Current-based doubly-fed motor speed control method and device

Abstract

The application discloses a current-based doubly-fed motor speed regulation control method and device, and belongs to the technical field of motor control. The application obtains electrical data of a doubly-fed motor, wherein the electrical data comprises stator three-phase voltage, stator three-phase current, rotor three-phase voltage and rotor three-phase current; determines a fault identification result according to the stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, the rotor three-phase current and a preset artificial intelligence model, wherein the fault identification result comprises a fault type label and a severity factor; determines a virtual impedance parameter according to the severity factor; updates a rotor current control loop according to the virtual impedance parameter; and obtains an updated rotor voltage control instruction, thereby achieving the beneficial effect of improving the stability of the operation of the doubly-fed motor under an unbalanced power grid fault.

Description

Technical Field

[0001] This invention relates to the field of motor control technology, and in particular to a current-based speed control method and device for a doubly fed motor. Background Technology

[0002] With technological advancements, doubly-fed induction generators (DFIGs) have gradually become core equipment in variable-speed constant-frequency power generation systems. When grid voltage drops or three-phase imbalance faults occur, significant negative-sequence components are generated in the stator windings. This negative-sequence magnetic field rotates relative to the rotor at twice the grid frequency, inducing high-frequency alternating currents in the rotor windings. This leads to severe overcurrent stress on the rotor-side converter, and may even cause power device burnout, jeopardizing the safe operation of the unit. Traditional vector control strategies are typically designed based on positive-sequence components, exhibiting response lag in suppressing negative-sequence components. Furthermore, they struggle to accurately identify the fault type and severity during fault transients, and cannot achieve adaptive current limiting and impedance regulation. Consequently, the stability of the DFIG operation under unbalanced grid faults decreases. Summary of the Invention

[0003] The present invention aims to solve at least one of the problems existing in the prior art, and to provide a current-based speed control method and device for doubly fed motors.

[0004] One aspect of the present invention provides a current-based speed control method for a doubly-fed induction generator, comprising: Acquire electrical data of the doubly-fed induction generator, including: stator three-phase voltage, stator three-phase current, rotor three-phase voltage, and rotor three-phase current; The fault identification result is determined based on the stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, the rotor three-phase current, and a preset artificial intelligence model. The fault identification result includes a fault type label and a severity factor. The virtual impedance parameters are determined based on the severity factor. The rotor current control loop is updated based on the virtual impedance parameters to obtain the updated rotor voltage control command.

[0005] Optionally, determining the fault identification result based on the stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, the rotor three-phase current, and a preset artificial intelligence model includes: The stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, and the rotor three-phase current are preprocessed to obtain a time-series sampling point sequence; The time-series sampling point sequence is input into the preset artificial intelligence model to obtain the initial fault identification result; The fault identification result is determined based on the initial fault identification result.

[0006] Optionally, before inputting the time-series sampling point sequence into the preset artificial intelligence model to obtain the initial fault identification result, the method further includes: Obtain a historical fault dataset, which includes multiple sets of historical time-series sampling point sequences, corresponding historical fault type labels, and historical severity factors; A training sample set is constructed based on the historical time-series sampling point sequence, the historical fault type label, and the historical severity factor; The initial micro-temporal Transformer model is trained and lightweighted based on the training sample set to obtain the preset artificial intelligence model.

[0007] Optionally, determining the virtual impedance parameter based on the severity factor includes: The virtual resistance is calculated based on the preset initial virtual resistance and the severity factor, and the virtual resistance is positively correlated with the square of the severity of the negative order component; The virtual inductance is calculated based on the preset initial virtual inductance and the severity factor, and the virtual inductance is linearly positively correlated with the severity of the negative sequence component. The virtual impedance parameter is determined based on the virtual resistance and the virtual inductance.

[0008] Optionally, the step of calculating the virtual resistance based on the preset initial virtual resistance and the severity factor includes: Calculate the virtual resistance increment based on the severity factor and the preset gain coefficient; The virtual resistance is determined based on the preset initial virtual resistance and the virtual resistance increment.

[0009] Optionally, after determining the virtual impedance parameter based on the severity factor, the method further includes: The variable gain coefficient is determined based on the rate of change of the severity factor; The virtual impedance parameters are smoothed according to the variable gain coefficient to obtain smoothed virtual impedance parameters. The rotor current control loop is updated based on the smoothed virtual impedance parameters.

