Wind turbine yaw control method, device, electronic equipment and storage medium

Abstract

The embodiment of the present invention proposes a yaw control method, device, electronic device and storage medium for a wind turbine generator set, which belongs to the field of control technology. The method includes: discretizing the yaw action of the wind turbine, generating an N-ary tree of yaw actions with respect to multiple step lengths, pruning the branch sequence that meets the sequence invalidity condition in the N-ary tree, and obtaining a pruned N-ary tree, thereby selecting a control action solution matching the control step length from the pruned N-ary tree as a target action solution according to a set control step length, calculating a control sequence corresponding to each target action solution, and selecting an optimal control sequence from multiple control sequences, thereby greatly reducing the searchable solution space of the optimal control sequence, thereby reducing the computational complexity and computing resources of the optimal control sequence acquisition process.

Description

Technical Field

[0001] The present invention relates to the field of control technology, and in particular to a method, device, electronic equipment and storage medium for yaw control of a wind turbine generator set. Background Art

[0002] A wind turbine is an electrical device that converts wind energy into mechanical work, which drives the rotor to rotate and finally outputs alternating current. The yaw system of a wind turbine is a device that makes the wind rotor face the wind direction. It is generally composed of a yaw bearing, a yaw drive device, a yaw brake, a yaw calculator, a cable protection device, and a yaw hydraulic circuit.

[0003] Model Predictive Controller (MPC) is a commonly used controller in the industrial field. It is a control method based on state space and supports constraints on spatial state variables. However, the control theory of this controller is too ideal and requires a lot of calculations and computing resources. Summary of the invention

[0004] In view of this, an object of the present invention is to provide a yaw control method, device, electronic device and storage medium for a wind turbine generator set, which can reduce the calculation amount and computing resources of the current yaw control method, and can adapt to external wind conditions and enhance the environmental adaptability of the yaw system.

[0005] In order to achieve the above objectives, the technical solutions adopted by the embodiments of the present invention are as follows.

[0006] In a first aspect, an embodiment of the present invention provides a yaw control method for a wind turbine generator set, which adopts the following technical solution.

[0007] A yaw control method for a wind turbine generator set, the method comprising:

[0008] Discretize the yaw action of the wind turbine to generate an N-ary tree of yaw actions with multiple steps, wherein the yaw actions include clockwise yaw, counterclockwise yaw and stop yaw;

[0009] Pruning the branch sequence that meets the sequence invalidity condition in the N-ary tree to obtain a pruned N-ary tree, wherein the branch sequence formed from any child node to the root node of the N-ary tree represents a set of control action solutions;

[0010] According to the set control step length, a control action solution matching the control step length is selected from the pruned N-ary tree as a target action solution, wherein the number of yaw actions of the target action solution is consistent with the control step length value;

[0011] Calculate the control sequence corresponding to each target action solution, and select the optimal control sequence from multiple control sequences;

[0012] The wind turbine is yaw controlled according to the optimal control sequence.

[0013] Furthermore, the step of calculating the control sequence corresponding to each target action solution for each target action solution includes:

[0014] Each target action solution is multiplied by the basic yaw velocity to obtain a control sequence corresponding to each target action solution.

[0015] Furthermore, the step of selecting an optimal control sequence from a plurality of control sequences comprises:

[0016] Calculating a theoretical yaw error corresponding to each control sequence according to a preset yaw system state space model and a current actual yaw error of the wind turbine;

[0017] According to the wind conditions in the area where the wind turbine is currently located, combined with each control sequence and the theoretical yaw error corresponding to the control sequence, a cost value of each control sequence is calculated;

[0018] Among all the control sequences, the control sequence with the smallest cost value is taken as the optimal control sequence.

[0019] Furthermore, the step of calculating the cost value of each control sequence according to the wind condition of the area where the wind turbine is currently located, in combination with each control sequence and the theoretical yaw error corresponding to the control sequence, comprises:

[0020] Determining a wind condition stability weight according to the wind condition in the area where the wind turbine is currently located;

[0021] Determining a yaw error weight according to a current actual yaw error of the wind turbine;

[0022] According to the preset yaw mileage weight, the wind stability weight, the yaw error weight and the theoretical yaw error, in combination with the control sequence, a cost value corresponding to each of the control sequences is calculated.

