Wind turbine wind direction prediction, yaw control method, device and wind turbine

Abstract

The present invention provides a method and device for predicting the wind direction and controlling the yaw of a wind turbine, and a wind turbine. The method for predicting the wind direction of the wind turbine includes: obtaining the position data of each wind turbine in the target area, the target wind turbine to be monitored, and the first wind direction data of the target wind turbine; based on the position data of the wind turbines, determining the first wind turbine closest to the target wind turbine, and obtaining the second wind direction data of the first wind turbine; inputting the second wind direction data, the position data of the target wind turbine and the first wind turbine into a wind direction prediction model to perform wind direction prediction, and obtaining the wind direction prediction result of the target wind turbine; based on the relationship between the wind direction prediction result and the first wind direction data, determining the current wind direction of the target wind turbine. By introducing the second wind direction data corresponding to the first wind turbine, even if the wind vane corresponding to the target wind turbine fails under special working conditions, the wind direction data of the target wind turbine can be effectively predicted through the second wind direction data, greatly improving the accuracy of wind direction prediction.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power generation, and particularly relates to a method and device for predicting the wind direction and controlling the yaw of a wind turbine, and a wind turbine. Background Art

[0002] In the prior art, the wind direction is mostly monitored by a wind vane, so as to control the yaw of a wind turbine (i.e., a wind machine) to face the wind. However, due to the uncertainty of the wind direction, there will be a certain lag when the wind turbine yaws to face the wind according to the wind direction data monitored by the wind vane, resulting in uneven force on the wind wheel of the wind turbine and a significant increase in the load of the unit. In special working conditions, such as rain and snow weather, etc., it is also possible that the wind vane fails, resulting in an inability to effectively predict the wind direction, and thus an inability to control the wind turbine to accurately yaw to face the wind. Summary of the Invention

[0003] Therefore, the technical problem to be solved by the present invention is to overcome the defect in the prior art that due to special working conditions, the wind vane fails, resulting in an inability to effectively predict the wind direction, and thus an inability to control the wind turbine to accurately yaw to face the wind, so as to provide a method and device for predicting the wind direction and controlling the yaw of a wind turbine, and a wind turbine.

[0004] According to a first aspect, an embodiment of the present invention provides a method for predicting the wind direction of a wind turbine, the method including:

[0005] Obtaining the position data of each wind turbine in a target area, a target wind turbine to be monitored, and first wind direction data collected by a wind vane corresponding to the target wind turbine, where the target wind turbine is located in the target area;

[0006] Based on the wind turbine position data, determining a first wind turbine closest to the target wind turbine, and obtaining second wind direction data collected by a wind vane corresponding to the first wind turbine;

[0007] Inputting the second wind direction data, the position data of the target wind turbine and the first wind turbine into a wind direction prediction model for wind direction prediction, to obtain a wind direction prediction result of the target wind turbine;

[0008] Based on the relationship between the wind direction prediction result and the first wind direction data, determining the current wind direction of the target wind turbine.

[0009] Optionally, the wind direction prediction model is constructed in the following manner:

[0010] Obtaining the climate data of the target area and the position data of each wind turbine in the target area;

[0011] Based on the climate data and the position data of each wind turbine, performing an analysis and calculation on the influence of the wind direction between wind turbines under different wind directions, to obtain a calculation result of the wind turbine correlation;

[0012] Based on the calculation results of the fan correlation, construct a fan influence topology diagram under different wind directions;

[0013] Based on the fan influence topology diagram under different wind directions and the climate data, construct a wind direction prediction model.

[0014] Optionally, the constructing a wind direction prediction model based on the fan influence topology diagram under different wind directions and the climate data includes:

[0015] Based on the fan influence topology diagram under different wind directions, calculate the wind direction lag time between the current fan and adjacent fans under different wind direction data;

[0016] Based on the wind direction lag time, the fan influence topology diagram under different wind directions and the climate data, construct a wind direction prediction model.

[0017] Optionally, the determining the current wind direction of the target fan based on the relationship between the wind direction prediction result and the first wind direction data includes:

[0018] Calculate the difference between the wind direction prediction result and the first wind direction data;

[0019] Determine whether the difference is greater than a preset threshold;

[0020] When the difference is greater than the preset threshold, correct the wind direction prediction result according to the second wind direction data, and determine the current wind direction of the target fan based on the corrected wind direction prediction result;

[0021] When the difference is not greater than the preset threshold, determine the current wind direction of the target fan based on the wind direction prediction result.

