Method and device for determining parameters of doubly-fed wind generator, medium and electronic equipment

Abstract

The invention discloses a doubly-fed wind generator parameter determination method and device, a medium and electronic equipment, and relates to the field of power equipment. The parameter identification efficiency of the doubly-fed wind generator can be improved. The method for determining the parameters of the doubly-fed wind generator comprises the following steps: measuring to obtain three-phase electrical parameters of the doubly-fed wind generator, and converting the three-phase electrical parameters into a two-phase coordinate system to obtain two-phase electrical parameters; inputting the two-phase electrical parameters into a deep learning model to obtain an identification parameter estimation value output by the deep learning model; based on the identification parameter estimation value and the two-phase electrical parameter, calculating an electrical parameter estimation value when the identification parameter estimation value is taken by the doubly-fed wind generator; training the deep learning model based on the difference between the three-phase electrical parameter and the electrical parameter estimation value to obtain a trained deep learning model; and obtaining identification parameters of the doubly-fed wind generator through the trained deep learning model.

Description

Technical Field

[0001] The present application relates to the field of electric power equipment, and in particular to a method, device, medium and electronic equipment for determining parameters of a doubly-fed wind turbine generator. Background Art

[0002] Doubly Fed Induction Generator (DFIG) is a highly efficient variable speed wind power generation technology that combines the design concepts of synchronous and asynchronous generators to adapt to the volatility and unpredictability of wind power. The working principle of DFIG is similar to that of traditional induction motors, but it has a unique rotor circuit design that enables it to perform excellently in wind power generation systems. Thanks to its advantages in variable speed operation and high efficiency power generation, the application of doubly fed wind generators is becoming more and more extensive. The efficient and stable operation of doubly fed wind generators has high requirements for accurate parameter identification. Traditional parameter identification methods face the problems of insufficient accuracy and low efficiency when dealing with complex systems with multiple variables interacting. Summary of the invention

[0003] The present application provides a method, device, medium and electronic equipment for determining parameters of a doubly-fed wind generator, which can adapt to various operating conditions of a wind power system, accurately identify parameters, and enhance the operating stability of the doubly-fed wind generator.

[0004] In a first aspect, the present application provides a method for determining parameters of a doubly fed wind generator, comprising: measuring and obtaining three-phase electrical parameters of the doubly fed wind generator, and converting the three-phase electrical parameters into a two-phase coordinate system to obtain two-phase electrical parameters; inputting the two-phase electrical parameters into a deep learning model to obtain identification parameter estimates output by the deep learning model; calculating electrical parameter estimates of the doubly fed wind generator when the identification parameter estimates are taken based on the identification parameter estimates and the two-phase electrical parameters; training the deep learning model based on the difference between the three-phase electrical parameters and the electrical parameter estimates to obtain a trained deep learning model; and obtaining identification parameters of the doubly fed wind generator through the trained deep learning model.

[0005] According to the parameter determination method of the doubly fed wind generator of the present application, the three-phase electrical parameters of the doubly fed wind generator are measured and converted into a two-phase coordinate system to obtain the two-phase electrical parameters, and then the two-phase electrical parameters are input into the deep learning model, and the identification parameter estimation values ​​are obtained through model prediction, and then the identification parameter estimation values ​​obtained through model prediction and the two-phase electrical parameters are used to calculate the corresponding electrical parameter estimation values ​​when the parameters of the doubly fed wind generator are the identification parameters predicted by the model, and finally the deep learning model is trained by the electrical parameter estimation values ​​and the measured three-phase electrical parameters to obtain the final identification parameters. With this scheme, only the three-phase electrical parameters of the doubly fed wind generator need to be measured, and it does not rely on variables related to different operating states, which can enhance the stability of the parameter identification of the doubly fed wind generator; and the identification parameters output by the deep learning model are verified by the three-phase electrical parameters obtained by real measurement, which can improve the accuracy of the identification parameters; at the same time, the calculation process is simple and has high efficiency.

[0006] In an exemplary implementation, the two-phase electrical parameters include an α-axis current, a β-axis current, an α-axis voltage, and a β-axis voltage on the stator side of the doubly-fed wind turbine generator.

