Method and system for inter-turn short circuit fault diagnosis of electric machines based on current prediction error

Abstract

The application relates to a motor inter-turn short-circuit fault diagnosis method and system based on current prediction error, which comprises the following steps: during the operation of a traction induction motor, the operation parameters of the induction motor are acquired by real-time sampling, the stator current is predicted, the value function of the stator current prediction model is calculated, the inter-turn short-circuit fault index is calculated, compared with the fault index threshold, and the inter-turn short-circuit fault diagnosis is performed; the construction process of the inter-turn short-circuit fault index comprises the following steps: the electromagnetic equation of the induction motor is constructed, the stator current prediction model is obtained, the stator current prediction value is compared with the current reference value, and the value function of the stator current prediction model is constructed; and the inter-turn short-circuit fault index is constructed according to the ratio of the direct current component or the second harmonic component in the value function to the electric angular velocity of the induction motor. Compared with the prior art, the application has the advantages of effectively diagnosing the inter-turn short-circuit fault of the traction induction motor, being less affected by the speed change, having strong robustness and the like.

Description

Technical Field

[0001] This invention relates to the field of motor fault prediction technology, and in particular to a method and system for diagnosing inter-turn short-circuit faults in motors based on current prediction errors. Background Technology

[0002] Railways are a strategic, pioneering, and critical national infrastructure. Safety is the foundation of railway operation and also the greatest risk and challenge facing railway transportation. Therefore, ensuring the safety of railway transportation is of paramount importance in future technological research. Electric locomotives are the carriers of railway transportation, and ensuring the safe operation of trains has become a top priority for railway development, urgently requiring higher standards for the reliability of electric locomotive equipment.

[0003] The traction electric drive system is the core of an electric locomotive. Taking high-speed trains as an example, its traction system mainly includes the pantograph (containing high-voltage electrical equipment), traction transformer, traction converter, traction motor, and gear transmission. The traction motor is the power source of the traction system, responsible for outputting kinetic energy and converting electrical energy into mechanical energy—converting electrical energy into mechanical energy during traction and mechanical energy into electrical energy during braking. Currently, most motors used in rail transit traction systems are AC induction motors, with a traction system failure rate of 32.3%. This demonstrates that the reliability of the traction system directly affects the safe operation of the train. The traction motor is a key component of the rail transit traction drive system, and its fault detection is crucial for ensuring the safe and reliable operation of electric locomotives. The harsh operating environment of high-speed trains and the use of high-frequency voltage pulse drives pose a serious risk of insulation failure to the traction motor, resulting in frequent stator inter-turn short-circuit faults in induction motors. Therefore, predicting and providing early warnings for stator inter-turn short-circuit faults in high-speed train induction motors to avoid serious faults is extremely important for ensuring train reliability.

[0004] Based on the different principles of fault diagnosis methods, motor fault diagnosis technology can be divided into the following two categories: data-driven and analytical model-based. Data-driven methods are further subdivided into signal processing-based and artificial intelligence-based fault diagnosis methods.

[0005] Model-based fault diagnosis methods, while employing analytical models that can effectively simulate the steady-state and dynamic processes of a system, involve two main components: 1) residual signal generation, where the residual signal is the difference between the measured process variable and the model-based estimate; and 2) residual evaluation and decision-making. Because the analytical process model is embedded, this method is suitable for fault diagnosis under both dynamic and static conditions, but its robustness is also affected by multiple factors such as model parameters, operating environment, set thresholds, and set residuals. Furthermore, the accuracy of the analytical model itself is limited by the depth of understanding of complex systems and the simplification of the system model.

[0006] Artificial intelligence-based fault diagnosis methods can take into account the impact of motor operating environment, complex operating conditions and multiple faults on fault diagnosis, and have strong robustness. However, they require a large amount of operating data of healthy and faulty motors. Fault data is often scarce, and intelligent algorithms are time-consuming and have high requirements for hardware configuration. Therefore, it is difficult to achieve accurate fault diagnosis using artificial intelligence-based fault diagnosis methods.

