelerating the convergence speed of the algorithm and improving the performance of the algorithm;

[0147] The rule for selecting the initial set is given by the following formula:

[0148] g < h, if (g rank < h rank ) or (g rank < h rank and (g dist < h dist ))

[0149] where g and h represent two individuals used for comparison and selection in the algorithm, and g rank and h rank represent the non-dominated ranks of members g and h respectively, and g dist and hdist represent the crowding distances of members g and h respectively;

[0150] Step S1-5-5: If the iteration number limit is reached, the program ends and the fitness of the objective function and the non-dominated solutions are found; if not, go to Step S1-5-6;

[0151] Step S1-5-6: Perform crossover and mutation operations on the new population P n +1 to generate a new population Q n +1, then go to Step S1-5-2, and loop through Steps S1-5-2 to S1-5-5 until the fitness of the objective function and the non-dominated solutions are output.

[0152] Furthermore, in Step S1-5, the NSGA-II algorithm parameters are configured as 10,000 estimated evaluations, 500 samples per iteration, and 500 initial samples. The maximum number of candidates is three, and the allowable Pareto percentage is 70%. As more generations are generated under the set flux density target, the search direction of the objective function is obtained. Analyze the design variables and output variables and their corresponding performances. Candidate A, Candidate B, and Candidate C represent the best designs generated by the optimization program. In this embodiment, efficiency has the highest priority, followed by torque ripple and average torque. Therefore, the finally selected candidate will have higher efficiency. Finally, perform 2D finite element simulation on the best design using Maxwell software based on finite element analysis;

[0153] As Figure 2 shown, it is a control system topology diagram based on the combination of back electromotive force control and iterative learning control. The five-phase permanent magnet motor control system includes: a data acquisition module, a signal processing module, a rectifier, an inverter, a fault diagnosis module, a back electromotive force model module, an iterative learning controller module, a current controller module, and a five-phase permanent magnet motor;

[0154] The stator of the five-phase permanent magnet motor adopts a pole-slot combination of 10 slots and 8 poles. The winding is a double-layer fractional-slot concentrated winding structure. The rotor is a surface permanent magnet rotor structure and the magnet adopts a centrifugal structure. The rated speed is 15,000 r / min, the rated power is 7 kW, the rated torque is 4.5 N·m, SmCo30 is used as the permanent magnet material, and T-100 is used as the iron core material;

[0155] The control strategy of the five-phase permanent magnet motor control system includes the following steps:

[0156] Step S5-1: In the data acquisition module, the signal parameter values of the five-phase permanent magnet motor are obtained in real time, including the current, voltage, rotor position, and torque signals of each phase. The stray magnetic flux around the motor is monitored using a fluxgate sensor, and the back electromotive force of the motor under different states is obtained through two-dimensional finite element operation on the motor. Finally, the collected data is subjected to filtering and normalization preprocessing operations;

[0157] Step S5-2: The collected current signal parameters are input into the signal processing module, and the alternating current of the current on the ɑβ coordinate axis is obtained through coordinate transformation, and the transformed current is preprocessed; the preprocessing includes normalization processing and window segmentation;

[0158] Step S5-3: The preprocessed current is input into the fault diagnosis module, and the current is predicted through a transformer neural network and a model-based method respectively and compared with the actual current to judge the operating state of the motor; the operating state includes normal operating state, open-circuit fault state, and short-circuit fault state;

[0159] Step S5-4: When the motor operates in a fault state, an electromotive force model module is established according to the back electromotive force signal in Step S5-1, and the optimal current value is calculated based on different objective functions of open-circuit faults and short-circuit faults, providing an initial optimal reference current;

[0160] Step S5-5: The iterative learning controller module updates the torque error calculated according to the optimal reference current in Step S5-4 and the torque signal in Step S5-1 and the healthy phase current;

[0161] Step S5-6: The updated current is input into the current controller, thereby generating the gate drive signal of the voltage source inverter, enabling the stator phase current to follow the optimal reference current;

[0162] Step S5-7: Through two-dimensional finite element analysis of the motor, the torque ripple, current distribution, and ohmic loss data of the motor under different fault conditions are obtained, and the data is used to evaluate the effect of the control scheme.