[0007] In an exemplary embodiment, the inputting the two-phase electrical parameters into a deep learning model to obtain estimated values ​​of identification parameters output by the deep learning model includes: when the two-phase electrical parameters are the α-axis current, β-axis current, α-axis voltage, and β-axis voltage of the stator side, the α-axis current, β-axis current, α-axis voltage, and β-axis voltage of the stator side are input into the deep learning model to obtain estimated values ​​of identification parameters of the stator side output by the deep learning model, wherein the estimated values ​​of identification parameters of the stator side include stator winding, stator self-inductance, and mutual inductance.

[0008] In an exemplary embodiment, the electrical parameter estimation value of the doubly fed wind generator when taking the identification parameter estimation value based on the identification parameter estimation value and the two-phase electrical parameters includes: obtaining a first dynamic equation between current, voltage and flux of the doubly fed wind generator in a two-phase coordinate system, solving the first dynamic equation based on the α-axis current, β-axis current, α-axis voltage, β-axis voltage, and stator winding on the stator side to obtain α-axis flux and β-axis flux; obtaining a second dynamic equation between flux and current of the doubly fed wind generator in a two-phase coordinate system; solving the second dynamic equation based on the α-axis flux and β-axis flux, the stator self-inductance and the mutual inductance to obtain the α-axis current and β-axis current on the rotor side; converting the α-axis current and β-axis current to a three-phase coordinate system to obtain an A-phase current estimation value, a B-phase current estimation value and a C-phase current estimation value.

[0009] In an exemplary embodiment, the three-phase electrical parameters include the three-phase current on the rotor side, and the parameter estimation value includes the three-phase current estimation value on the rotor side; the training of the deep learning model based on the difference between the three-phase electrical parameters and the parameter estimation value includes: obtaining an objective function, solving the objective function through the difference between the three-phase current on the rotor side and the three-phase current estimation value on the rotor side to obtain an identification error; the objective function is:

[0010]

[0011] Where l is the number of sampling points, i rai 、i rbi 、i rci is the three-phase current of the i-th sampling point; i′ rai , i′ rbi , i′ rci is the three-phase current estimation value of the i-th sampling point, and F is the recognition error; the deep learning model is trained based on the recognition error.

[0012] In an exemplary embodiment, the electrical parameter estimation value also includes a two-phase electrical parameter estimation value on the rotor side, and the method further includes: training the deep learning model based on the difference between the two-phase electrical parameters and the two-phase electrical parameter estimation value on the rotor side.

[0013] In an exemplary embodiment, the deep learning model includes an input layer, a hidden layer and an output layer, the input layer includes a plurality of nodes, and the plurality of nodes correspond one-to-one to the two-phase electrical parameters; inputting the two-phase electrical parameters into the deep learning model includes: inputting the two-phase electrical parameters into the respective corresponding nodes.

[0014] In a second aspect, the present application provides a parameter determination device for a doubly fed wind generator, comprising: a parameter measurement module, used to measure and obtain the three-phase electrical parameters of the doubly fed wind generator, and convert the three-phase electrical parameters into a two-phase coordinate system to obtain the two-phase electrical parameters; a model identification module, used to input the two-phase electrical parameters into a deep learning model to obtain the identification parameter estimation values ​​output by the deep learning model; a parameter calculation module, used to calculate the electrical parameter estimation values ​​of the doubly fed wind generator when the identification parameter estimation values ​​are taken based on the identification parameter estimation values ​​and the two-phase electrical parameters; a model training module, used to train the deep learning model based on the difference between the three-phase electrical parameters and the electrical parameter estimation values ​​to obtain the trained deep learning model; a parameter determination module, used to obtain the identification parameters of the doubly fed wind generator through the trained deep learning model.

[0015] In a third aspect, the present application provides an electronic device, the electronic device comprising a memory and one or more processors. The memory stores one or more computer programs, the computer programs comprising instructions, and when the instructions are executed by the processor, the electronic device can execute the parameter determination method of the doubly-fed wind turbine generator in the first aspect.

[0016] In a fourth aspect, the present application provides a computer-readable storage medium having instructions stored therein, which, when executed on an electronic device, enables the electronic device to execute the parameter determination method for a doubly-fed wind turbine generator as in the first aspect.