[0007] Fault diagnosis methods based on signal processing often utilize fault characteristic signals carried by voltage, current, power, torque, magnetic flux, and control signals in the traction motor control system. These signals are combined with modern signal processing algorithms (such as FFT, wavelet transform, Hilbert-Huang transform, empirical mode decomposition, etc.) to extract fault characteristic signals. Among these, fault diagnosis methods based on motor current signature analysis (MCSA) are a class of non-intrusive, reliable, and classic fault diagnosis algorithms. Summary of the Invention

[0008] The purpose of this invention is to overcome the shortcomings of the prior art by providing a method and system for diagnosing inter-turn short-circuit faults in motors based on current prediction errors. This method can effectively diagnose inter-turn short-circuit faults in traction induction motors and has strong robustness.

[0009] The objective of this invention can be achieved through the following technical solutions:

[0010] A method for diagnosing inter-turn short-circuit faults in motors based on current prediction error includes the following steps:

[0011] Construct the electromagnetic equations of the induction motor based on its operating parameters;

[0012] Discretize the stator current in the electromagnetic equations of the induction motor to obtain a stator current prediction model;

[0013] The stator current prediction value output by the stator current prediction model is compared with the current reference value to construct the value function of the stator current prediction model;

[0014] Based on the ratio of the DC component or second harmonic component in the value function to the electrical angle of the induction motor, an inter-turn short-circuit fault index is constructed.

[0015] During the operation of the traction induction motor, the operating parameters of the induction motor are sampled in real time to predict the stator current, thereby calculating the value function of the stator current prediction model, and then calculating the inter-turn short circuit fault index and comparing it with the preset fault index threshold to diagnose the inter-turn short circuit fault.

[0016] Furthermore, the calculation expression for the inter-turn short-circuit fault index is as follows:

[0017]

[0018] In the formula, FI x The calculated value of the inter-turn short-circuit fault index is given. The subscript x can be 0 or 2, representing the DC component and the second harmonic component, respectively. J is the calculated result of the value function, and the electric angular velocity of the induction motor is given. n1 is the synchronous speed of the motor, n p This represents the number of pole pairs of the motor.

[0019] Furthermore, the expression for the value function is:

[0020]

[0021] In the formula, It is the measured value of the αβ axis current at the current moment; This is the predicted value of the αβ axis current at the next moment; the superscript * indicates the reference value; the superscript p indicates the predicted value; θ i The current phase is equal to that of the faulty phase; i f The fault current caused by the inter-turn short-circuit fault is μ; the short-circuit turns ratio is i. f (k+1) represents the fault current caused by the inter-turn short circuit fault of the motor at time (k+1).

[0022] Furthermore, the fault current i caused by the inter-turn short-circuit fault f The expression is:

[0023] i f =I f sin(θ e +θ i )

[0024] In the formula, θ e It is the rotor electrical angle; θ i It is the current angle of the phase where the inter-turn short-circuit fault occurs; I f This represents the amplitude of the fault current.

[0025] Furthermore, the predicted value i of the αβ axis current at the next moment sα (k+1) and i sβ (k+1) is obtained from the stator current prediction model, and the calculation expression of the stator current prediction model is:

[0026]

[0027] In the formula, T s For the motor control cycle, R s R is the stator resistance. rL is the rotor resistance. s For the stator equivalent two-phase winding self-inductance, L r For the rotor's equivalent two-phase winding self-inductance, L m The mutual inductance between the coaxial equivalent windings of the stator and rotor. T represents the leakage coefficient. r =L r / R r ψ represents the rotor electromagnetic time constant. rα (k) represents the α-axis component of the rotor flux linkage at time k, ψ rβ (k) represents the β-axis component of the rotor flux linkage at time k, ω(k) represents the rotor electric angular velocity at time k, and u sα (k) represents the α-axis component of the stator voltage at time k, u sβ (k) represents the β-axis component of the stator voltage at time k.

[0028] Furthermore, the expression for the electromagnetic equation of the induction motor is as follows:

[0029]

[0030] In the formula, ω(k+1) is the rotor electric angular velocity at time k+1; J m T is the mechanical moment of inertia of the electric motor. L This represents the motor load torque.

[0031] Furthermore, since inter-turn short circuits will increase the DC content and second harmonic content in the value function, and the amplitude of the inter-turn short circuit current is proportional to the electric angular velocity of the motor, it is possible to determine whether an inter-turn short circuit fault of the traction motor has occurred based on the DC content or second harmonic content in the value function.

[0032] Furthermore, the control strategy for the traction induction motor is model predictive control.