[0022] According to a second aspect, an embodiment of the present invention provides a yaw control method for a wind turbine, and the method includes:

[0023] Adopt the wind direction prediction method for a wind turbine as described in the first aspect, or any optional implementation manner of the first aspect, to determine the current wind direction of a target fan in a target area, where the target area includes multiple fans;

[0024] Based on the current wind direction, control each fan in the target area to perform yaw alignment.

[0025] Optionally, the method further includes:

[0026] Obtain the operating state of the current fan, where the current fan is a fan in the target area;

[0027] When the current wind turbine is in a shutdown state and the difference between the wind direction prediction result and the first wind direction data does not exceed a preset threshold, the current wind turbine is yawed in advance to face the wind by using the wind direction prediction result.

[0028] Optionally, before yawing the current wind turbine in advance to face the wind by using the wind direction prediction result, the method further includes:

[0029] Obtaining the duration of the current wind direction;

[0030] Based on the duration of the current wind direction, determining whether the current wind is a gust;

[0031] When the current wind is a gust, yawing the current wind turbine in advance to face the wind by using the current wind direction.

[0032] According to a third aspect, an embodiment of the present invention provides a wind turbine wind direction prediction device, the device includes:

[0033] An acquisition module, configured to acquire position data of each wind turbine in a target area, a target wind turbine to be monitored, and first wind direction data collected by a wind vane corresponding to the target wind turbine, where the target wind turbine is located in the target area;

[0034] A first processing module, configured to determine a first wind turbine closest to the target wind turbine based on the wind turbine position data, and acquire second wind direction data collected by a wind vane corresponding to the first wind turbine;

[0035] A second processing module, configured to input the second wind direction data, the position data of the target wind turbine and the first wind turbine into a wind direction prediction model for wind direction prediction to obtain a wind direction prediction result of the target wind turbine;

[0036] A third processing module, configured to determine the current wind direction of the target wind turbine based on the relationship between the wind direction prediction result and the first wind direction data.

[0037] According to a fourth aspect, an embodiment of the present invention provides a wind turbine yaw control device, the device includes:

[0038] An acquisition module, configured to use the wind turbine wind direction prediction device as described in the third aspect to determine the current wind direction of a target wind turbine in a target area, where the target area includes multiple wind turbines;

[0039] A fourth processing module, configured to control each wind turbine in the target area to yaw and face the wind based on the current wind direction.

[0040] According to a fifth aspect, an embodiment of the present invention provides a wind turbine, including: a wind turbine and a controller connected to the wind turbine, wherein the controller includes: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the method described in the first aspect, or any optional implementation manner of the first aspect, or execute the method described in the second aspect, or any optional implementation manner of the second aspect.

[0041] The technical solution of the present invention has the following advantages:

[0042] 1. For the wind direction prediction method of the wind turbine provided by the present invention, by obtaining the position data of each wind turbine in the target area, the target wind turbine to be monitored, and the first wind direction data collected by the wind vane corresponding to the target wind turbine; based on the wind turbine position data, determining the first wind turbine closest to the target wind turbine, and obtaining the second wind direction data collected by the wind vane corresponding to the first wind turbine; inputting the second wind direction data, the position data of the target wind turbine and the first wind turbine into a wind direction prediction model for wind direction prediction to obtain a wind direction prediction result of the target wind turbine; based on the relationship between the wind direction prediction result and the first wind direction data, determining the current wind direction of the target wind turbine. By obtaining the first wind direction data of the target wind turbine and the second wind direction data of the first wind turbine closest to the target wind turbine, and inputting the second wind direction data, the target wind turbine and the position data of the first wind turbine into the wind direction prediction model, the wind direction prediction result of the target wind turbine can be obtained. By comparing the relationship between the wind direction prediction result and the first wind direction data, the current wind direction of the target wind turbine is finally determined. By introducing the second wind direction data corresponding to the first wind turbine closest to the target wind turbine, even if the wind vane corresponding to the target wind turbine fails under special working conditions, the wind direction data of the target wind turbine can be effectively predicted by the second wind direction data, greatly improving the accuracy of wind direction prediction, and then using the wind direction prediction result to achieve accurate yaw alignment control of the target wind turbine.