[0023] Furthermore, the step of determining the wind condition stability weight according to the wind condition in the area where the wind turbine is currently located includes:

[0024] The wind turbulence intensity is calculated according to the wind condition in the area where the wind turbine is currently located, and a wind condition stability weight matching the wind turbulence intensity is determined.

[0025] Furthermore, the step of determining the wind condition stability weight according to the wind condition in the area where the wind turbine is currently located includes:

[0026] According to the wind condition in the area where the wind turbine is currently located, the wind direction standard deviation is calculated, and the wind condition stability weight matching the wind direction standard deviation is determined.

[0027] Furthermore, the sequence invalidation condition includes a yaw system constraint rule and a solution invalidation rule.

[0028] In a second aspect, an embodiment of the present invention provides a yaw control device for a wind turbine generator set, which adopts the following technical solution.

[0029] A yaw control device for a wind turbine generator set, comprising a pre-analysis module, a processing module and a control module;

[0030] The pre-solution module is used to discretize the yaw action of the wind turbine, generate an N-ary tree of yaw actions with multiple step lengths, and prune the branch sequence that meets the sequence invalidity condition in the N-ary tree to obtain a pruned N-ary tree, wherein the yaw action includes clockwise yaw, counterclockwise yaw and stop yaw, and the branch sequence formed by any child node to the root node of the N-ary tree represents a set of control action solutions;

[0031] The processing module is used to select a control action solution matching the control step length from the pruned N-ary tree as a target action solution according to the set control step length, calculate a control sequence corresponding to each target action solution, and select an optimal control sequence from a plurality of control sequences, wherein the number of yaw actions of the target action solution is consistent with the control step length value;

[0032] The control module performs yaw control on the wind turbine according to the optimal control sequence.

[0033] In a third aspect, an embodiment of the present invention provides an electronic device, which adopts the following technical solution.

[0034] An electronic device comprises a processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor can execute the machine executable instructions to implement the yaw control method of a wind turbine generator set as described in the first aspect.

[0035] In a fourth aspect, an embodiment of the present invention provides a storage medium, which adopts the following technical solution.

[0036] A storage medium stores a computer program, wherein when the computer program is executed by a processor, the yaw control method of a wind turbine generator set as described in the first aspect is implemented.

[0037] The yaw control method, device, electronic device and storage medium for a wind turbine provided by an embodiment of the present invention, after generating an N-ary tree, prunes the branch sequence that meets the sequence invalidity condition in the N-ary tree, that is, deletes the invalid solution, obtains the control action solution that matches the control step length from the pruned N-ary tree as the target action solution, thereby obtaining the optimal control sequence according to the target action solution, and performs yaw control on the wind turbine according to the optimal control sequence. The use of the N-ary tree can reduce the range of the control sequence solution space, and pruning the branch sequence that meets the sequence invalidity condition can further reduce the searchable solution space of the optimal control sequence, thereby greatly reducing the computational complexity and computing resources of the optimal control sequence acquisition process.

[0038] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 A block diagram of a wind turbine generator set provided by an embodiment of the present invention is shown.

[0041] Figure 2 A schematic flow chart of a yaw control method for a wind turbine generator set provided in an embodiment of the present invention is shown.

[0042] Figure 3 A schematic diagram showing the structure of some nodes of an N-ary tree provided by an embodiment of the present invention is shown.

[0043] Figure 4 A schematic diagram of the structure of some nodes of a pruned N-ary tree provided by an embodiment of the present invention is shown.

[0044] Figure 5 Shows Figure 2 Flow chart of the sub-steps of step S107.

[0045] Figure 6 Shows Figure 5 Schematic diagram of the process of some sub-steps of step S203.

[0046] Figure 7 A block diagram of a yaw control device for a wind turbine generator set provided by an embodiment of the present invention is shown.

[0047] Figure 8A block diagram of an electronic device provided by an embodiment of the present invention is shown.

[0048] Icons: 100- wind turbine; 110- wind turbine; 120- yaw system; 130- sensor collection device; 140- controller; 150- wind turbine yaw control device; 160- pre-decomposition module; 170- processing module; 180- control module; 190- electronic equipment. DETAILED DESCRIPTION

[0049] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0050] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0051] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0052] The traditional wind turbine yaw control system uses judgment trigger control to realize the start-up judgment process of the yaw system. It mainly monitors the wind deviation collected by the control system to trigger the boundary conditions and outputs the yaw command to make the wind turbine correctly face the wind. In addition, researchers in related fields have also proposed a variety of methods for optimizing the control of the yaw system using genetic algorithms, fuzzy theory, deep learning and various advanced algorithms.