[0010] Optionally, before determining the fault identification result based on the stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, the rotor three-phase current, and the preset artificial intelligence model, the method further includes: The voltage drop amplitude is calculated based on the stator three-phase voltage and the stator three-phase current; Determine whether to trigger the fault identification process based on the voltage drop amplitude and the preset threshold. When the fault identification process is triggered, the step of determining the fault identification result based on the preset artificial intelligence model is executed.

[0011] Another aspect of the present invention provides a current-based speed control device for a doubly-fed induction generator, comprising: The acquisition module is used to acquire electrical data of the doubly-fed motor, including: stator three-phase voltage, stator three-phase current, rotor three-phase voltage, and rotor three-phase current; The analysis module is used to determine the fault identification result based on the stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, the rotor three-phase current, and a preset artificial intelligence model. The fault identification result includes a fault type label and a severity factor. A calculation module is used to determine virtual impedance parameters based on the severity factor; The adjustment module is used to update the rotor current control loop according to the virtual impedance parameters to obtain the updated rotor voltage control command.

[0012] In another aspect, the present invention provides a current-based doubly-fed motor speed control device, the current-based doubly-fed motor speed control device comprising: a memory, a processor, and a current-based doubly-fed motor speed control program stored in the memory and executable on the processor, the current-based doubly-fed motor speed control program being configured to implement the steps of the current-based doubly-fed motor speed control method described above.

[0013] In another aspect, the present invention provides a storage medium storing a current-based doubly-fed motor speed control program, wherein when executed by a processor, the current-based doubly-fed motor speed control program implements the steps of the current-based doubly-fed motor speed control method described above.

[0014] The present invention provides a current-based speed control method and apparatus for a doubly-fed motor. By acquiring electrical data of the doubly-fed motor, determining fault identification results based on the stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, the rotor three-phase current, and a preset artificial intelligence model, determining virtual impedance parameters based on the severity factor, and updating the rotor current control loop based on the virtual impedance parameters to obtain an updated rotor voltage control command, thereby improving the stability of the doubly-fed motor operation. Attached Figure Description

[0015] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0016] Figure 1 This is a schematic diagram of the structure of a current-based doubly-fed motor speed control device in the hardware operating environment involved in the embodiments of the present invention; Figure 2 This is a flowchart illustrating the first embodiment of the current-based doubly-fed motor speed control method of the present invention. Figure 3 This is a flowchart illustrating the second embodiment of the current-based doubly-fed motor speed control method of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the various embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, those skilled in the art will understand that many technical details are presented in the embodiments of the present invention to facilitate a better understanding of the invention. However, the technical solutions claimed in the present invention can be implemented even without these technical details and various variations and modifications based on the following embodiments. The division of the following embodiments is for ease of description and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined with and referenced by each other without contradiction.

[0018] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a current-based doubly-fed motor speed control device in the hardware operating environment of an embodiment of the present invention.

[0019] like Figure 1 As shown, the current-based doubly-fed motor speed control device may include: a processor 1001, a communication bus 1002, an interactive device 1003, a network interface 1004, and a memory 1005. The processor 1001 may be a central processing unit (CPU). The communication bus 1002 is used to enable communication between these components. The interactive device 1003 may include a display screen or an input unit such as a keyboard. Optionally, the interactive device 1003 may also be connected to the communication bus via standard wired or wireless interfaces. The network interface 1004 may optionally include standard wired or wireless interfaces (such as a Wi-Fi interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0020] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the current-based doubly-fed motor speed control device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0021] The memory 1005, which serves as a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and a current-based doubly-fed motor speed control program.

[0022] exist Figure 1 In the current-based doubly-fed motor speed control device shown, the network interface 1004 is mainly used for data communication with other devices; the interactive device 1003 is mainly used for data interaction with the user; the processor 1001 and memory 1005 in the current-based doubly-fed motor speed control device of the present invention can be set in the current-based doubly-fed motor speed control device. The current-based doubly-fed motor speed control device calls the current-based doubly-fed motor speed control program stored in the memory 1005 through the processor 1001 and executes the current-based doubly-fed motor speed control method provided in the embodiment of the present invention.

[0023] This invention provides a current-based speed control method for a doubly-fed induction generator (DFIG), referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of a current-based speed control method for a doubly fed motor according to the present invention.

[0024] In this embodiment, the current-based doubly fed motor speed control method includes steps S1 to S4.