[0017] In a fifth aspect, the present application provides a computer program product. When the computer program product is run on an electronic device, the electronic device executes the parameter determination method of the doubly-fed wind generator as described in the first aspect.

[0018] It can be understood that the beneficial effects that can be achieved by the above-mentioned doubly-fed wind generator parameter determination device, electronic device, computer-readable storage medium, and computer program product can refer to the beneficial effects in the first aspect and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic diagram of a flow chart of a method for determining parameters of a doubly-fed wind turbine generator provided in an embodiment of the present application;

[0020] Figure 2 A schematic diagram of the structure of a device for determining parameters of a doubly-fed wind turbine generator provided in an embodiment of the present application;

[0021] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, the words "first", "second" and the like are used to distinguish the same items or similar items with substantially the same functions and effects. For example, the first chip and the second chip are only used to distinguish different chips, and their order is not limited. Those skilled in the art can understand that the words "first", "second" and the like do not limit the quantity and execution order, and the words "first", "second" and the like do not necessarily limit the difference. It should be noted that in the embodiments of the present application, the words "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or design solutions. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way. In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more.

[0023] It should be noted that the “at…” in the embodiments of the present application may be the instant when a certain situation occurs, or may be a period of time after the occurrence of a certain situation, and the embodiments of the present application do not specifically limit this.

[0024] The implementation of this embodiment will be described in detail below with reference to the accompanying drawings.

[0025] This embodiment first provides a method for determining the parameters of a doubly-fed wind turbine generator. By way of example, the method for determining the parameters of a doubly-fed wind turbine generator can be applied to various electronic devices such as computers (PCs), tablet computers, virtual reality / augmented reality devices, wearable devices, industrial computers, and vehicle computers; it can also be applied to servers, cloud computing, server clusters, etc., and this embodiment does not make any special limitations on this.

[0026] Figure 1 A schematic flow chart of a method for determining parameters of a doubly-fed wind turbine generator provided in an embodiment of the present application is shown.

[0027] like Figure 1 As shown, the method for determining parameters of the doubly-fed wind turbine generator may include the following steps:

[0028] Step 101: Measure and obtain three-phase electrical parameters of a doubly-fed wind turbine generator, and convert the three-phase electrical parameters into a two-phase coordinate system to obtain two-phase electrical parameters.

[0029] In a doubly-fed wind turbine, the stator refers to the stationary part of the motor. The stator is composed of coil windings and is responsible for generating a rotating magnetic field. It is the starting point for electromagnetic energy conversion. The rotor is the part opposite to the stator. The rotor contains coil windings and can rotate under the drive of the wind wheel. Its speed can be adjusted according to changes in wind speed.

[0030] The three-phase electrical parameters refer to the current and voltage in the three-phase (A phase, B phase, C phase) coordinate system (also called the abc coordinate system). The three-phase electrical parameters of the doubly fed wind turbine generator can include the three-phase current and the three-phase voltage on the stator side, as well as the three-phase current and the three-phase voltage on the rotor side.

[0031] The three-phase electrical parameters of the doubly-fed wind generator can be obtained by measuring the current and voltage on the stator side and the rotor side of the doubly-fed wind generator respectively.

[0032] The two-phase coordinate system refers to the αβ coordinate system. According to the conversion relationship between the abc coordinate system and the αβ coordinate system, the three-phase electrical parameters of the abc coordinate system can be converted into two-phase electrical parameters in the αβ coordinate system. Specifically, the two-phase electrical parameters may include the α-axis current, α-axis voltage, β-axis current and β-voltage on the stator side; and may also include the α-axis current, α-axis voltage, β-axis current and β-voltage on the rotor side.

[0033] Step 102: Input the two-phase electrical parameters into a deep learning model to obtain estimated values ​​of identification parameters output by the deep learning model.

[0034] The estimated value of the identification parameter refers to the value of the identification parameter. In this embodiment, the input variables of the deep learning model are two-phase electrical parameters, and the output variables are the estimated values ​​of the identification parameters. The identification parameters may include parameters on the stator side, such as stator windings, stator self-inductance, and mutual inductance; and may also include parameters on the rotor side, such as rotor windings and rotor self-inductance.