[0053] Model Predictive Control (MPC) is a control method based on state space and supports constraints on spatial state variables. The existing control theory of MPC control is too ideal, some control methods lack real-time performance, require a large amount of calculation and computing resources, and are not conducive to the deployment and execution of common wind power control devices represented by PLC.

[0054] In the general MPC control process, the solver required by the general MPC is difficult to implement using PLC control code, and the required cost function form requires special construction, which limits the application of the general MPC in the yaw start-up judgment of wind turbines during the solution process.

[0055] In addition, the current yaw control method makes the environmental adaptability of the yaw system poor. Specifically, it easily causes the yaw system to operate frequently and the wind turbine to be instantly overloaded, ignoring the adverse effects that too many small yaw actions may not be executed and that the wind turbine is prone to failure due to excessive yaw; and, for different wind farms and models, the main problems encountered in the project, such as yaw system failure and yaw gearbox damage, have not been effectively solved.

[0056] Based on the above considerations, an embodiment of the present invention provides a yaw control method for a wind turbine generator set, which can reduce the amount of calculation and computing resources required for the control process, and enhance the environmental adaptability of the yaw system to protect the wind turbine and the yaw system. The following will introduce in detail the yaw control scheme of the wind turbine generator set provided by the embodiment of the present invention.

[0057] The yaw control method of a wind turbine generator set provided by the embodiment of the present invention can be applied to Figure 1 In the environment shown, the wind turbine generator set 100 includes a wind turbine 110, a yaw system 120, a sensor collection device 130 and a controller 140. The controller 140 can communicate with the yaw system 120 and the sensor collection device 130 in a wired or wireless manner. After discretizing the yaw action of the wind turbine 110, the controller 140 generates an N-ary tree including multiple groups of control action solutions, and after pruning the branch sequence that meets the sequence invalidity condition in the N-ary tree, the solution space that needs to be searched for control is greatly reduced. Then, during control, the optimal control sequence can be obtained according to the pruned N-ary tree, and the yaw system 120 can be controlled based on the optimal control sequence.

[0058] The sensing collection device 130 may include a wind speed and direction sensor and a weather station sensor. The weather station sensor may be replaced by any device that can measure the yaw position deviation.

[0059] In one embodiment, Figure 2 As shown, a yaw control method for a wind turbine generator set 100 is provided. This embodiment mainly applies the method to Figure 1 The controller 140 in FIG. 1 is used as an example.

[0060] S101, discretizing the yaw motion of the wind turbine to generate an N-ary tree of yaw motions with multiple step lengths.

[0061] The yaw action includes clockwise yaw, counterclockwise yaw and stop yaw. In essence, the main working state of the yaw system 120 is taken as the yaw action, and is recorded as: clockwise yaw (+1), counterclockwise yaw (-1) and stop yaw (0).

[0062] Discretization means that for each action, the yaw system 120 selects one of the yaw actions.

[0063] For example, refer to Figure 3 If the yaw system 120 has a total of 3 yaw actions (M=1), the depth of the N-ary tree is 3, and each node is one of the yaw actions. At this time, there are a total of 9 possible yaw action orders (the first step is the root node).

[0064] It should be noted that a step size represents a depth of the N-ary tree. For example, if the step size is 10, the depth of the N-ary tree is 10, that is, there are 10 layers of nodes. The N-ary tree is an N-ary tree with a finite step size (i.e., a finite depth). For a finite number of M steps of yaw, each step of the yaw process is connected to the N-ary tree data structure to complete the M-step yaw control N-ary tree data structure. The obtained N-ary tree structure is actually the solution space structure of the model predictive control.

[0065] S103, pruning the branch sequences that meet the sequence invalidity condition in the N-ary tree to obtain a pruned N-ary tree.

[0066] Among them, the branch sequence formed by any child node to the root node of the N-ary tree represents a set of control action solutions.

[0067] Reference Figure 4 , is an N-ary tree with a step size of 3 and after pruning, where [0, +1, 0] is a set of control action solutions.

[0068] S105, according to the set control step length, selecting a control action solution that matches the control step length from the pruned N-ary tree as a target action solution.

[0069] Among them, the number of yaw actions of the target action solution is consistent with the control step value.