[0025] Step S1: Obtain the electrical data of the doubly fed motor, including: stator three-phase voltage, stator three-phase current, rotor three-phase voltage, and rotor three-phase current.

[0026] In this embodiment, optionally, sensors are installed on the stator and rotor sides of the doubly-fed induction generator (DFIG) to obtain the stator three-phase voltage, stator three-phase current, rotor three-phase voltage, and rotor three-phase current. This data can characterize the symmetrical or asymmetrical fault features on the grid side, and can also express the transient response information of the rotor-side induced current.

[0027] Step S2: Determine the fault identification result based on the stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, the rotor three-phase current, and the preset artificial intelligence model. The fault identification result includes a fault type label and a severity factor.

[0028] In this embodiment, it should be noted that the stator three-phase voltage, stator three-phase current, rotor three-phase voltage, and rotor three-phase current need to be normalized. Optionally, data from different time ranges can be selected through a sliding window, generally including the electrical data at the current moment and data from a period of time prior to the current moment. The selected data is input into the preset artificial intelligence model to determine the fault identification result, and the fault identification result is output based on the preset artificial intelligence model.

[0029] Step S3: Determine the virtual impedance parameter based on the severity factor.

[0030] In this embodiment, the virtual impedance parameter is determined based on the obtained severity factor and through a preset mapping function or lookup table. The virtual impedance parameter typically includes virtual resistance and virtual inductance, and its value is positively correlated with the severity factor—that is, the more severe the grid imbalance, the larger the virtual impedance value. It should be explained that virtual impedance control is a technique that simulates series impedance in the control loop using software algorithms to limit current surges during fault transients. By dynamically adjusting this parameter, the doubly-fed induction generator (DFIG) can maintain low impedance to ensure efficiency during minor imbalances and increase impedance to suppress rotor overcurrent during severe faults, achieving a trade-off between protection thresholds and operating efficiency, and providing an adaptive current constraint boundary for the safe operation of the rotor-side converter.

[0031] Step S4: Update the rotor current control loop according to the virtual impedance parameters to obtain the updated rotor voltage control command.

[0032] Specifically, virtual impedance parameters are injected into the rotor current control loop in real time. By reconstructing the output equation of the current regulator, the virtual impedance voltage drop is superimposed on the original rotor voltage control command. Optionally, the specific virtual resistance is multiplied by the vector sum of the rotor current and the virtual inductance multiplied by the current differential to obtain the updated rotor voltage control command. The rotor voltage control command, along with the power devices of the rotor-side converter driven by space vector modulation, is used to adjust the voltage amplitude and phase applied to the rotor winding in real time.

[0033] Through this update mechanism, the control loop automatically exhibits high impedance characteristics during grid fault transients, effectively suppressing the high-frequency rotor current induced by the negative sequence magnetic field, preventing the converter overcurrent protection from tripping or the power devices from burning out, and enabling the doubly fed motor to achieve low voltage ride-through and safe operation under unbalanced grid faults.

[0034] In this embodiment, by acquiring the electrical data of the doubly-fed motor, determining the fault identification result based on the stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, the rotor three-phase current, and the preset artificial intelligence model, determining the virtual impedance parameter based on the severity factor, updating the rotor current control loop based on the virtual impedance parameter, and obtaining the updated rotor voltage control command, the stability of the doubly-fed motor operation can be improved.

[0035] Furthermore, based on the first embodiment, a second embodiment of the current-based doubly-fed motor speed control method of the present invention is proposed. In this embodiment, reference is made to... Figure 3 The step of determining the fault identification result based on the stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, the rotor three-phase current, and the preset artificial intelligence model includes steps S21 to S23.

[0036] Step S21: Preprocess the stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, and the rotor three-phase current to obtain a time-series sampling point sequence.

[0037] Specifically, the preprocessing here includes: first, eliminating high-frequency sampling noise and electromagnetic interference through a low-pass filter; second, normalization processing to map voltage and current values ​​of different dimensions to a unified numerical range; and then, aligning and splicing them according to timestamps to form a time-series sampling point sequence. It should be noted that since the sequence here is a fixed-length time window data, it contains the instantaneous values ​​of voltage and current and their historical trajectories, which not only preserves the waveform characteristics of the fault transient, but also meets the dimensional requirements of the input tensor for deep learning models.