[0033] Furthermore, the switching state corresponding to the predicted current output by the stator current prediction model is applied to the inverter to achieve current tracking control.

[0034] The present invention also provides a motor inter-turn short circuit fault diagnosis system based on current prediction error, including a memory and a processor. The memory stores a computer program, and the processor calls the computer program to execute the steps of the method described above.

[0035] Compared with the prior art, the present invention has the following advantages:

[0036] (1) This invention discloses a method for diagnosing inter-turn short circuit faults of traction motors applicable to model predictive control strategies. The proposed method can achieve rapid diagnosis and accurate location of inter-turn short circuits and has high robustness for diagnosing inter-turn short circuit faults of induction motors under different operating conditions.

[0037] (2) This invention analyzes the model predictive control strategy of traction motor and the equivalent model of inter-turn short circuit fault of traction motor, and finds that inter-turn short circuit will increase the DC content and second harmonic content in the value function of the model predictive control strategy of traction motor, and that the amplitude of inter-turn short circuit current is proportional to the electric angular velocity of motor. It constructs a fault index that is independent of motor speed, and can quickly and accurately diagnose inter-turn short circuit faults.

[0038] (3) This method does not require additional equipment or measurement systems; it does not require extracting, collecting or constructing new signals, but directly utilizes the existing value function signals of the model predictive control system.

[0039] (4) This method can effectively diagnose inter-turn short circuit faults in traction induction motors by comprehensively utilizing the second harmonic component in the value function.

[0040] (5) The fault index constructed by this method is less affected by changes in rotational speed and has strong robustness. Attached Figure Description

[0041] Figure 1 This is a flowchart illustrating a method for diagnosing inter-turn short-circuit faults in a motor based on current prediction error, provided in an embodiment of the present invention.

[0042] Figure 2 This is a block diagram of a traction motor system based on model predictive control provided in an embodiment of the present invention;

[0043] Figure 3 This is an equivalent diagram of a stator inter-turn short-circuit fault provided in an embodiment of the present invention;

[0044] Figure 4 This is a schematic diagram of the harmonic content of a simulated value function provided in an embodiment of the present invention;

[0045] Figure 5 This is a schematic diagram of fault indicators at different speeds provided in an embodiment of the present invention;

[0046] Figure 6 This is a schematic diagram of fault indicators under different load torques provided in an embodiment of the present invention;

[0047] Figure 7 This is a schematic diagram of fault indicators for different short-circuit turns ratios provided in an embodiment of the present invention. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0049] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0050] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0051] Example 1

[0052] like Figure 1 As shown, this embodiment provides a method for diagnosing inter-turn short-circuit faults in motors based on current prediction errors, including the following steps:

[0053] Construct the electromagnetic equations of the induction motor based on its operating parameters;

[0054] By discretizing the stator current in the electromagnetic equations of the induction motor, a stator current prediction model is obtained.

[0055] The stator current prediction value output by the stator current prediction model is compared with the current reference value to construct the value function of the stator current prediction model;

[0056] Based on the ratio of the DC component or second harmonic component in the value function to the electrical angle of the induction motor, an inter-turn short-circuit fault index is constructed.

[0057] During the operation of the traction induction motor, the operating parameters of the induction motor are sampled in real time to predict the stator current, thereby calculating the value function of the stator current prediction model, and then calculating the inter-turn short circuit fault index and comparing it with the preset fault index threshold to diagnose the inter-turn short circuit fault.

[0058] This method can achieve rapid diagnosis and accurate location of inter-turn short circuits, and has high robustness in diagnosing inter-turn short circuit faults of induction motors under different operating conditions.

[0059] Its specific structural principle is as follows:

[0060] I. Traction Motor Model Predictive Control Strategy

[0061] Figure 2 The predictive control strategy for the traction motor model shown consists of the following three parts:

[0062] 1.1 Electromagnetic Equations of Induction Motors in a Stationary Two-Phase Coordinate System

[0063]

[0064] In the formula, T s For the motor control cycle, R s R is the stator resistance. r L is the rotor resistance. s For the stator equivalent two-phase winding self-inductance, L r For the rotor's equivalent two-phase winding self-inductance, L m The mutual inductance between the coaxial equivalent windings of the stator and rotor. T represents the leakage coefficient. r =L r / R r ψ represents the rotor electromagnetic time constant. rα (k) represents the α-axis component of the rotor flux linkage at time k, ψ rβ (k) represents the β-axis component of the rotor flux linkage at time k, ω(k) represents the rotor electric angular velocity at time k, and u sα (k) represents the α-axis component of the stator voltage at time k, u sβ (k) represents the β-axis component of the stator voltage at time k. ω(k+1) represents the rotor electric angular velocity at time k+1; J represents the mechanical moment of inertia of the motor; T L This represents the motor load torque.