[0043] 2. For the yaw control method of the wind turbine provided by the present invention, by adopting the wind direction prediction method of the wind turbine provided by another embodiment of the present invention, determining the current wind direction of the target wind turbine in the target area, the target area including multiple wind turbines; controlling each wind turbine in the target area to perform yaw alignment based on the current wind direction. By effectively predicting the current wind direction using the wind direction prediction method of the wind turbine, and timely performing yaw control on the wind turbine according to the current wind direction, while ensuring the accuracy of the wind direction data, the efficiency and accuracy of yaw control are further improved.

[0044] 3. The wind turbine provided by the present invention includes a wind turbine and a controller connected to the wind turbine. By the controller, the first wind direction data of the target wind turbine and the second wind direction data of the first wind turbine closest to the target wind turbine are obtained. The second wind direction data, the position data of the target wind turbine, and the position data of the first wind turbine are input into the wind direction prediction model, and then the wind direction prediction result of the target wind turbine can be obtained. By comparing the relationship between the wind direction prediction result and the first wind direction data, the current wind direction of the target wind turbine is finally determined. By introducing the second wind direction data corresponding to the first wind turbine closest to the target wind turbine, even in special working conditions where the wind vane corresponding to the target wind turbine fails, the wind direction data of the target wind turbine can be effectively predicted by the second wind direction data. While significantly improving the accuracy of wind direction prediction, the wind direction prediction result is further used to achieve accurate yaw control for the target wind turbine to face the wind. On this basis, by effectively predicting the current wind direction using the wind turbine wind direction prediction method and timely performing yaw control on the wind turbine according to the current wind direction, while ensuring the accuracy of the wind direction data, the efficiency and accuracy of yaw control are further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0046] Figure 1 It is a flowchart of the wind turbine wind direction prediction method according to an embodiment of the present invention;

[0047] Figure 2 It is a topological diagram of the influence of a wind turbine under different wind directions according to an embodiment of the present invention;

[0048] Figure 3 It is a topological diagram of the influence of a wind turbine under the wind direction condition of 20° to 50°;

[0049] Figure 4 It is a topological diagram of the influence of a wind turbine under the wind direction condition of 300° to 330°;

[0050] Figure 5 It is a schematic structural diagram of the wind turbine wind direction prediction device according to an embodiment of the present invention;

[0051] Figure 6 It is a flowchart of the wind turbine yaw control method according to an embodiment of the present invention;

[0052] Figure 7 It is a schematic structural diagram of the wind turbine yaw control device according to an embodiment of the present invention;

[0053] Figure 8 Structural schematic diagram of a wind turbine according to an embodiment of the present invention;

[0054] Figure 9 Structural schematic diagram of the controller of the wind turbine according to the embodiment of the present invention. Specific embodiments

[0055] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative work shall fall within the protection scope of the present invention.

[0056] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present invention. In addition, the terms "first", "second", "third", "fourth" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0057] In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, the terms "installation", "connection", "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can also be the communication inside two elements. It can be a wireless connection or a wired connection. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0058] In addition, the technical features involved in different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0059] The embodiment of the present invention provides a method for predicting the wind direction of a wind turbine, as Figure 1 shown. The method for predicting the wind direction of the wind turbine specifically includes the following steps:

[0060] Step S101: Obtain the position data of each wind turbine in the target area, the target wind turbine to be monitored, and the first wind direction data collected by the wind vane corresponding to the target wind turbine. The target wind turbine is located in the target area.

[0061] Step S102: Based on the fan position data, determine the first fan closest to the target fan, and obtain the second wind direction data collected by the corresponding wind vane of the first fan.

[0062] Specifically, in practical applications, since the fans in the target area will affect each other, the embodiments of the present invention make full use of this phenomenon of mutual influence among the fans. While obtaining the first wind direction data collected by the wind vane corresponding to the target fan, the second wind direction data collected by the wind vane corresponding to the first fan closest to the target fan is obtained. Thus, when the wind vane corresponding to the target fan fails, the wind direction at the position of the target fan can be determined by the second wind direction data of the first fan. In the embodiments of the present invention, the fan closest to the target fan is used as the first fan and the second wind direction data of the corresponding wind vane of this fan is adopted, but the actual situation is not limited to this. The position and quantity of the first fan can also be changed according to the network diagram of the mutual influence among the fans, so as to ensure the accuracy of the subsequent wind direction prediction result.