[0038] Step S22: Input the time-series sampling point sequence into the preset artificial intelligence model to obtain the initial fault identification result.

[0039] The pre-defined AI model here uses a miniature temporal Transformer architecture. Optionally, it captures long-range dependencies and local features in the sequence through a self-attention mechanism, and outputs initial fault identification results through forward propagation. The results here include the original score distribution of fault type labels and regression values ​​of the severity of negative-order components.

[0040] Step S23: Determine the fault identification result based on the initial fault identification result.

[0041] In this embodiment, the original scores are converted into a probability distribution using the Softmax function, and the index of the maximum value is used to determine the final fault type label. At the same time, the severity factor is smoothed by moving average or subjected to amplitude limiting to eliminate instantaneous jitter. When the consistency of results in multiple consecutive frames is lower than the confidence threshold, a time series voting mechanism or model integration strategy is triggered to finally generate a stable and reliable fault identification result.

[0042] In this embodiment, the stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, and the rotor three-phase current are preprocessed to obtain a time-series sampling point sequence. The time-series sampling point sequence is then input into the preset artificial intelligence model to obtain an initial fault identification result. Based on the initial fault identification result, the fault identification result is determined, thereby improving the accuracy of the fault identification result.

[0043] Furthermore, before inputting the time-series sampling point sequence into the preset artificial intelligence model to obtain the initial fault identification result, the method further includes: Obtain a historical fault dataset, which includes multiple sets of historical time-series sampling point sequences, corresponding historical fault type labels, and historical severity factors; A training sample set is constructed based on the historical time-series sampling point sequence, the historical fault type label, and the historical severity factor; The initial micro-temporal Transformer model is trained and lightweighted based on the training sample set to obtain the preset artificial intelligence model.

[0044] In this embodiment, a historical fault dataset is acquired offline before model deployment. This dataset covers multiple fault cases recorded in actual power grid operation, including typical operating conditions such as voltage dips, single-phase grounding, and phase-to-phase short circuits. Each set of historical time-series sampling points is assigned a corresponding historical fault type label and a historical severity factor ground value through manual annotation or simulation generation, constructing a training sample set for supervised learning. Furthermore, stator three-phase voltage, stator three-phase current, rotor three-phase voltage, and rotor three-phase current within a continuous time window are extracted from the historical fault dataset to form a historical time-series sampling point sequence as input features. Simultaneously, based on waveform analysis at the fault occurrence time and expert experience, corresponding historical fault type labels are labeled. Optionally, a historical severity factor calculated based on voltage proportion is used as the output label. The lightweight processing here includes knowledge distillation, weight quantization, or structured pruning techniques to compress the model size.

[0045] In this embodiment, a historical fault dataset is obtained, and a training sample set is constructed based on the historical time-series sampling point sequence, the historical fault type label, and the historical severity factor. The initial micro-time-series Transformer model is trained and lightweighted based on the training sample set to obtain the preset artificial intelligence model, thereby improving the accuracy of the model.

[0046] Furthermore, based on the first or second embodiment, a third embodiment of the current-based doubly-fed motor speed control method of the present invention is proposed. In this embodiment, determining the virtual impedance parameter according to the severity factor includes: The virtual resistance is calculated based on the preset initial virtual resistance and the severity factor, and the virtual resistance is positively correlated with the square of the severity of the negative order component; The virtual inductance is calculated based on the preset initial virtual inductance and the severity factor, and the virtual inductance is linearly positively correlated with the severity of the negative sequence component. The virtual impedance parameter is determined based on the virtual resistance and the virtual inductance.

[0047] In this embodiment, it should be noted that the negative-sequence severity factor is a normalized index used to quantify the severity of grid voltage or current asymmetry faults. It is typically defined as the ratio of the negative-sequence component amplitude to the positive-sequence component amplitude. Using the negative-sequence severity factor, virtual resistance and virtual inductance are calculated to construct complete virtual impedance parameters. The virtual resistance is positively correlated with the square of the severity factor. This nonlinear mapping relationship causes the resistance value to increase exponentially when the grid is severely unbalanced, thereby strongly suppressing overcurrent surges and power losses on the rotor side. The virtual inductance, on the other hand, maintains a linear positive correlation with the severity factor, ensuring adequate phase lag compensation during dynamic processes and maintaining system stability.