[0163] Further, the method for obtaining the optimal current in Step S5-4 is to first use the electromagnetic torque that generates no ripple and has the minimum ohmic loss under fault conditions as the optimization target, and then use a closed-form equation to calculate the reference optimal current according to the back electromotive force model under the condition of representing the influence of the fault type by a look-up table;

[0164] The calculation of the optimal current in the case of an open-circuit fault is as follows:

[0165] The objective function for minimizing ohmic loss is:

[0166]

[0167] wherein represents the phase current vector, k represents the back electromotive force vector with speed normalized, T* represents the desired torque, F represents the fault matrix, whose elements are used to represent the constraints imposed by the stator winding connection and the fault location, and p1 and p2 are Lagrange multipliers;

[0168] The optimal current for the open - circuit fault is found as:

[0169]

[0170] wherein, F -1 is the left inverse of the matrix, defined as F -1 =(F T F) -1 F T , and F' is given by F'=(I n -FF l -1 );

[0171] The calculation of the optimal current in the case of the short - circuit fault is as follows:

[0172] The open - circuit fault - tolerant control is extended to the short - circuit fault, and the modified objective function is defined as:

[0173]

[0174] wherein, i sc is a new parameter introduced to consider the influence of the short - circuit current;

[0175] The optimal current for the short - circuit fault is found as:

[0176]

[0177] wherein, F τ -T is the right inverse of the matrix, defined as F τ -T =F(F T F) -1 , and i sc represents that the short - circuit - related current is equal to zero during healthy operation and is given by during a single - phase fault.

[0178] Furthermore, the specific method for updating the current in step S5 - 5 is to calculate based on the system equation, the performance of the motor equation, the error signal, and the learning algorithm, and suppress the torque ripple with reference to the current update rule;

[0179] The system equation is:

[0180] y j (m)=P(q)uj (m) + d(m)

[0181] where m is the time index, j is the iteration index, q is the forward time shift operator qx(m) = x(m + 1), y j is the output, u j is the control input, and d is the repeated exogenous signal;

[0182] The motor equation is:

[0183] T m = k T i + T d

[0184] where T m represents the output torque, and T d represents the oscillatory torque disturbance;

[0185] The error signal is:

[0186] e j (m) = y d (m) - y j (m)

[0187] where, y d is the desired output;

[0188] The learning algorithm is:

[0189] u j+1 (m) = Q(q)[u j (m) + L(q)e j (m + 1)]

[0190] where, Q(q) and L(q) are defined as the Q filter and the learning function respectively, and e j = T* - T m,j , T m,j represents the motor output torque at the j-th iteration, and T* represents the desired torque;

[0191] The iterative learning current update formula is:

[0192] i * ILC,j+1 = i * ILC,j + β(F'k(k T F'k) -1 )(T* - T m,j )j

[0193] where, i * ILC,j represents the iterative learning current reference at the j-th iteration, and β is a constant.

[0194] Further, the steps for the current controller in step S5-6 to achieve current tracking are as follows:

[0195] Step S5-6-1: The current controller monitors the actual value of the stator phase current in real time and compares it with the optimal reference current;

[0196] Step S5-6-2: According to the comparison result, the current controller adjusts the gate drive signal to ensure that the stator phase current quickly and accurately tracks the optimal reference current.