[0035] In this embodiment, the deep learning model can be a multi-layer deep neural network model, specifically including an input layer, a hidden layer and an output layer. Among them, the input layer includes a plurality of nodes, and the number of nodes in the input layer is consistent with the number of two-phase electrical parameters. Each node corresponds to one of the two-phase electrical parameters of the doubly fed wind turbine. Each parameter of the two-phase electrical parameters is input to the corresponding node respectively. The hidden layer is composed of a plurality of sublayers, each of which contains a certain number of neurons, and a nonlinear activation function such as a rectified linear unit (ReLU) or a hyperbolic tangent function (tanh) is used to process the two-phase electrical parameters input by the input layer to obtain an output. The output layer includes one or more neurons, which can specifically correspond to the number of identification parameters, and each neuron can output an estimated value of an identification parameter after processing.

[0036] The weights and thresholds of each layer of the deep learning model can be initially determined based on experience or randomly selected. The two-phase electrical parameters, such as the α-axis current, α-axis voltage, β-axis current and β-voltage on the stator side, are respectively input to the corresponding nodes in the input layer, and the corresponding identification parameter estimates are obtained through the mapping of the deep learning model.

[0037] It can be understood that when the input layer inputs the electrical parameters of the stator side, the output layer outputs the estimated values ​​of the identification parameters of the stator side accordingly.

[0038] Specifically, when the two-phase electrical parameters are the α-axis current, β-axis current, α-axis voltage, and β-axis voltage on the stator side, the α-axis current, β-axis current, α-axis voltage, and β-axis voltage on the stator side are input into the deep learning model to obtain the estimated values ​​of the identification parameters of the stator side output by the deep learning model, and the estimated values ​​of the identification parameters on the stator side include stator winding, stator self-inductance, and mutual inductance.

[0039] When the two-phase electrical parameters are the α-axis current, β-axis current, α-axis voltage, and β-axis voltage on the rotor side, the α-axis current, β-axis current, α-axis voltage, and β-axis voltage on the rotor side are input into the deep learning model to obtain the estimated values ​​of the identification parameters of the rotor side output by the deep learning model, and the estimated values ​​of the identification parameters on the rotor side include the rotor winding and the rotor self-inductance.

[0040] The deep learning model in this embodiment can receive multi-dimensional data input, perform nonlinear mapping in the process of hidden layer transmission, extract features, enhance the nonlinear expression ability of the network, identify complex patterns in the data by extracting features, and then learn and adapt to the mapping relationship under different modes, thereby improving the accuracy of the model in identifying identification parameters.

[0041] Exemplarily, the input layer of the deep learning model may include nodes consistent with the number of three-phase electrical parameters. Through training, the deep learning model can also learn the relationship between the three-phase electrical parameters and the identification parameters. The trained deep learning model can also receive three-phase electrical parameter inputs, that is, use phase A current, phase B current, phase C current and phase A voltage, phase B voltage, and phase C voltage as inputs of the deep learning model, and predict the output corresponding identification parameter estimates.

[0042] Step 103: Calculating the estimated electrical parameter values ​​of the doubly-fed wind turbine generator when the estimated identification parameter values ​​are taken based on the estimated identification parameter values ​​and the two-phase electrical parameters.

[0043] After obtaining the estimated values ​​of the identification parameters predicted by the deep learning model, the electrical parameters of the doubly-fed wind turbine generator under the estimated values ​​of the identification parameters, that is, the estimated values ​​of the electrical parameters, can be calculated based on the predicted estimated values ​​of the identification parameters.

[0044] The electrical parameter estimation value may specifically include the three-phase current on the rotor side, or the two-phase current on the rotor side; it may also include the three-phase current on the stator side, or the two-phase current on the stator side. Specifically, when the two-phase electrical parameters are the α-axis current, β-axis current, α-axis voltage, and β-axis voltage on the stator side, and the identification parameter estimation values ​​are the stator self-inductance, stator winding, and mutual inductance, a first dynamic equation between the current, voltage, and flux of the doubly fed wind generator in a two-phase coordinate system is obtained, and the first dynamic equation is solved based on the α-axis current, β-axis current, α-axis voltage, β-axis voltage, and stator winding on the stator side to obtain the α-axis flux and β-axis flux; a second dynamic equation between the flux and current of the doubly fed wind generator in a two-phase coordinate system is obtained; the second dynamic equation is solved based on the α-axis flux and β-axis flux, the stator self-inductance, and the mutual inductance to obtain the α-axis current and β-axis current on the rotor side; the α-axis current and β-axis current are converted to a three-phase coordinate system to obtain an estimated value of phase A current, an estimated value of phase B current, and an estimated value of phase C current.