[0048] Furthermore, the step of calculating the virtual resistance based on the preset initial virtual resistance and the severity factor includes: Calculate the virtual resistance increment based on the severity factor and the preset gain coefficient; The virtual resistance is determined based on the preset initial virtual resistance and the virtual resistance increment.

[0049] In this embodiment, optionally, the formula for calculating the virtual resistance is: Rv = Rv0 + α × (Kneg) 2 ; Where Rv is the virtual resistance, Rv0 is the preset initial virtual resistance, α is the preset gain coefficient, and Kneg is the negative sequence component severity factor. Optionally, the negative sequence component severity factor is extracted, which characterizes the intensity of the grid voltage asymmetry fault. This factor is then multiplied by the preset gain coefficient, and the product is squared to obtain the virtual resistance increment. This squared relationship ensures that the virtual resistance increment grows non-linearly and rapidly with the fault severity, ensuring a gradual increase in resistance to maintain efficiency during minor asymmetries.

[0050] In this embodiment, the accuracy of the virtual resistance can be improved by calculating the virtual resistance increment based on the severity factor and the preset gain coefficient, and determining the virtual resistance based on the preset initial virtual resistance and the virtual resistance increment.

[0051] Furthermore, based on any of the above embodiments, a fourth embodiment of the current-based doubly-fed motor speed control method of the present invention is proposed. In this embodiment, after determining the virtual impedance parameter according to the severity factor, the method further includes: The variable gain coefficient is determined based on the rate of change of the severity factor; The virtual impedance parameters are smoothed according to the variable gain coefficient to obtain smoothed virtual impedance parameters. The rotor current control loop is updated based on the smoothed virtual impedance parameters.

[0052] In this embodiment, the smoothed virtual impedance parameters are injected into the voltage feedforward or feedback loop of the rotor current control circuit in real time, and the rotor voltage control command is reconstructed according to the definition of virtual impedance. Specifically, the calculation is to add the virtual impedance voltage drop term to the original current regulator output voltage to form an updated rotor voltage reference value.

[0053] Furthermore, before determining the fault identification result based on the stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, the rotor three-phase current, and the preset artificial intelligence model, the method further includes: The voltage drop amplitude is calculated based on the stator three-phase voltage and the stator three-phase current; Determine whether to trigger the fault identification process based on the voltage drop amplitude and the preset threshold. When the fault identification process is triggered, the step of determining the fault identification result based on the preset artificial intelligence model is executed.

[0054] In this embodiment, when the fault identification process is triggered, the system immediately starts the preset artificial intelligence model and inputs the stator three-phase voltage, stator three-phase current, rotor three-phase voltage and rotor three-phase current into the lightweight micro time series model; the model calculates through forward inference and outputs the fault identification result containing fault type label and negative sequence component severity factor.

[0055] Furthermore, this embodiment of the invention also proposes a current-based doubly-fed motor speed control device, which includes an acquisition module, an analysis module, a calculation module, and an adjustment module.

[0056] The acquisition module is used to acquire electrical data of the doubly fed motor, including: stator three-phase voltage, stator three-phase current, rotor three-phase voltage, and rotor three-phase current.

[0057] The analysis module is used to determine the fault identification result based on the stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, the rotor three-phase current, and a preset artificial intelligence model. The fault identification result includes a fault type label and a severity factor.

[0058] A calculation module is used to determine the virtual impedance parameters based on the severity factor.

[0059] The adjustment module is used to update the rotor current control loop according to the virtual impedance parameters to obtain the updated rotor voltage control command.

[0060] Furthermore, this invention also proposes a current-based doubly-fed motor speed control device, which includes: a memory, a processor, and a current-based doubly-fed motor speed control program stored in the memory and executable on the processor. The current-based doubly-fed motor speed control program is configured to perform the steps of the current-based doubly-fed motor speed control method described in any of the above embodiments.

[0061] Furthermore, this embodiment of the invention also proposes a storage medium storing a current-based doubly-fed motor speed control program. When the current-based doubly-fed motor speed control program is executed by a processor, it implements the steps of the current-based doubly-fed motor speed control method described in any of the above embodiments.

[0062] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0063] Those skilled in the art will understand that the above embodiments are specific implementations of the present invention, and in practical applications, various changes can be made in form and detail without departing from the spirit and scope of the present invention.