[0070] For example, continue to refer to Figure 4, if the control step length is 3, then the control action solution formed by backtracking from each leaf node of the Mth step (Mth layer) of the N-ary tree to its parent node until reaching the root node of the N-ary tree is the target action solution. At this time, the target action solution includes [0, +1, +1], [0, +1, 0], [0, 0, 0], [0, -1, 0] and [0, -1, -1].

[0071] S107, for each target action solution, calculate the control sequence corresponding to each target action solution, and select the optimal control sequence from multiple control sequences.

[0072] S109, performing yaw control on the wind turbine according to the optimal control sequence.

[0073] According to the optimal control sequence, the best yaw start timing (time and duration) can be obtained, and the corresponding control can be executed. That is, the optimal control sequence (the multiple yaw actions that constitute the optimal control sequence have a sequence, and each yaw action has an actual control direction) is output to the yaw system according to the yaw action and the actual control direction, driving the yaw motor to start and run.

[0074] At present, the traditional yaw control method using model predictive control requires a large amount of calculation and computing resources. The yaw control method of the wind turbine 100 provided in the embodiment of the present invention records the yaw process as a yaw action (i.e., discretization), and represents the yaw process by generating an N-ary tree structure with a finite step length, which greatly reduces the solution space range that MPC needs to search, and deletes the branch sequence (control action solution) that meets the sequence invalidity condition in the N-ary tree, further reducing the searchable solution space of the optimal control sequence, thereby reducing the amount of calculation and the computing resources occupied in the actual control process (i.e., obtaining the optimal control sequence based on the pruned N-ary tree, and controlling according to the optimal control sequence).

[0075] It should be noted that, at the initial stage, after performing steps S101 and S103, it is not necessary to perform steps S101 and S103 each time thereafter (ie, performing steps S105, S107 and S109).

[0076] Further, the sequence invalidation condition may include a yaw system constraint rule and a solution invalidation rule.

[0077] Since the yaw system 120 is a low-speed, large inertia system, its motion state cannot be changed quickly, so the constraint rule of the yaw system 120 can be: before running in the opposite direction of any motion direction, it has not passed through the stopped yaw state. For example, after yaw counterclockwise, it must pass through the stopped yaw state before it can yaw clockwise (+1 to 0 to -1); after yaw clockwise, it must pass through the stopped yaw state before it can yaw counterclockwise (-1 to 0 to +1). If these two conditions are not met, it is considered that the yaw constraint rule is met.

[0078] Considering the need to reduce the number of yaws as much as possible and avoid the multi-peak problem of MPC solution, the invalid solution rule can be designed as follows: a single sequence is only allowed to exit the stop yaw state once. A single sequence refers to a control process. When the control step size is 3, the single sequence includes 3 yaw actions, that is, the control action solution includes 3 yaw actions.

[0079] The invalidation rule is a preference based on the yaw state change. Different invalidation rules can be set according to different preferences.

[0080] In other embodiments, the sequence invalidation condition may only include the yaw constraint rule.

[0081] In one implementation, the control sequence of each target motion solution may be calculated in the following manner: each target motion solution is multiplied by a basic yaw velocity to obtain a control sequence corresponding to each target motion solution.

[0082] For example, if the target motion solution is [0, +1, +1], take the base yaw velocity Then the control sequence corresponding to the target action solution is [0, 0.3, 0.3]. At this time, Represents a control sequence.

[0083] In order to enhance the environmental adaptability of the yaw system 120, in one embodiment, referring to Figure 5 , is a flowchart of some sub-steps of step S107, and the optimal control sequence is selected from multiple control sequences through the following steps.

[0084] S201, calculating a theoretical yaw error corresponding to each control sequence according to a preset yaw system state space model and a current actual yaw error of the wind turbine.

[0085] The state space model of the yaw system 120 can be set in various forms, for example, a first-order model, a second-order model and other low-order models. The state space model of the yaw system 120 can be established in a suitable form according to actual needs.

[0086] In one embodiment, the simplest state space model of the yaw system 120 that can be established is:

[0087]

[0088] Among them, θ Posn is the displacement of the nth yaw, θ Posn+1 is the displacement of the nth yaw, θ Errn is the theoretical yaw error after the nth yaw, θ Errn+1is the theoretical yaw error after the n+1th yaw, θ Errm is the actual yaw error of the wind turbine 110 measured by the sensor, and dt is the sampling time.

[0089] Substituting the actual yaw error and the control sequence into the above-mentioned state space model of the yaw system 120, the theoretical yaw error corresponding to each control sequence can be obtained.