[0045] Among them, the first kinetic equation is as follows:

[0046]

[0047] Among them, u sα is the α-axis voltage on the stator side, u sβ is the β-axis voltage on the stator side, r s is the winding on the stator side, i sα is the α-axis current on the stator side, i sβ is the β-axis current on the stator side, ψ sα and ψ sβ are the magnetic flux along the α-axis and β-axis respectively, and p represents the derivative.

[0048] The α-axis current, β-axis current, α-axis voltage, and β-axis voltage on the stator side are obtained by measurement, and the stator winding is obtained by model prediction. These parameters are substituted into the above formula (1) to solve the α-axis flux and β-axis flux.

[0049] The second kinetic equation is:

[0050]

[0051] Among them, L s is the stator self-inductance, L m is the mutual inductance between the stator and the rotor. rα is the α-axis current on the rotor side, i rβ is the β-axis current on the rotor side. Substituting the known quantities of α-axis flux and β-axis flux, stator self-inductance and mutual inductance into the above formula (2), the α-axis current and β-axis current on the rotor side are calculated.

[0052] In order to align the coordinate systems of the stator side and the rotor side, the α-axis current and β-axis current calculated on the rotor side can be uniformly transformed to the αβ coordinate system on the stator side. The transformation relationship is as follows:

[0053]

[0054] i′ rα is the transformed rotor side α-axis current, i′ rβ is the transformed rotor side β-axis current, and θ is the coordinate axis angle. The transformation can align the coordinate systems of the stator side and the rotor side, thereby reducing the calculation error.

[0055] Through the transformation relationship between the abc coordinate system and the αβ coordinate system, the calculated α-axis current and β-axis current on the rotor side are transformed into the abc coordinate system to obtain the estimated value of the A-phase current, the estimated value of the B-phase current, and the estimated value of the C-phase current on the rotor side. The estimated value of the A-phase current, the estimated value of the B-phase current, and the estimated value of the C-phase current on the rotor side are called the three-phase current on the rotor side.

[0056] Next, step 104: training the deep learning model based on the difference between the three-phase electrical parameters and the electrical parameter estimation values ​​to obtain a trained deep learning model.

[0057] After calculating the estimated values ​​of the electrical parameters of the doubly-fed wind turbine generator under the condition of the estimated values ​​of the identification parameters, the error size of the model prediction can be calculated based on the calculated estimated values ​​of the electrical parameters and the actual three-phase electrical parameters of the doubly-fed wind turbine generator measured in step 101. Specifically, this embodiment may include: obtaining an objective function, solving the objective function through the difference between the three-phase current on the rotor side and the estimated value of the three-phase current on the rotor side, obtaining an identification error, and training the deep learning model based on the identification error. Wherein, the objective function is:

[0058]

[0059] Where l is the number of sampling points, i rai 、i rbi 、i rci is the three-phase current of the i-th sampling point; i′ rai , i′ rbi , i′ rci is the estimated value of the three-phase current at the i-th sampling point, and F is the identification error.

[0060] The sampling point refers to the data obtained by measuring the voltage and current of the doubly-fed wind turbine generator, that is, a set of three-phase power parameters is a sampling point. In this embodiment, the difference between the estimated three-phase current and the actual measured three-phase current is calculated by the mean square error, that is, the difference of the A phase current is: The difference in phase B current is: The difference in phase C current is: The overall difference E can be the average value of the three phases, that is:

[0061]

[0062] The objective function can be understood as the overall performance indicator of the model. After calculating the error predicted by the model, the model is trained based on the error so that the recognition error of the objective function reaches the minimum value. For example, using the error back propagation algorithm, after calculating the error, the gradient descent method is used to update the network weights of the model, and then the recognition error of the updated model is calculated through a new batch of sampling points until the recognition error is less than the preset value, and the training is completed. Specifically, the parameter update process of the model is:

[0063]

[0064] Among them, W ij is the weight connecting the input layer and the hidden layer, i.e., the model parameter, is the updated model parameter, E is the error, and η is the learning rate, which can be set according to actual conditions.