Claims

1. A speed control method for a doubly-fed induction generator based on current, characterized in that, include: Acquire electrical data of the doubly-fed induction generator, including: stator three-phase voltage, stator three-phase current, rotor three-phase voltage, and rotor three-phase current; The fault identification result is determined based on the stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, the rotor three-phase current, and a preset artificial intelligence model. The fault identification result includes a fault type label and a severity factor. The virtual impedance parameters are determined based on the severity factor. The rotor current control loop is updated based on the virtual impedance parameters to obtain the updated rotor voltage control command.

2. The speed control method for a doubly-fed induction generator based on current according to claim 1, characterized in that, The step of determining the fault identification result based on the stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, the rotor three-phase current, and a preset artificial intelligence model includes: The stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, and the rotor three-phase current are preprocessed to obtain a time-series sampling point sequence; The time-series sampling point sequence is input into the preset artificial intelligence model to obtain the initial fault identification result; The fault identification result is determined based on the initial fault identification result.

3. The current-based speed control method for a doubly-fed induction generator according to claim 2, characterized in that, Before inputting the time-series sampling point sequence into the preset artificial intelligence model to obtain the initial fault identification result, the method further includes: Obtain a historical fault dataset, which includes multiple sets of historical time-series sampling point sequences, corresponding historical fault type labels, and historical severity factors; A training sample set is constructed based on the historical time-series sampling point sequence, the historical fault type label, and the historical severity factor; The initial micro-temporal Transformer model is trained and lightweighted based on the training sample set to obtain the preset artificial intelligence model.

4. The current-based speed control method for a doubly-fed induction generator according to claim 1, characterized in that, Determining the virtual impedance parameter based on the severity factor includes: The virtual resistance is calculated based on the preset initial virtual resistance and the severity factor, and the virtual resistance is positively correlated with the square of the severity of the negative order component; The virtual inductance is calculated based on the preset initial virtual inductance and the severity factor, and the virtual inductance is linearly positively correlated with the severity of the negative sequence component. The virtual impedance parameter is determined based on the virtual resistance and the virtual inductance.

5. The current-based speed control method for a doubly-fed induction generator according to claim 4, characterized in that, The step of calculating the virtual resistance based on the preset initial virtual resistance and the severity factor includes: Calculate the virtual resistance increment based on the severity factor and the preset gain coefficient; The virtual resistance is determined based on the preset initial virtual resistance and the virtual resistance increment.

6. The current-based speed control method for a doubly-fed induction generator according to claim 1, characterized in that, After determining the virtual impedance parameter based on the severity factor, the method further includes: The variable gain coefficient is determined based on the rate of change of the severity factor; The virtual impedance parameters are smoothed according to the variable gain coefficient to obtain smoothed virtual impedance parameters. The rotor current control loop is updated based on the smoothed virtual impedance parameters.

7. The current-based speed control method for a doubly-fed induction generator according to any one of claims 1 to 6, characterized in that, Before determining the fault identification result based on the stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, the rotor three-phase current, and the preset artificial intelligence model, the method further includes: The voltage drop amplitude is calculated based on the stator three-phase voltage and the stator three-phase current; Determine whether to trigger the fault identification process based on the voltage drop amplitude and the preset threshold. When the fault identification process is triggered, the step of determining the fault identification result based on the preset artificial intelligence model is executed.

8. A speed control device for a doubly-fed induction generator based on current, characterized in that, include: The acquisition module is used to acquire electrical data of the doubly-fed motor, including: stator three-phase voltage, stator three-phase current, rotor three-phase voltage, and rotor three-phase current; The analysis module is used to determine the fault identification result based on the stator three-phase voltage, the stator three-phase current, the rotor three-phase voltage, the rotor three-phase current, and a preset artificial intelligence model. The fault identification result includes a fault type label and a severity factor. A calculation module is used to determine virtual impedance parameters based on the severity factor; The adjustment module is used to update the rotor current control loop according to the virtual impedance parameters to obtain the updated rotor voltage control command.

9. A speed control device for a doubly-fed induction generator based on current, characterized in that, The current-based doubly-fed motor speed control device includes: a memory, a processor, and a current-based doubly-fed motor speed control program stored in the memory and executable on the processor, wherein the current-based doubly-fed motor speed control program is configured to implement the steps of the current-based doubly-fed motor speed control method according to any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores a current-based doubly-fed motor speed control program, which, when executed by a processor, implements the steps of the current-based doubly-fed motor speed control method according to any one of claims 1 to 7.

Images