[0090] It should be noted that the above-mentioned state-space model of the yaw system 120 is only an example, and the state-space model of the yaw system 120 is not limited.

[0091] S203, calculating a cost value of each control sequence according to the wind condition of the area where the wind turbine is currently located, in combination with each control sequence and a theoretical yaw error corresponding to the control sequence.

[0092] S205: Among all control sequences, the control sequence with the smallest cost value is taken as the optimal control sequence.

[0093] It should be noted that cost refers to the effort required in the control process. The smaller the cost, the better the control.

[0094] Through the above steps S201-S205, by introducing the actual wind condition in the process of calculating the cost value, the change of wind condition can be considered in the yaw control, and the control such as reducing the yaw action when the wind speed and wind direction are unstable can be achieved, so as to enhance the environmental adaptability of the yaw system 120. At the same time, by setting a low-order state space model of the yaw system 120, the amount of calculation can be further reduced.

[0095] Further, for S203, the method for calculating the cost value can be flexibly selected, for example, it can be calculated according to a preset rule. Figure 6 , which is a flowchart of some sub-steps of the above step S203.

[0096] S301, determining a wind condition stability weight according to the wind condition in the area where the wind turbine is currently located.

[0097] Among them, wind conditions can be collected by wind speed and direction sensors.

[0098] In a feasible implementation, the wind condition stability may be measured by using the wind direction standard deviation or wind turbulence, and then the wind condition stability weight may be determined according to the wind condition stability.

[0099] When wind turbulence is used to measure wind stability, the above step S301 is implemented in the following manner: according to the wind conditions in the area where the wind turbine 110 is currently located, the wind turbulence intensity is calculated, and a wind stability weight matching the wind turbulence intensity is determined.

[0100] When the wind direction standard deviation is used to measure the wind condition stability, the above step S301 can be implemented in the following manner: according to the wind condition in the area where the wind turbine 110 is currently located, the wind direction standard deviation is calculated, and the wind condition stability weight matching the wind direction standard deviation is determined.

[0101] It should be noted that wind turbulence and wind direction standard deviation are only examples of wind stability measurement values, not the only limitation, and can be adaptively selected according to actual conditions. For example, the average wind speed and / or average wind direction can be used for measurement.

[0102] S302: Determine a yaw error weight according to the actual current yaw error of the wind turbine.

[0103] The actual yaw error can be obtained by collecting sensors at the weather station.

[0104] S303, calculating a cost value corresponding to each control sequence according to a preset yaw mileage weight, a wind stability weight, a yaw error weight and a theoretical yaw error, in combination with the control sequence.

[0105] The method for calculating the cost value can be flexibly set according to the actual situation and is not specifically limited. In a feasible implementation, the cost value can be calculated by the following cost function.

[0106] The cost function is:

[0107] Among them, ω Pos is the yaw mileage weight, ω Wind is the wind stability weight, ω Err is the yaw error weight, is the yaw range of a single yaw control sequence, θ Errn is the theoretical yaw error.

[0108] In the above cost function, increasing the yaw error weight ω Err This means that the sensitivity of the yaw action at this moment is increased; the yaw mileage weight ω is increased Pos This means that the sensitivity of the yaw action at this moment is reduced; the wind stability weight ω is increased Wind This means that the sensitivity of the yaw action performed at this moment is quickly reduced.

[0109] In the embodiment of the present invention, the yaw error weight ω Err , wind stability weight ω Wind The calculation method of , and the off-course mileage weight ω Pos The value of and sampling time dt are not specifically limited. In actual use, corresponding configurations can be made according to usage requirements.

[0110] In a feasible implementation, the yaw error weight ω can be determined by the following method: Err , wind stability weight ω Wind , yaw mileage weight ω Pos and adopts the value of time dt.

[0111] dt=5s is taken, and 5s is used as the time of a single yaw action, thereby alleviating the short start and stop problem of the yaw system 120 .

[0112] Off-course mileage weight ω Pos =1.0, at this time, considering yaw requires paying the price of response.

[0113] When the actual yaw error measured is taken as the absolute value |θ Errm | is less than the error threshold, then ω Err =0, otherwise ω Err =1. At this time, the influence of the yaw dead zone can be realized and considered. The error threshold can be set according to experience, such as the error threshold can be 8.