[0065] Get multiple sampling points. In each training, input a batch of sampling points into the model for processing to obtain the output identification parameter estimation value, then calculate the overall error E and the identification error, and use the error back propagation algorithm to iteratively update the model parameters based on the error E. When the identification error F of the updated deep learning model is less than the preset value, the training can be determined to be completed. Or when the preset maximum number of iterations is reached, the training is completed.

[0066] Step 105: Obtain identification parameters of the doubly-fed wind turbine generator through the trained deep learning model.

[0067] The estimated values ​​of the identification parameters output by the deep learning model when the training is completed are determined as the final identification parameters of the doubly-fed wind turbine generator.

[0068] In this embodiment, by converting the three-phase electrical parameters into two-phase electrical parameters, two sets of true values ​​are obtained, and then the two-phase electrical parameters are used to train the deep learning model, and the three-phase electrical parameters are used to verify the model output, without the need for additional variables, which greatly reduces the calculation parameters and can improve the calculation efficiency. In addition, by identifying the identification parameters through deep learning, the accuracy of the identification parameters can be improved.

[0069] In an exemplary embodiment, the electrical parameter estimation value may also include two-phase electrical parameters on the rotor side, such as the α-axis current and the β-axis current on the rotor side. Then, the identification error may also be calculated based on the two-phase electrical parameters on the rotor side and the two-phase electrical parameter estimation value on the rotor side, so as to train the deep learning model based on the identification error.

[0070] Furthermore, this embodiment also provides a device for determining parameters of a doubly-fed wind turbine generator, which can be used to execute the above-mentioned method for determining parameters of a doubly-fed wind turbine generator. Figure 2 As shown, the parameter determination device 200 of the doubly fed wind generator may include: a parameter measurement module 201, used to measure and obtain the three-phase electrical parameters of the doubly fed wind generator, and convert the three-phase electrical parameters into a two-phase coordinate system to obtain the two-phase electrical parameters; a model identification module 202, used to input the two-phase electrical parameters into a deep learning model to obtain the identification parameter estimation values ​​output by the deep learning model; a parameter calculation module 203, used to calculate the electrical parameter estimation values ​​of the doubly fed wind generator when the identification parameter estimation values ​​are taken based on the identification parameter estimation values ​​and the two-phase electrical parameters; a model training module 204, used to train the deep learning model based on the difference between the three-phase electrical parameters and the electrical parameter estimation values ​​to obtain the trained deep learning model; a parameter determination module 205, used to obtain the identification parameters of the doubly fed wind generator through the trained deep learning model.

[0071] In an exemplary embodiment, the two-phase electrical parameters include an α-axis current, a β-axis current, an α-axis voltage, and a β-axis voltage on the stator side of the doubly-fed wind turbine generator.

[0072] In an exemplary embodiment, the model identification module 202 includes a stator parameter identification module, which is used to input the α-axis current, β-axis current, α-axis voltage, and β-axis voltage of the stator side into a deep learning model when the two-phase electrical parameters are the α-axis current, β-axis current, α-axis voltage, and β-axis voltage of the stator side, and obtain the identification parameter estimation values ​​of the stator side output by the deep learning model, wherein the identification parameter estimation values ​​of the stator side include stator winding, stator self-inductance, and mutual inductance.

[0073] In an exemplary embodiment, the parameter calculation module 203 is specifically used to obtain a first dynamic equation between the current, voltage and flux of the doubly fed wind generator in a two-phase coordinate system, solve the first dynamic equation based on the α-axis current, β-axis current, α-axis voltage, β-axis voltage, and stator winding on the stator side to obtain the α-axis flux and β-axis flux; obtain a second dynamic equation between the flux and current of the doubly fed wind generator in a two-phase coordinate system; solve the second dynamic equation based on the α-axis flux and β-axis flux, the stator self-inductance and the mutual inductance to obtain the α-axis current and β-axis current on the rotor side; convert the α-axis current and β-axis current to a three-phase coordinate system to obtain an A-phase current estimate, a B-phase current estimate and a C-phase current estimate.