[0063] Step S103: Input the second wind direction data, the position data of the target fan and the first fan into the wind direction prediction model for wind direction prediction, and obtain the wind direction prediction result of the target fan.

[0064] Specifically, in practical applications, when the wind vane corresponding to the target fan fails, the embodiments of the present invention can input the second risk data and the position data of the target fan and the first fan into the wind direction prediction model for wind direction prediction to obtain the wind direction prediction result of the target fan. On the premise of ensuring the accuracy of the second wind direction data, by analyzing the positions of the target fan and the first fan, the wind direction prediction result of the target fan can be obtained.

[0065] By this means, the embodiments of the present invention can effectively avoid the situation that the wind vane corresponding to the target fan fails to obtain accurate wind direction data under special working conditions. In practical applications, the first wind direction data can also be compared with the wind direction data collected by the wind vanes corresponding to other fans, so as to check the failed wind vane before wind direction prediction, ensure the accuracy of the collected wind direction data, and thus provide effective data support for ensuring the wind direction prediction result.

[0066] Step S104: Determine the current wind direction of the target fan based on the relationship between the wind direction prediction result and the first wind direction data.

[0067] By performing the above steps, the wind direction prediction method provided by the embodiments of the present invention obtains the first wind direction data of the target wind turbine and the second wind direction data of the first wind turbine closest to the target wind turbine, and inputs the second wind direction data, the position data of the target wind turbine and the first wind turbine into the wind direction prediction model, then the wind direction prediction result of the target wind turbine can be obtained. By comparing the relationship between the wind direction prediction result and the first wind direction data, the current wind direction of the target wind turbine is finally determined. By introducing the second wind direction data corresponding to the first wind turbine closest to the target wind turbine, even under special working conditions when the wind vane corresponding to the target wind turbine fails, the wind direction data of the target wind turbine can be effectively predicted by the second wind direction data, greatly improving the accuracy of wind direction prediction, and then using the wind direction prediction result to achieve accurate yaw control of the target wind turbine for wind alignment.

[0068] Specifically, in one embodiment, the construction of the wind direction prediction model specifically includes the following steps:

[0069] Step S201: Obtain the climate data of the target area and the position data of each wind turbine in the target area.

[0070] Step S202: Based on the climate data and the position data of each wind turbine, perform wind direction influence analysis and calculation between wind turbines under different wind directions to obtain the wind turbine correlation calculation result.

[0071] Step S203: Based on the wind turbine correlation calculation result, construct a wind turbine influence topology diagram under different wind directions.

[0072] Step S204: Based on the wind turbine influence topology diagram under different wind directions and the climate data, construct a wind direction prediction model.

[0073] Specifically, in practical applications, in order to determine the weight relationship of the influence between wind turbines, the embodiments of the present invention calculate the correlation coefficients between every two wind turbines by using the historical climate data, geographical location data and the original wind direction and the wind direction in the previous 30s of the wind turbine historical data in the target area; since the influence weight of the wind turbines under different wind directions will be affected, and in addition, it may also be affected by the wind directions of multiple wind turbines, so it is necessary to establish a wind turbine influence topology diagram under different wind directions as shown in Figure 2 shown.

[0074] Among them, the wind turbine correlation calculation result can be obtained by the correlation coefficient method, and the calculation process refers to the correlation calculation process in the prior art, which will not be elaborated here.

[0075]

[0076] Wherein, r(X, Y) is the calculation result of the correlation between Fan X and Fan Y; Cov(X, Y) is the covariance between Fan X and Fan Y; Var[X] is the variance of Fan X; and Var[Y] is the variance of Fan Y.

[0077] In the embodiment of the present invention, by performing the analysis and calculation of the wind direction influence between fans under different wind directions, the strength relationship of the wind direction influence between fans can be measured. When the calculation result of the fan correlation is 1, it indicates that Fan X and Fan Y are positively correlated, that is, under the current wind direction, Fan X will enhance the wind direction and wind force at the location of Fan Y; when the calculation result of the fan correlation is, it indicates that Fan X and Fan Y are negatively correlated, that is, under the current wind direction, Fan X will weaken the wind direction and wind force at the location of Fan Y; when the calculation result of the fan correlation is closer to 0, it indicates that the correlation between Fan X and Fan Y is weaker.