[0114] When the wind turbulence intensity is less than the intensity threshold, ω Wind =1, otherwise ω Wind =2. This allows for consideration of the impact of wind condition changes. The intensity threshold can be determined based on a large amount of historical data or experience, such as an intensity threshold of 0.16.

[0115] For example, when the control sequence Theoretical yaw error θ Errn =12deg,|θ Errm | is greater than the error threshold, and the wind turbulence intensity is less than the intensity threshold,

[0116] After the optimal control sequence is calculated through the above steps S201-S205 and steps S301-S303. With respect to S109, the embodiment of the present invention does not impose any specific restrictions on the control method, that is, there may be different control methods. For example, the optimal control sequence may be determined once after each single yaw action time interval, or once after each single sequence time interval. Then, the optimal control sequence obtained by MPC is The steps and actual control direction are output to the yaw system 120 to drive the yaw motor to operate and realize yaw control.

[0117] The single sequence time refers to the time elapsed after all yaw actions of the optimal control sequence are completed.

[0118] It should be understood that steps S105-S109 are actually an MPC control method based on the pruned N-ary tree and considering the stability of wind conditions, and are an optimized MPC control method. In this embodiment, the optimized MPC control can be expressed as: This means that the control sequence with the minimum cost is used as the optimal control sequence for yaw control.

[0119] The above-mentioned wind turbine yaw control method provided by the embodiment of the present invention achieves the following objectives:

[0120] (1) Design and implement a MPC solution approach (S101-S107) specifically for the yaw system, improve the problem of large amount of calculation in the MPC control implementation process, thereby improving practical problems such as the disadvantages of large amount of calculation in the deployment and execution of common controllers 140 represented by PLC, and contribute to the safe loading and operation of commonly used controllers 140.

[0121] (2) By introducing a wind stability weight into the cost function, the yaw system 120 can take changes in wind conditions into account and minimize yaw movements when wind speed and direction are unstable, thereby protecting the wind turbine 110 and the yaw system 120.

[0122] (3) Using the provided yaw control method for the wind turbine generator set 100, the yaw system 120 is subjected to rolling optimization to achieve optimal control.

[0123] It should be emphasized that, without considering the conditions of real-time calculation or when the hardware computing power of the controller 140 is sufficient, other control algorithms such as neural networks can be used to implement any point or any points in the above-mentioned inventive concept.

[0124] Based on the same inventive concept as the above-mentioned wind turbine yaw control method, in one embodiment, Figure 7 As shown, the present invention further provides a yaw control device 150 for a wind turbine generator set, comprising a pre-analysis module 160 , a processing module 170 and a control module 180 .

[0125] The pre-analysis module 160 is used to discretize the yaw motion of the wind turbine 110, generate an N-ary tree of yaw motions with multiple steps, and prune the branch sequences that meet the sequence invalidity condition in the N-ary tree to obtain a pruned N-ary tree.

[0126] Among them, the yaw action includes clockwise yaw, counterclockwise yaw and stop yaw, and the branch sequence formed by any child node to the root node of the N-ary tree represents a set of control action solutions.

[0127] The processing module 170 is used to select a control action solution matching the control step length from the pruned N-ary tree as a target action solution according to the set control step length, calculate a control sequence corresponding to each target action solution, and select an optimal control sequence from multiple control sequences.

[0128] Among them, the number of yaw actions of the target action solution is consistent with the control step value.

[0129] The control module 180 performs yaw control on the wind turbine 110 according to an optimal control sequence.

[0130] In the above-mentioned wind turbine yaw control device 150, the pre-solution module 160 discretizes the yaw action, generates an N-ary tree, and cuts off the branch sequence that meets the sequence invalidity rule in the N-ary tree, thereby reducing the scope of the control sequence solution space and the solution space that needs to be searched for control, thereby reducing the amount of calculation and computing resources in the process of the processing module 170 obtaining the optimal control sequence.

[0131] For the specific definition of the wind turbine yaw control device 150, please refer to the definition of the yaw control method of the wind turbine 100 above, which will not be repeated here. Each module in the above-mentioned wind turbine yaw control device 150 can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the electronic device 190 in the form of hardware, or can be stored in the memory in the electronic device 190 in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0132] In one embodiment, an electronic device 190 is provided. The electronic device 190 may be a terminal, and its internal structure diagram may be as follows: Figure 8 As shown. The electronic device 190 includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the electronic device 190 is used to provide computing and control capabilities. The memory of the electronic device 190 includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the electronic device 190 is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a yaw control method of a wind turbine 100 is implemented. The display screen of the electronic device 190 can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device 190 can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the housing of the electronic device 190, or an external keyboard, touchpad or mouse.