[0197] Further, the steps of the two-dimensional finite element analysis method in step S5-7 are as follows:

[0198] Step S5-7-1: Based on the number of slots, inner diameter, outer diameter of the stator, dimensions of the rotor, positions and dimensional parameters of the permanent magnets in the actual structure of the motor, a two-dimensional geometric model is established;

[0199] Step S5-7-2: Define the material properties of each part of the motor, and the materials include the material of the stator core, the material of the permanent magnet, and the material of the winding;

[0200] Step S5-7-3: Mesh the model, and discretize the geometric model into 20,000 elements according to the accuracy requirements and calculation time limit;

[0201] Step S5-7-4: Apply boundary conditions to the geometric model, define the external boundary of the motor as a magnetic insulation boundary condition, simulate the air environment around the motor, apply a permanent magnet excitation to the motor and apply an updated current excitation to achieve fault tolerance control;

[0202] Step S5-7-5: Use the two-dimensional finite element method to solve the partial differential equation of the motor electromagnetic field, and obtain the distribution of the electromagnetic field quantities inside the motor. The electromagnetic field quantities include magnetic field distribution and magnetic flux density, so as to obtain torque ripple, current distribution and ohmic loss data;

[0203] Further, after the fault diagnosis module discriminates a system fault, the fault tolerance control system adjusts the healthy phase current through the speed outer loop and the current inner loop, controls the motor to operate with a fault. The current inner loop analyzes the current in the stationary coordinate system to judge the type of motor fault, and passes each phase current into the back electromotive force model to define the objective function and solve for the optimal current. The optimal current is compared with the actual current through the current controller to ensure current tracking; the speed outer loop analyzes and compares the rotor speed w with the given reference speed w * , and obtains the torque reference value through the speed PI controller;

[0204] Furthermore, the data acquisition module includes sensors for multiple signals such as current, voltage, rotational speed, and torque, an optical encoder for sensing the rotor position angle, and a device for filtering and preprocessing each signal through standardization; the torque sensor transmits the acquired torque information to the iterative learning controller module in real time, enabling the iterative learning controller to adjust in a timely manner according to the latest torque information. After receiving the torque information, the iterative learning controller compares it with the reference torque and makes adjustments according to the current update law. When the output torque is lower than the expected torque, the iterative learning module will correspondingly increase the current, and vice versa, it will correspondingly decrease the current, forming a closed-loop control loop. The reference torque is estimated by the PI controller based on the speed error; since the vector control based on svpwm has excellent performance during normal operation, the vector control based on svpwm is selected as the control method for the normal operation of the motor.

[0205] The fault diagnosis module in step S5-3 includes a short-circuit fault diagnosis module and an open-circuit fault diagnosis module;

[0206] As Figure 3 shown, the overall process of the short-circuit fault diagnosis module is as follows:

[0207] The preprocessed current signal is input into the diagnosis model based on TNN. The diagnosis model includes multiple encoders, and each encoder includes an MHA module and an FF module; the input signal is encoded through the MHA module and the FF module. After hierarchical processing by multiple encoders, an output tensor is obtained; the output tensor is used to estimate the number of shorted coils and the short-circuit current, and the third harmonic component of the stray magnetic flux is used to detect and locate the short-circuit fault. Finally, the number of shorted coils, the amplitude of the short-circuit current, and the analysis result of the stray magnetic flux are comprehensively estimated to determine the short-circuit fault and its degree; the TNN is a transformer neural network module, the MHA is a multi-head attention module, and the FF is a fully connected feedforward network module;

[0208] Furthermore, the calculation process of the MHA module is as follows:

[0209] Step S6-1-1: Through linear transformation of the input sequence, the query matrix Q = XW Q 、the key matrix K = XW K and the value matrix V = XW V are obtained, where is the input vector matrix, is the trainable weight matrix, d feat is the number of input features, and T m is the time step;

[0210] Step S6-1-2: Calculate the self-attention according to the formula, and its function is used to normalize the attention score;

[0211] Step S6-1-3: Calculate through multiple parallel self-attention layers, namely multi-heads, and splice and linearly transform the results to obtain the output of the MHA module;

[0212] Furthermore, the FF module specifically includes two linear transformation layers, and residual connection and normalization processing are performed before and after each linear layer respectively;

[0213] Furthermore, the calculation process of the FF module is as follows:

[0214] Step S6-2-1: The input of the first linear transformation layer is X e ', and the output is GELU(X e 'W FF1 +b FF1 ), where is the trainable weight of the fully connected feed-forward network, is the bias of the fully connected feed-forward network, and GELU is the Gaussian error linear unit activation function;