[0078] Such as Figure 3 As shown, from the fan influence topology diagram under the wind direction condition of 20° to 50°, it can be seen that Fan 4 is most affected by Fan 2, and will affect the respective wind directions of Fan 5 and Fan 6, and then these two fans together affect the wind direction of Fan 8. And in Figure 4 In the fan influence topology diagram under the wind direction condition of 300° to 330° shown, Fan 4 is most affected by Fan 3.

[0079] In the embodiment of the present invention, by constructing the fan influence topology diagram under different wind directions, the wind direction influence relationship between each fan is visually reflected, while greatly reducing the data processing difficulty of the fan prediction model and further improving the accuracy of the prediction result.

[0080] Specifically, in practical applications, the embodiment of the present invention will also calculate the maximum likelihood estimator between fans according to the constructed fan influence topology diagram under different wind directions, and effectively analyze the wind direction influence result between fans, so as to further ensure the accuracy of the prediction result. The calculation process and necessary formulas for calculating the maximum likelihood estimator between fans can refer to the relevant descriptions in the prior art and will not be elaborated here.

[0081] Specifically, in one embodiment, the above step S204 constructs a wind direction prediction model based on the fan influence topology diagram and climate data under different wind directions, which specifically includes the following steps:

[0082] Step S301: Based on the fan influence topology diagram under different wind directions, calculate the wind direction lag time between the current fan and the adjacent fan under different wind direction data.

[0083] Step S302: Based on the wind direction lag time, the fan influence topology diagram under different wind directions and climate data, construct a wind direction prediction model.

[0084] Specifically, in practical applications, after constructing the topological diagram of the influence of the wind turbine under different wind directions, the embodiments of the present invention will obtain parameters such as the wind farm terrain α (high slopes, canyons, plains, etc.), season β, the distance d between wind turbines, wind speed signal v, wind direction signal γ, and the number n of associated units, and construct a wind direction prediction model based on the above parameters. In addition, considering that the interval distances between wind turbines are relatively far, for the same gust of wind, the arrival times at different wind turbines may be different. Therefore, the embodiments of the present invention also take the wind direction lag time t as an influencing factor and construct the wind direction prediction model together with the above parameters of the wind farm terrain α (high slopes, canyons, plains, etc.), season β, the distance d between wind turbines, wind speed signal v, wind direction signal γ, and the number n of associated units.

[0085] Specifically, in practical applications, in order to quickly and accurately determine the wind direction data, the embodiments of the present invention construct a wind direction prediction model based on the BP neural network model and optimize it using the grey wolf optimization algorithm. It is also possible to use optimization algorithms such as particle swarm optimization and relevant classification models of support vector machines to construct the wind direction prediction model, but the actual situation is not limited to this. Changes in the type or quantity of the wind direction prediction model to ensure the accuracy of the wind direction prediction result are also within the protection scope of the wind turbine wind direction prediction method provided by the embodiments of the present invention.

[0086] Specifically, the embodiments of the present invention need to determine the nodes of the input layer, hidden layer, and output layer of the wind direction prediction model. After determining the number of nodes corresponding to each layer, the collected input set information is used as the input of the classification model, and the wind direction information of the wind turbine is used as the output result to train and predict the model. After training the wind direction prediction model, historical wind direction data is used to verify its accuracy, and finally, a wind direction prediction model that can be used for wind direction prediction is obtained.

[0087] Specifically, the wind direction information of the wind turbine includes the position information of the wind turbine and the real-time wind direction of the wind turbine, etc., which are wind turbine and wind direction data.

[0088] The specific training and verification process of the wind direction prediction model can refer to the relevant descriptions in the prior art and will not be elaborated here.

[0089] Specifically, in one embodiment, the above step S104 determines the current wind direction of the target wind turbine based on the relationship between the wind direction prediction result and the first wind direction data, and specifically includes the following steps:

[0090] Step S401: Calculate the difference between the wind direction prediction result and the first wind direction data.

[0091] Step S402: Determine whether the difference is greater than a preset threshold.