[0133] Those skilled in the art will understand that Figure 8 The structure shown in the figure is merely a block diagram of a partial structure related to the solution of the present invention, and does not constitute a limitation on the electronic device 190 to which the solution of the present invention is applied. The specific electronic device 190 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0134] In one embodiment, the wind turbine yaw control device 150 provided by the present invention can be implemented in the form of a computer program. The computer program can be Figure 8 The electronic device 190 is shown as running. The memory of the electronic device 190 can store various program modules constituting the yaw control device 150 of the wind turbine generator set, for example, Figure 7 The pre-analysis module 160, the processing module 170 and the control module 180 are shown. The computer program composed of various program modules enables the processor to execute the steps of the yaw control method of the wind turbine generator set 100 according to various embodiments of the present invention described in this specification.

[0135] For example, Figure 8 The electronic device 190 shown may be Figure 7 The pre-analysis module 160 in the wind turbine yaw control device 150 shown in the figure performs steps S101 and S103. The electronic device 190 can perform steps S105 and S107 through the processing module 170. The electronic device 190 can perform step S109 through the control module 180.

[0136] In one embodiment, an electronic device 190 is provided, including a memory and a processor, the memory storing machine executable instructions, and the processor implementing the following steps when executing the machine executable instructions: discretizing the yaw action of the wind turbine 110 to generate an N-ary tree of yaw actions with multiple step lengths, the yaw actions including clockwise yaw, counterclockwise yaw and stop yaw; pruning the branch sequence that meets the sequence invalidity condition in the N-ary tree to obtain a pruned N-ary tree, the branch sequence formed by any child node to the root node of the N-ary tree represents a set of control action solutions; according to the set control step length, selecting a control action solution that matches the control step length from the pruned N-ary tree as the target action solution, the number of yaw actions of the target action solution is consistent with the control step length value; for each target action solution, calculating the control sequence corresponding to each target action solution, and selecting the optimal control sequence from multiple control sequences; and performing yaw control on the wind turbine 110 according to the optimal control sequence.

[0137] In one embodiment, the processor further implements the following steps when executing the computer program: calculating the theoretical yaw error corresponding to each control sequence according to the preset state space model of the yaw system 120 and the current actual yaw error of the wind turbine 110; calculating the cost value of each control sequence according to the wind conditions in the current area of ​​the wind turbine 110, in combination with each control sequence and the theoretical yaw error corresponding to the control sequence; and taking the control sequence with the smallest cost value among all the control sequences as the optimal control sequence.

[0138] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: discretizing the yaw action of the wind turbine 110 to generate an N-ary tree of yaw actions with multiple step lengths, wherein the yaw actions include clockwise yaw, counterclockwise yaw and stop yaw; pruning the branch sequence that meets the sequence invalidity condition in the N-ary tree to obtain a pruned N-ary tree, wherein the branch sequence formed from any child node to the root node of the N-ary tree represents a set of control action solutions; according to the set control step length, selecting a control action solution that matches the control step length from the pruned N-ary tree as a target action solution, wherein the number of yaw actions of the target action solution is consistent with the control step length value; for each target action solution, calculating the control sequence corresponding to each target action solution, and selecting the optimal control sequence from multiple control sequences; and performing yaw control on the wind turbine 110 according to the optimal control sequence.

[0139] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the preset state space model of the yaw system 120 and the current actual yaw error of the wind turbine 110, the theoretical yaw error corresponding to each control sequence is calculated; based on the wind conditions in the current area of ​​the wind turbine 110, the cost value of each control sequence is calculated in combination with each control sequence and the theoretical yaw error corresponding to the control sequence; among all the control sequences, the control sequence with the smallest cost value is taken as the optimal control sequence.