[0215] Step S62-2: The input of the second linear transformation layer is the output of the first linear transformation layer, and the output is GELU(X e 'W FF1 +b FF1 )W FF2 +b FF2 , where is the trainable weight of the fully connected feed-forward network, is the bias of the fully connected feed-forward network;

[0216] As Figure 4 shown, the overall process of the open-circuit fault diagnosis module is as follows: Use a model-based method for fault detection, specifically including using an extended Kalman filter to estimate the current of the motor and establishing a discretized state space model;

[0217] Furthermore, the open-circuit fault diagnosis steps are as follows:

[0218] Step S6-3-1: Use an extended Kalman filter to estimate the current of the motor;

[0219] Step S6-3-2: Establish a discretized state space model, which is divided into a prediction module and an update module:

[0220] In the prediction module: is the state estimate value from time k-1 to time k; where is the state estimate value at time k-1, and u k-1 is the input at time k-1; is the state transition function, is the estimated error covariance matrix at time k-1 for time k, where I is the identity matrix, is the system matrix, where L d and L q are the direct-axis inductance and quadrature-axis inductance respectively, λ PM is the permanent magnet flux linkage, T s is the sampling time, F k is the Jacobian matrix of A, P k-1|k-1 is the estimated error covariance matrix at time k-1, Q k-1 is the covariance matrix of the process noise;

[0221] In the update module: is the Kalman gain, where H k is the measurement matrix, R k is the covariance matrix of the measurement noise; is the updated state estimate at time k, where h(x) is the measurement function, y k is the measurement at time k; P k|k =(I-K k H k )P k|k-1 is the updated estimated error covariance matrix at time k; where, x = [i d i q T , u = [V d V q ω e T , h(x (k) ) = Cx (k) , i d and i q are the direct-axis current and quadrature-axis current respectively, V d and V q are the direct-axis voltage and quadrature-axis voltage, ω e is the electrical angular velocity, is the transformation matrix; Calculate the residual: And apply it to the CUSUM algorithm for fault detection. The CUSUM algorithm detects the occurrence of faults by accumulating changes in the residual; At the same time, use the whiteness test to judge whether the sensor is faulty. The whiteness test calculates the autocorrelation function of the residual and the normalized ACF: where N is the number of data samples, ε t is the residual at time t, is the mean value of the residual; If the residual exceeds the set threshold or the whiteness test shows an anomaly, it is judged that there is a fault; The CUSUM algorithm is the cumulative sum algorithm.

[0222] ​​After the fault diagnosis module determines a system fault, the fault-tolerant control system adjusts the healthy phase current through the speed outer loop and the current inner loop to control the motor to operate with a fault. The current inner loop analyzes the current in the stationary coordinate system to determine the type of motor fault, and passes each phase current into the back electromotive force model to define the objective function to solve for the optimal current, and compares the optimal current with the actual current through the current controller to ensure current tracking; the speed outer loop analyzes and compares the rotor speed w with the given reference speed w * , and obtains the torque reference value through the speed PI controller.