[0065] The state variable can be represented as:

[0066] X = [w ψ rα ψ rβ i sα i rβ ] T (2)

[0067] Input variables can be represented as:

[0068] U = [u sα u sβ T L ] T (3)

[0069] 1.2 Stator Current Prediction

[0070] Discretizing the stator current equation in equation (1) using the forward Euler method, we get:

[0071]

[0072] In the formula, i sα (k), i sβ (k) is the measured value of the αβ axis current at the current moment; This is the predicted value of the αβ axis current at the next moment. Because the control period T... s Since it is less than the electrical time constant of the motor, the system variables ω(k) and ψ can be considered as constants within one cycle. rα (k), ψ rβ (k) remains constant, and the current prediction value at the next moment is only related to the voltage control quantity. The voltage vector remains constant within each control cycle, and the inverter switching state is updated only at the beginning of the next cycle.

[0073] The above current prediction model can be used to predict the output current at future times.

[0074] 1.3 Scrolling Optimization

[0075] In the rolling optimization section, online optimization is implemented by constructing an objective function and comparing the predicted stator current value with the current reference value. The value function in the predictive control of the induction motor model can be taken as:

[0076]

[0077] In this context, the superscript * indicates a reference value, and the superscript p indicates a predicted value.

[0078] In equation (5), the reference value of the αβ axis stator current The predicted values ​​of the αβ axis stator currents are calculated using the flux linkage setpoint, the difference between the speed reference value and the feedback value, and then output by the PI controller. It is given by using equation (4).

[0079] In rolling optimization, the objective function corresponding to the stator current prediction value under all switching vectors is calculated in turn to obtain the predicted current that minimizes the objective function. This predicted current is closest to the given current and can achieve the best actual current tracking effect. The switching state corresponding to this predicted current is taken and applied to the inverter to achieve current tracking control.

[0080] II. Mechanism for Diagnosing Inter-turn Short Circuit Faults

[0081] 2.1 Equivalent Model of Inter-turn Short Circuit Fault in Traction Motor

[0082] Assuming the fault occurs in stator phase A, such as Figure 3 As shown, the short-circuit resistance is R. fs The short-circuit turns ratio, μ, is defined as the ratio of the number of short-circuit turns to the number of turns in the phase winding, representing the size of the short-circuit fault range. The electromagnetic equations of the faulty motor are derived as follows:

[0083]

[0084]

[0085]

[0086]

[0087]

[0088] The electromagnetic equations of the fault circuit are as follows:

[0089]

[0090] In the formula,

[0091] ψ s =[ψ sa ψ sb ψ sc ] T , ψ r =[ψ ra ψ rb ψ rc ] T i s =[i sa i sb i sc ] T i r =[i ra i rb i rc ] T ,

[0092] A1=[-(L′ m +L ls )L′ m / 2L′ m / 2] T A2 = [cosθ r cos(θ r -2 / 3π)cos(θ r +2 / 3π)] T .

[0093] θ r It is the rotor position angle, L′ m It is the mutual inductance between the stator and rotor, L ls It's stator leakage inductance, L lr It's rotor leakage inductance.

[0094] Using the Clarke transformation, the electromagnetic equations of the faulty motor in the stationary coordinate system can be obtained:

[0095]

[0096] Where, k = [cosθ] f sinθ f ], R s =diag(R) s ), R r =diag(R) r ), L s =diag(L s ), L m =diag(L m ), L r =diag(L r ), L m =1.5L′ m L m =1.5L′ m +L ls L r =1.5L′ m +L lr θ f =0, -2 / 3π, 2 / 3π, respectively, indicating that the fault occurred in phases A, B, and C.

[0097] As can be seen from equation (13), after an inter-turn short circuit fault occurs, the stator current can be divided into the stator current of the healthy motor and the fault current caused by the inter-turn short circuit fault.