[0074] In an exemplary embodiment, the three-phase electrical parameters include the three-phase current on the rotor side, and the parameter estimation value includes the three-phase current estimation value on the rotor side. Based on this, the model training module 204 specifically includes an objective function calculation module for obtaining an objective function, solving the objective function through the difference between the three-phase current on the rotor side and the three-phase current estimation value on the rotor side to obtain an identification error; and an iteration module for training the deep learning model based on the identification error. The objective function is:

[0075]

[0076] Where l is the number of sampling points, i rai 、i rbi 、i rci is the three-phase current of the i-th sampling point; i′ rai , i′ rbi , i′ rci is the estimated value of the three-phase current at the i-th sampling point, and F is the identification error.

[0077] In an exemplary embodiment, the parameter determination device 200 of the doubly-fed wind generator further includes two parameter training modules for training the deep learning model based on the difference between the two-phase electrical parameters and the estimated values ​​of the two-phase electrical parameters on the rotor side.

[0078] In an exemplary embodiment, the deep learning model includes an input layer, a hidden layer, and an output layer, wherein the input layer includes a plurality of nodes, and the plurality of nodes correspond to the two-phase electrical parameters one by one. Based on this, the model identification module 202 is specifically used to input the two-phase electrical parameters into the respective corresponding nodes.

[0079] The specific details of each module or unit in the above-mentioned doubly-fed wind generator parameter determination device have been described in detail in the corresponding doubly-fed wind generator parameter determination method, so they will not be repeated here.

[0080] The embodiment of the present application also provides an electronic device, Figure 3 A schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure is shown. Figure 3 The electronic device 600 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0081] like Figure 3 As shown, electronic device 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In RAM 603, various programs and data required for system operation are also stored. CPU 601, ROM 602 and RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to bus 604.

[0082] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0083] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the embodiment of the present application are executed.

[0084] For example, when the computer program is executed by the central processing unit (CPU) 601, it can be executed as follows: measure the three-phase electrical parameters of the doubly fed wind turbine generator, and convert the three-phase electrical parameters into a two-phase coordinate system to obtain the two-phase electrical parameters; input the two-phase electrical parameters into a deep learning model to obtain the identification parameter estimation values ​​output by the deep learning model; calculate the electrical parameter estimation values ​​of the doubly fed wind turbine generator when the identification parameter estimation values ​​are taken based on the identification parameter estimation values ​​and the two-phase electrical parameters; train the deep learning model based on the difference between the three-phase electrical parameters and the electrical parameter estimation values ​​to obtain a trained deep learning model; obtain the identification parameters of the doubly fed wind turbine generator through the trained deep learning model.

[0085] It should be noted that the computer-readable medium shown in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0086] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0087] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, and the units described may also be arranged in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0088] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and the one or more programs include instructions, and when the instructions are executed by the electronic device, the electronic device implements the method described in the above embodiment.

[0089] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0090] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application shall be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for determining parameters of a doubly-fed wind turbine generator, characterized in that: include: Measure and obtain three-phase electrical parameters of the doubly-fed wind turbine generator, and convert the three-phase electrical parameters into a two-phase coordinate system to obtain two-phase electrical parameters; Inputting the two-phase electrical parameters into a deep learning model to obtain estimated values ​​of identification parameters output by the deep learning model; Calculating an estimated electrical parameter value of the doubly-fed wind turbine when the estimated identification parameter value is taken based on the estimated identification parameter value and the two-phase electrical parameters; Training the deep learning model based on the difference between the three-phase electrical parameters and the electrical parameter estimation values ​​to obtain a trained deep learning model; The identification parameters of the doubly-fed wind turbine are obtained through the trained deep learning model.

2. The method for determining parameters of a doubly-fed wind turbine generator according to claim 1, wherein: The two-phase electrical parameters include the α-axis current, β-axis current, α-axis voltage, and β-axis voltage on the stator side of the doubly-fed wind turbine generator.