Claims

1. A multi-objective optimization method for a five-phase permanent magnet motor, characterized in that: The multi-objective optimization method for a five-phase permanent magnet motor comprises the following steps: Step S1-1, clarifying the optimization objectives of the five-phase permanent magnet motor, including average torque, efficiency, and torque pulsation performance parameters, and determining corresponding objective functions and constraints; the objective function is used to maximize efficiency, minimize torque pulsation, and improve average torque; the constraints include the number of stator winding turns, permanent magnet thickness, air gap length, rotor pole pair number, inductance, and resistance; Step S1-2: Based on the optimization target, the central composite design method is used to generate sample points, determine the number and location of design points, and record the data of relevant parameters of each design point; Step S1-3, using GARS to perform sensitivity analysis on the generated sample points, quantify the sensitivity of the motor response to each design feature, and evaluate the sensitivity index of the design variable to the optimization target; the GARS is a genetic aggregation response surface; the design features are various factors that affect the performance of the motor, including stator outer diameter, permanent magnet thickness, air gap length, centrifugal height, and notch depth; the design variables are specific parameters for quantifying these design features; Step S1-4: Based on the results of the sensitivity analysis, a response surface model is constructed based on the weighted average of GARS, and the model includes multiple different meta-models to accurately describe the relationship between the design variables in the design space; through the response surface model, the influence of different combinations of design variables on the optimization target is characterized, providing a basis for multi-objective optimization; the design space is a set consisting of the value ranges of all design variables; Step S1-5, based on the NSGA-II algorithm, multi-objective optimization is performed on the average torque, efficiency and torque ripple of the five-phase permanent magnet motor, a non-dominated solution set is generated under the constraints, the balance of the optimization objectives is achieved, and the optimization results are verified by finite element analysis; the NSGA-II is a non-dominated genetic algorithm.

2. A five-phase permanent magnet motor multi-objective optimization method according to claim 1, characterized in that: The central composite design method of step S1-2 specifically includes the following steps: Step S1-2-1, determining the design variables related to the performance of the five-phase permanent magnet motor and their value ranges; Step S1-2-2, select the design points of the center point, the axial point and the star point; the center point is located at the center of the design space and is used to estimate the experimental error to determine the benchmark motor performance; the axial point is located at the boundary of the value range of the design variable to ensure that the boundary conditions of the motor performance are fully considered; the star point is determined by setting the position of the asterisk arm and is used to estimate the nonlinear response of the design variable and evaluate the influence of the curvature of the design variable on the motor performance; Step S1-2-3, based on the design points of the center point, axial point and star point selected in step S1-2-2, generate corresponding sample points; the sample points can cover the design space and are used for experiments and simulations to obtain motor performance data, and then analyze the relationship between design variables and motor performance, providing data support for motor optimization.

3. A five-phase permanent magnet motor multi-objective optimization method according to claim 1, characterized in that: The step S1-3 uses a minimum-maximum search algorithm to search for the minimum and maximum values ​​of each output parameter and its corresponding input parameter to comprehensively evaluate the response values ​​of all variables, thereby evaluating the impact of the design variables on the sensitivity index of the output parameters; The functional relationship between the global objective function and the constraint function in the response surface design space in step S1-4 is: Among them, y(x) represents the relationship between the global objective function and the constraint function. represents the basic function, α i represents the weighting parameter, N m Indicates the number of metamodels; The response surface model solves the complex nonlinear relationship between the design variables and the average efficiency, torque, and torque ripple by a quadratic approximation method. The prediction of the i-th response of the response surface model is expressed as: in, represents the predicted value of the ith response, a0 represents the baseline value of the response variable when all independent variables are zero, and a i Indicates the linear influence of the ith independent variable on the response, a ii Indicates the nonlinear influence of the square term of the ith independent variable on the response, a ij It is expressed as the degree of influence of the interaction between the ith independent variable and the jth independent variable on the response, and all a are determined by least squares regression: a=(X T X) -1 X T y The GARS used in step S1-4 is represented as a set using the weighted average of several different meta-models: Among them, w i satisfy:

4. A five-phase permanent magnet motor multi-objective optimization method according to claim 1, characterized in that: The NSGA-II algorithm in step S1-5 includes the following steps: Step S1-5-1, generate the parent population P0, whose size is N P ; Then, the offspring population Q0 is generated through crossover and mutation operations; the subsequent stage is denoted as the nth generation; Step S1-5-2: Generate combined population R n =P n ∪Q n , population R n The scale is 2N P ; Step S1-5-3: Combined population R n Decode and determine the fitness of the objective function; use the non-dominated solution sets L1, L2, and L3 to decode the population R n Sort them; the solution belonging to the best non-dominated solution set L1 is the best solution, followed by the solution in the set L2, and the solution selected from the set L3 is ranked last; Step S1-5-4: When the total number of members of the selected set is equal to or exceeds N P When , select the initial set; calculate the crowding distance of each member in the selected set; for the next generation P n +1, select the first k1 sets according to the elitist principle; sort the kth set according to the crowding distance, select the member with the larger crowding distance and add it to P n In the +1 generation, until the population reaches N P ; The elitism principle is a commonly used strategy in genetic algorithms, which aims to retain individuals with higher fitness in each generation to ensure that excellent genes can be passed on to the next generation, thereby accelerating the convergence speed of the algorithm and improving the performance of the algorithm; The rule for selecting the initial set is given by the following formula: g<h,if(g rank <h rank )or(g rank <h rank and(g dist <h dist )) Among them, g and h represent two individuals used for comparison and selection in the algorithm, g rank and h rank denote the non-dominated ranks of members g and h, respectively. dist and h dist They represent the crowding distances of members g and h respectively; Step S1-5-5, if the limit of the number of iterations is reached, the program ends and finds the fitness and non-dominated solution of the objective function; if not, proceed to step S1-5-6; Step S1-5-6: For the new population P n +1 Perform crossover and mutation operations to generate a new population Q n +1, then enter step S1-5-2, and loop steps S1-5-2 to S1-5-5 until the fitness and non-dominated solution of the objective function are output.

5. A multi-objective optimization method for a five-phase permanent magnet motor according to claim 1, and a control system for controlling the five-phase permanent magnet motor optimized by the multi-objective optimization method, characterized in that: The control system includes: a data acquisition module, a signal processing module, a rectifier, an inverter, a fault diagnosis module, a back electromotive force model module, an iterative learning controller module, a current controller module, and a five-phase permanent magnet motor; The stator of the five-phase permanent magnet motor adopts a pole-slot combination of 10 slots and 8 poles, the winding is a double-layer fractional slot concentrated winding structure, the rotor is a surface permanent magnet rotor structure and the magnet adopts a centrifugal structure; The control strategy of the control system includes the following steps: Step S5-1, in the data acquisition module, the signal parameter values ​​of the five-phase permanent magnet motor are obtained in real time, including the current, voltage, rotor position, and torque signals of each phase, the stray magnetic flux around the motor is monitored by a fluxgate sensor, and the back electromotive force of the motor under different states is obtained by performing two-dimensional finite element operations on the motor, and finally the collected data is filtered and standardized for preprocessing; Step S5-2, inputting the collected current signal parameters into the signal processing module, obtaining the alternating current on the αβ coordinate axis through coordinate transformation, and preprocessing the transformed current; the preprocessing includes standardization processing and window segmentation; Step S5-3, input the pre-processed current into the fault diagnosis module, predict the current by using the transformer neural network and the model-based method respectively, and compare it with the actual current to determine the motor operation state; the operation state includes normal operation state, open circuit fault state and short circuit fault state; Step S5-4: when the motor is running in a fault state, a back-electromotive force model module is established according to the back-electromotive force signal in step S5-1, and an optimal current value is calculated according to different objective functions of open circuit fault and short circuit fault to provide an initial optimal reference current; Step S5-5, the iterative learning controller module updates the healthy phase current according to the optimal reference current in step S5-4 and the torque error calculated by the torque signal in step S5-1; Step S5-6, inputting the updated current into the current controller to generate a gate drive signal for the voltage source inverter so that the stator phase current can follow the optimal reference current; Step S5-7: Perform two-dimensional finite element analysis on the motor to obtain torque pulsation, current distribution and ohmic loss data of the motor under different fault conditions, and use the data to evaluate the effect of the control scheme.