[0098] The fault current caused by an inter-turn short-circuit fault can also be expressed as:

[0099] i f =I f sin(θ e +θ i (13)

[0100] In the formula, θ e It is the rotor electrical angle. In the early stages of a fault, the short-circuit current can be considered to be in phase with the phase current of that phase. Therefore, θ i It is equal to the current phase of the faulty phase.

[0101] In a stationary coordinate system, the electromagnetic equations of a healthy motor are as follows:

[0102]

[0103] Comparing equations (12) and (14), it is easy to see that an inter-turn short-circuit fault will introduce -2 / 3kμi into the stator current. f Harmonics.

[0104] 2.2 Analysis of Fault Characteristic Signals in the Value Function

[0105] In theory, for a stable traction motor system, there exists

[0106] Therefore, the model predictive control value function simplifies to:

[0107]

[0108] As can be seen from equation (14), inter-turn short circuits will increase the DC content and second harmonic content in the value function.

[0109] Therefore, the predictive control value function is related to the characteristic current of inter-turn short circuit faults and the short-circuit turns ratio. Considering factors such as model error and noise interference, signal processing methods such as Fourier transform can be used to extract fault characteristic signals to realize the diagnosis of inter-turn short circuit faults in traction motors.

[0110] In equation (11), the short-circuit turns are generally small, and the voltage drop across the short-circuit winding is ignored, then we have:

[0111]

[0112] As can be seen from equation (16), the amplitude of the inter-turn short-circuit current is proportional to the electric angular velocity of the motor.

[0113] To eliminate the interference of different motor speeds on fault diagnosis, Equation (15) is further processed as follows to obtain a fault indicator that is independent of motor speed.

[0114]

[0115] In the formula, the subscript x can be 0 or 2, representing the DC component and the second harmonic component.

[0116] Then, by comparing with the fault indicator threshold FI th By comparison, inter-turn short-circuit fault diagnosis can be achieved.

[0117] This embodiment also provides a motor inter-turn short circuit fault diagnosis system based on current prediction error, including a memory and a processor. The memory stores a computer program, and the processor calls the computer program to execute the steps of the motor inter-turn short circuit fault diagnosis method based on current prediction error as described above.

[0118] The following is a specific implementation example of this method.

[0119] In this example, various parameters of the induction motor were simulated, and the corresponding simulation parameters are shown in Table 1.

[0120] Table 1 Simulation parameters of induction motor

[0121] Rated power <![CDATA[P n (kW)]]> 149.2 Rated voltage <![CDATA[U n (V)]]> 460 Rated frequency <![CDATA[f n (Hz)]]> 60 Stator resistance <![CDATA[R s (Oh)]]> 0.01485 Rotor resistance <![CDATA[R r (Oh)]]> 0.009295 Winding mutual inductance <![CDATA[L m (mH)]]> 10.46 stator leakage <![CDATA[L ls (mH)]]> 0.3027 Rotor leakage inductance <![CDATA[L lr (mH)]]> 0.3027 Maximum torque <![CDATA[T emax (Nm)]]> 1200 Given magnetic flux ψ(Wb) 0.73 Extreme logarithm <![CDATA[N p ]]> 2

[0122] The simulation analysis process for fault indicators is as follows:

[0123] Figure 4 This paper presents the amplitude variations of the DC component, first harmonic component, and second harmonic component in the value function of a traction motor operating under rated conditions. Figure 4 As can be seen, compared with a healthy motor, the amplitudes of both the DC component and the second harmonic component increase after an inter-turn short-circuit fault occurs, consistent with the previous analysis. Clearly, the increase in the second harmonic component is more significant; therefore, fault diagnosis can be achieved based on the change in the second harmonic content in the value function.

[0124] Figure 5 This paper presents the changes in fault indicators for healthy and faulty traction motors at speeds ranging from 800 rpm to 1200 rpm. Figure 5 It can be seen that, at different speeds, the fault indicators of the faulty motor are significantly higher than those of the healthy motor, and the fault indicators of the faulty motor have better robustness to changes in speed.

[0125] Figure 6 This paper presents the changes in fault indicators for healthy and faulty traction motors under torque conditions ranging from 0 Nm to 720 Nm. Figure 6 It can be seen that, under different load torques, the fault indicators of the faulty motor are significantly higher than those of the healthy motor.