[0140] In several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical functions. 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 consecutive boxes 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 and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0141] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0142] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0143] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A yaw control method for a wind turbine generator set, characterized in that: The method comprises: Discretize the yaw action of the wind turbine to generate an N-ary tree of yaw actions with multiple steps, wherein the yaw actions include clockwise yaw, counterclockwise yaw and stop yaw; Pruning a branch sequence that satisfies a sequence invalidity condition in the N-ary tree to obtain a pruned N-ary tree, wherein a branch sequence formed from any child node to a root node of the N-ary tree represents a set of control action solutions, and the sequence invalidity condition includes a yaw system constraint rule and a solution invalidity rule; According to the set control step length, a control action solution matching the control step length is selected from the pruned N-ary tree as a target action solution, wherein the number of yaw actions of the target action solution is consistent with the control step length value; Calculate the control sequence corresponding to each target action solution, and select the optimal control sequence from multiple control sequences; Performing yaw control on the wind turbine according to the optimal control sequence; The step of selecting an optimal control sequence from a plurality of the control sequences comprises: Calculating a theoretical yaw error corresponding to each control sequence according to a preset yaw system state space model and a current actual yaw error of the wind turbine; According to the wind conditions in the area where the wind turbine is currently located, combined with each control sequence and the theoretical yaw error corresponding to the control sequence, a cost value of each control sequence is calculated; Among all the control sequences, the control sequence with the smallest cost value is taken as the optimal control sequence; The step of calculating the cost value of each control sequence according to the wind condition of the area where the wind turbine is currently located, in combination with each control sequence and the theoretical yaw error corresponding to the control sequence, comprises: Determining a wind condition stability weight according to the wind condition in the area where the wind turbine is currently located; Determining a yaw error weight according to a current actual yaw error of the wind turbine; According to the preset yaw mileage weight, the wind condition stability weight, the yaw error weight and the theoretical yaw error, in combination with the control sequence, a cost value corresponding to each of the control sequences is calculated.

2. The yaw control method of a wind turbine generator set according to claim 1, characterized in that: For each of the target action solutions, the step of calculating a control sequence corresponding to each of the target action solutions comprises: Each target action solution is multiplied by the basic yaw velocity to obtain a control sequence corresponding to each target action solution.

3. The yaw control method of a wind turbine generator set according to claim 1, characterized in that: The step of determining a wind condition stability weight according to the wind condition in the area where the wind turbine is currently located comprises: The wind turbulence intensity is calculated according to the wind condition in the area where the wind turbine is currently located, and a wind condition stability weight matching the wind turbulence intensity is determined.

4. The yaw control method of a wind turbine generator set according to claim 1, characterized in that: The step of determining a wind condition stability weight according to the wind condition in the area where the wind turbine is currently located comprises: According to the wind condition in the area where the wind turbine is currently located, the wind direction standard deviation is calculated, and the wind condition stability weight matching the wind direction standard deviation is determined.

5. A yaw control device for a wind turbine generator set, characterized in that: It includes a pre-decomposition module, a processing module and a control module; The pre-solution module is used to discretize the yaw action of the wind turbine, generate an N-ary tree of yaw actions with multiple step lengths, and prune the branch sequence that meets the sequence invalidity condition in the N-ary tree to obtain a pruned N-ary tree, wherein the yaw action includes clockwise yaw, counterclockwise yaw and stop yaw, and the branch sequence formed by any child node to the root node of the N-ary tree represents a set of control action solutions, and the sequence invalidity condition includes yaw system constraint rules and solution invalidity rules; The processing module is used to select a control action solution matching the control step length from the pruned N-ary tree as a target action solution according to the set control step length, calculate a control sequence corresponding to each target action solution, and select an optimal control sequence from a plurality of control sequences, wherein the number of yaw actions of the target action solution is consistent with the control step length value; The control module performs yaw control on the wind turbine according to the optimal control sequence; The processing module is further used for: Calculating a theoretical yaw error corresponding to each control sequence according to a preset yaw system state space model and a current actual yaw error of the wind turbine; According to the wind conditions in the area where the wind turbine is currently located, combined with each control sequence and the theoretical yaw error corresponding to the control sequence, a cost value of each control sequence is calculated; Among all the control sequences, the control sequence with the smallest cost value is taken as the optimal control sequence; The processing module is further used for: Determining a wind condition stability weight according to the wind condition in the area where the wind turbine is currently located; Determining a yaw error weight according to a current actual yaw error of the wind turbine; According to the preset yaw mileage weight, the wind condition stability weight, the yaw error weight and the theoretical yaw error, in combination with the control sequence, a cost value corresponding to each of the control sequences is calculated.

6. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor can execute the machine executable instructions to implement the yaw control method of a wind turbine generator set according to any one of claims 1 to 4.

7. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the yaw control method of a wind turbine generator set according to any one of claims 1 to 4 is implemented.

Images