6. A five-phase permanent magnet motor control system according to claim 5, characterized in that: The fault diagnosis module in step S5-3 includes a short circuit fault diagnosis module and an open circuit fault diagnosis module; The overall process of the short-circuit fault diagnosis module is as follows: the pre-processed current signal is input into the TNN-based diagnosis model, and the diagnosis model includes multiple encoders, each encoder includes an MHA module and an FF module; the input signal is encoded and processed by the MHA module and the FF module, and an output tensor is obtained after hierarchical processing by multiple encoders; the output tensor is used to estimate the number of short-circuited coils and the short-circuit current, and then the third harmonic component of the stray magnetic flux is used to detect and locate the short-circuit fault, and finally the number of short-circuited coils, the short-circuit current amplitude and the stray magnetic flux analysis results are comprehensively estimated to determine the short-circuit fault and its degree; the TNN is a transformer neural network module, the MHA is a multi-head attention module, and the FF is a fully connected feedforward network module; The MHA module calculation process is as follows: Step S6-1-1: Perform a linear transformation on the input sequence to obtain a query matrix Q = XW Q , key matrix K = XW K Sum matrix V = XW V ,in is the input vector matrix, t=1,2,…,T m ; is the trainable weight matrix, d feat is the number of input features, T m is the time step; Step S6-1-2, calculate self-attention according to the formula, and its function is used to normalize the attention score; Step S6-1-3, perform calculations through multiple parallel self-attention layers, i.e., multiple heads, and concatenate and linearly transform the results to obtain the output of the MHA module; The FF module specifically includes two linear transformation layers, and residual connection and normalization processing are performed before and after each linear layer respectively; The FF module calculation process is as follows: Step S6-2-1: The input of the first linear transformation layer is X′ e , the output is GELU(X′ e W FF1 +b FF1 ),in are the trainable weights of the fully connected feedforward network, is the bias of the fully connected feedforward network, GELU is the Gaussian error linear unit activation function; Step S6-2-2: The input of the second linear transformation layer is the output of the first linear transformation layer, and the output is GELU(X′ e W FF1 +b FF1 )W FF2 +b FF2 ,in are the trainable weights of the fully connected feedforward network, is the bias of the fully connected feed-forward network; The overall process of the open circuit fault diagnosis module is as follows: using a model-based approach to perform fault detection, specifically including using an extended Kalman filter to estimate the current of the motor and establish a discretized state space model; The open circuit fault diagnosis steps are as follows: Step S6-3-1, using an extended Kalman filter to estimate the current of the motor; Step S6-3-2: Establish a discretized state space model, which is divided into a prediction module and an update module: In the prediction module: is the estimated value of the state at time k at time k-1; is the estimated value of the state at time k-1, u k-1 is the input at time k-1; is the state transfer function, is the estimated error covariance matrix of time k-1 to time k, where I is the identity matrix, is the system matrix, Where L d , L q are the direct-axis inductance and quadrature-axis inductance, respectively, PM is the permanent magnet flux, T s is the sampling time, F k is the Jacobian matrix of A, P k-1|k-1 is the estimated error covariance matrix at time k-1, Q k-1 is the covariance matrix of process noise; In the update module: is the Kalman gain, where H k is the measurement matrix, R k is the covariance matrix of the measurement noise; is the updated state estimate at time k, where h(x) is the measurement function and y k is the measured value at time k; P k|k =(IK k H k ) k|k-1 is the estimated error covariance matrix after updating at time k; where x = [i d i q ] T ,u=[V d V q ω e ] T ,h(x (k) )=Cx (k) ,i d 、i q are the direct-axis current and quadrature-axis current, V d 、V q is the direct-axis voltage and quadrature-axis voltage, ω e is the electrical angular velocity, is the transformation matrix; calculate the residual: It is applied to the CUSUM algorithm for fault detection. The CUSUM algorithm detects the occurrence of faults by accumulating the change of residuals. At the same time, the whiteness test is used to determine whether the sensor is faulty. The whiteness test calculates the autocorrelation function of the residuals. And the normalized ACF: Where N is the number of data samples, ε t is the residual at time t, is the mean of the residuals; if the residuals exceed the set threshold or the whiteness test shows an abnormality, it is determined that a fault exists; the CUSUM algorithm is a cumulative sum algorithm.