[0126] Figure 7 The changes in fault indicators of the traction motor are presented when the short-circuit turns ratio is between 0.05 and 0.25. (From...) Figure 7 It can be seen that as the short-circuit turns ratio increases, the fault indicators of the faulty motor show a significant upward trend.

[0127] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.

Claims

1. A method for diagnosing inter-turn short-circuit faults in motors based on current prediction error, characterized in that, Includes the following steps: Construct the electromagnetic equations of the induction motor based on its operating parameters; Discretize the stator current in the electromagnetic equations of the induction motor to obtain a stator current prediction model; The stator current prediction value output by the stator current prediction model is compared with the current reference value to construct the value function of the stator current prediction model; Based on the ratio of the DC component or second harmonic component in the value function to the synchronous electric angular velocity of the induction motor, an inter-turn short-circuit fault index is constructed. During the operation of the traction induction motor, the operating parameters of the induction motor are sampled in real time to predict the stator current, thereby calculating the value function of the stator current prediction model, and then calculating the inter-turn short circuit fault index and comparing it with the preset fault index threshold to diagnose the inter-turn short circuit fault. The calculation expression for the inter-turn short-circuit fault index is as follows: In the formula, FI x This is the calculated value of the inter-turn short-circuit fault index. The subscript x can be 0 or 2, representing the DC component and the second harmonic component, respectively. The result of the value function calculation; synchronous electric angular velocity of the induction motor. , n 1 represents the synchronous speed of the motor rotor magnetic field. n p This represents the number of pole pairs of the motor. The value function expression for the predictive control of the stator current prediction model is: In the formula, , It is the current moment. α and β Reference value for shaft current; , The next moment α and β Predicted value of shaft current; The superscript * indicates a reference value; superscript p Indicates the predicted value; It is equal to the current phase of the faulty phase; This refers to the fault current caused by the inter-turn short-circuit fault; Short-circuit turns ratio; ( k +1) is k The fault current caused by the inter-turn short circuit fault of the motor at time +1; The next moment α and β Predicted value of shaft current and Obtained from the stator current prediction model, the equation of the stator current prediction model is as follows: In the formula, For motor control cycle, For stator resistance, For rotor resistance, For the self-inductance of the equivalent two-phase stator winding, The self-inductance of the rotor's equivalent two-phase winding is... The mutual inductance between the coaxial equivalent windings of the stator and rotor. , representing the leakage coefficient, ψ represents the rotor electromagnetic time constant. rα (k) is k Rotor flux at all times α Axial components, ψ rβ (k) is k Rotor flux at all times Axial components, for k The rotor's mechanical electric angular velocity at all times, for k Stator voltage at any moment Axial components, for k Stator voltage at any time β Axial components.

2. The method for diagnosing inter-turn short-circuit faults in motors based on current prediction error according to claim 1, characterized in that, The fault current caused by the inter-turn short circuit fault The expression is: In the formula, It is the rotor electrical angle; It is the current angle of the phase where the inter-turn short-circuit fault occurs; I f This represents the amplitude of the fault current.

3. The method for diagnosing inter-turn short-circuit faults in motors based on current prediction error according to claim 1, characterized in that, The electromagnetic equation expression for the health-sensing motor is: In the formula, for k The rotor's mechanical electric angular velocity at time +1; J m This refers to the mechanical rotational inertia of the electric motor. T L This represents the motor load torque.

4. The method for diagnosing inter-turn short-circuit faults in motors based on current prediction error according to claim 1, characterized in that, Since inter-turn short circuits increase the DC content and second harmonic content in the value function, and the amplitude of the inter-turn short circuit current is proportional to the synchronous electric angular velocity of the motor, the presence or absence of an inter-turn short circuit fault in the traction motor can be determined based on the DC content or second harmonic content in the value function.

5. The method for diagnosing inter-turn short-circuit faults in motors based on current prediction error according to claim 1, characterized in that, The control strategy for the traction induction motor is model predictive control.

6. The method for diagnosing inter-turn short-circuit faults in a motor based on current prediction error according to claim 5, characterized in that, The switching state corresponding to the predicted current output by the stator current prediction model is applied to the inverter to achieve current tracking control.

7. A motor inter-turn short-circuit fault diagnosis system based on current prediction error, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, and the processor invokes the computer program to perform the steps of the method as described in any one of claims 1 to 6.

Images