3. The method for determining parameters of a doubly-fed wind turbine generator according to claim 2, wherein: Inputting the two-phase electrical parameters into a deep learning model to obtain estimated values ​​of identification parameters output by the deep learning model includes: When the two-phase electrical parameters are the α-axis current, β-axis current, α-axis voltage, and β-axis voltage of the stator side, the α-axis current, β-axis current, α-axis voltage, and β-axis voltage of the stator side are input into a deep learning model to obtain the estimated values ​​of the identification parameters of the stator side output by the deep learning model, and the estimated values ​​of the identification parameters of the stator side include stator winding, stator self-inductance, and mutual inductance.

4. The method for determining parameters of a doubly-fed wind turbine generator according to claim 3, wherein: The calculating, based on the identification parameter estimation value and the two-phase electrical parameters, the electrical parameter estimation value of the doubly-fed wind turbine generator when taking the identification parameter estimation value comprises: Obtaining a first dynamic equation between current, voltage, and flux of the doubly-fed wind turbine generator in a two-phase coordinate system, and solving the first dynamic equation based on the α-axis current, β-axis current, α-axis voltage, β-axis voltage, and stator winding on the stator side to obtain α-axis flux and β-axis flux; Obtaining a second dynamic equation between flux and current of the doubly-fed wind turbine in a two-phase coordinate system; Solving the second dynamic equation based on the α-axis magnetic flux and the β-axis magnetic flux, the stator self-inductance, and the mutual inductance to obtain the α-axis current and the β-axis current on the rotor side; The α-axis current and the β-axis current are converted into a three-phase coordinate system to obtain an estimated value of the A-phase current, an estimated value of the B-phase current, and an estimated value of the C-phase current.

5. The method for determining parameters of a doubly-fed wind turbine generator according to claim 1, wherein: The three-phase electrical parameters include three-phase currents on the rotor side, and the parameter estimation values ​​include three-phase current estimation values ​​on the rotor side; The training of the deep learning model based on the difference between the three-phase electrical parameters and the parameter estimation values ​​includes: Obtaining an objective function, and solving the objective function by a difference between the three-phase current on the rotor side and an estimated value of the three-phase current on the rotor side to obtain an identification error; The objective function is: Where l is the number of sampling points, i rai 、i rbi 、i rci is the three-phase current at the i-th sampling point; i′ rai , i′ rbi , i′ rci is the estimated value of the three-phase current at the i-th sampling point, and F is the identification error; The deep learning model is trained based on the recognition error.

6. The method for determining parameters of a doubly-fed wind turbine generator according to claim 1, wherein: The electrical parameter estimation value further includes two-phase electrical parameter estimation values ​​on the rotor side, and the method further includes: The deep learning model is trained based on the difference between the two-phase electrical parameters and the estimated values ​​of the two-phase electrical parameters on the rotor side.

7. The method for determining parameters of a doubly-fed wind turbine generator according to claim 1, wherein: The deep learning model includes an input layer, a hidden layer, and an output layer, wherein the input layer includes a plurality of nodes, and the plurality of nodes correspond one-to-one to the two-phase electrical parameters; Inputting the two-phase electrical parameters into the deep learning model includes: The two-phase electrical parameters are input into their respective corresponding nodes.

8. A parameter determination device for a doubly-fed wind turbine generator, characterized in that: include: A parameter measurement module is used to measure the three-phase electrical parameters of the doubly-fed wind turbine generator and convert the three-phase electrical parameters into a two-phase coordinate system to obtain two-phase electrical parameters; a model identification module, configured to input the two-phase electrical parameters into a deep learning model to obtain estimated values ​​of identification parameters output by the deep learning model; a parameter calculation module, configured to calculate, based on the identification parameter estimation value and the two-phase electrical parameters, an estimated electrical parameter value of the doubly-fed wind turbine when the identification parameter estimation value is taken; a model training module, configured to train the deep learning model based on the difference between the three-phase electrical parameters and the estimated values ​​of the electrical parameters to obtain a trained deep learning model; A parameter determination module is used to obtain the identification parameters of the doubly fed wind turbine through a trained deep learning model.

9. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the parameter determination method for a doubly-fed wind turbine generator according to any one of claims 1 to 7.

10. An electronic device, characterized in that: The electronic device comprises a processor and a memory, wherein one or more computer programs are stored in the memory, and the one or more computer programs include instructions. When the instructions are executed by the electronic device, the electronic device executes the parameter determination method of the doubly fed wind turbine generator according to any one of claims 1 to 7.

Images