7. A five-phase permanent magnet motor control system according to claim 5, characterized in that: The optimal current in step S5-4 is obtained by first taking the electromagnetic torque without ripple and with minimum ohmic loss under fault conditions as the optimization target, and then using a closed-form equation to calculate the reference optimal current according to the back electromotive force model when the influence of the fault type is represented by a lookup table; The optimal current calculation for the open circuit fault condition is as follows: The objective function to minimize ohmic loss is: in represents the phase current vector, k represents the speed normalized back EMF vector, T* represents the desired torque, F represents the fault matrix whose elements are used to represent the constraints imposed by the stator winding connection and the fault location, and p1 and p2 are Lagrange multipliers; Find the optimal current for open circuit fault as: Among them, F -1 is the left inverse of the matrix, defined as F -1 =(F T F) -1 F T , F' is given; The optimal current calculation under the short-circuit fault condition is as follows: The open-circuit fault-tolerant control is extended to short-circuit faults, and the modified objective function is defined as: Among them, i sc New parameters introduced to consider the effect of short-circuit current; Find the optimal short-circuit fault current as: in, is the right inverse of the matrix, defined as i sc Indicates that the short-circuit related current is equal to zero in healthy operation and is equal to zero in single-phase fault. Given.

8. The control system of a five-phase permanent magnet motor according to claim 5, characterized in that: The specific method of updating the current in step S5-5 is to calculate based on the system equation, motor equation performance, error signal and learning algorithm, and suppress the torque pulsation with reference to the current update law; The system equation is: y j (m)=P(q)u j (m)+d(m) Where m is the time index, j is the iteration index, q is the forward time shift operator qx(m)=x(m+1), y j is the output, u j is the control input, d is the repeated exogenous signal; The motor equation is: T m =k T i+T d Where T m Represents the output torque, T d Indicates oscillating torque disturbance; The error signal is: e j (m)=y d (m)-y j (m) Among them, y d is the expected output; The learning algorithm is: u j+1 (m)=Q(q)[u j (m)+L(q)e j (m+1)] Among them, Q(q) and L(q) are defined as Q filter and learning function respectively, e j =T*-T m,j , T m,j represents the motor output torque of the jth iteration, T* represents the expected torque; The iterative learning current update formula is: i * ILC,j+1 =i * ILC,j +β(F'k(k T F'k) -1 )(T*-T m,j )j Among them, i * ILC,j represents the iterative learning current reference of the jth iteration, and β is a constant.

9. A control system for a five-phase permanent magnet motor according to claim 5, characterized in that: The steps for the current controller in step S5-6 to implement current following are as follows: Step S5-6-1, the current controller monitors the actual value of the stator phase current in real time and compares it with the optimal reference current; Step S5-6-2: Based on the comparison result, the current controller adjusts the gate drive signal to ensure that the stator phase current quickly and accurately tracks the optimal reference current.

10. A control system for a five-phase permanent magnet motor according to claim 5, characterized in that: The two-dimensional finite element analysis method steps in step S5-7 are: Step S5-7-1, establishing a two-dimensional geometric model according to the number of slots, inner diameter, outer diameter of the stator, the size of the rotor, the position and size parameters of the permanent magnet in the actual structure of the motor; Step S5-7-2, defining the material properties of each part of the motor, wherein the material includes the material of the stator core, the material of the permanent magnet, and the material of the winding; Step S5-7-3, meshing the model, discretizing the geometric model into 20,000 units according to accuracy requirements and calculation time limits; Step S5-7-4, applying boundary conditions to the geometric model, defining the outer boundary of the motor as a magnetic insulation boundary condition, simulating the air environment around the motor, applying permanent magnet excitation to the motor and applying updated current excitation to achieve fault-tolerant control; Step S5-7-5, using the two-dimensional finite element method to solve the partial differential equation of the motor's electromagnetic field, to obtain the distribution of the electromagnetic field quantity inside the motor, the electromagnetic field quantity including the magnetic field distribution and the magnetic flux density, thereby obtaining the torque pulsation, current distribution and ohmic loss data.

Images