[0092] Step S403: When the difference is greater than a preset threshold, correct the wind direction prediction result according to the second wind direction data, and determine the current wind direction of the target wind turbine based on the corrected wind direction prediction result.

[0093] Step S404: When the difference is not greater than the preset threshold, determine the current wind direction of the target wind turbine based on the wind direction prediction result.

[0094] Specifically, in practical applications, when the difference between the wind direction prediction result and the first wind direction data is greater than the preset threshold, it indicates that the wind vane corresponding to the target wind turbine may be faulty. At this time, the wind direction at the position of the target wind turbine will be determined according to the second wind direction data and the influence topology map of the wind turbine under different wind directions in the wind direction prediction model, and the wind direction prediction result will be corrected according to this wind direction, and the current wind direction of the target wind turbine will be determined based on the corrected wind direction prediction result. Exemplarily, the preset threshold can be 10°.

[0095] Specifically, when the difference is greater than the preset threshold, the embodiment of the present invention will obtain the position information of the target wind turbine and give an early warning prompt and feedback it to the maintenance department, so that technicians can master the fault situation of the target wind turbine in the first time, greatly improving the efficiency of fault troubleshooting and ensuring the stable operation of the wind turbine.

[0096] The embodiment of the present invention ensures that even if the wind vane corresponding to the target wind turbine fails, the current wind direction of the accurate target wind turbine can be obtained through the wind direction prediction model by setting a preset threshold and correcting the predicted value according to the second wind direction result when the difference exceeds the preset threshold. While avoiding the situation that the wind vane fails due to special working conditions and the wind direction data cannot be accurately obtained, the current wind direction of the target wind turbine is cleverly obtained by using the influence topology map of the wind turbine under different wind directions and the wind direction data collected by the wind vanes corresponding to other wind turbines, which not only ensures the normal operation of the wind turbine, but also further improves the accuracy of wind direction prediction.

[0097] The embodiment of the present invention provides a wind direction prediction device for a wind turbine generator set, as Figure 5 shown. The wind direction prediction device for the wind turbine generator set includes:

[0098] An acquisition module 101, configured to acquire the position data of each wind turbine in the target area, the target wind turbine to be monitored, and the first wind direction data collected by the wind vane corresponding to the target wind turbine, and the target wind turbine is located in the target area. For detailed content, refer to the relevant description of step S101 in the above method embodiment, and details will not be described here again.

[0099] A first processing module 102, configured to determine the first wind turbine closest to the target wind turbine based on the wind turbine position data, and acquire the second wind direction data collected by the wind vane corresponding to the first wind turbine. For detailed content, refer to the relevant description of step S102 in the above method embodiment, and details will not be described here again.

[0100] The second processing module 103 is configured to input the second wind direction data, the position data of the target wind turbine and the first wind turbine into a wind direction prediction model for wind direction prediction, so as to obtain the wind direction prediction result of the target wind turbine. For the detailed content, please refer to the relevant description of step S103 in the above method embodiment, and details will not be repeated here.

[0101] The third processing module 104 is configured to determine the current wind direction of the target wind turbine based on the relationship between the wind direction prediction result and the first wind direction data. For the detailed content, please refer to the relevant description of step S104 in the above method embodiment, and details will not be repeated here.

[0102] For a further description of the above wind turbine wind direction prediction device, please refer to the relevant description of the above wind turbine wind direction prediction method embodiment, and details will not be repeated here.

[0103] Through the collaborative cooperation of the above-mentioned various components, the wind turbine wind direction prediction device provided by the embodiment of the present invention obtains the first wind direction data of the target wind turbine and the second wind direction data of the first wind turbine closest to the target wind turbine, and inputs the second wind direction data, the target wind turbine and the position data of the first wind turbine into the wind direction prediction model, so as to obtain the wind direction prediction result of the target wind turbine. By comparing the relationship between the wind direction prediction result and the first wind direction data, the current wind direction of the target wind turbine is finally determined. By introducing the second wind direction data corresponding to the first wind turbine closest to the target wind turbine, even if the wind vane corresponding to the target wind turbine fails under special working conditions, the wind direction data of the target wind turbine can be effectively predicted by the second wind direction data, greatly improving the accuracy of wind direction prediction, and then using the wind direction prediction result to realize accurate yaw wind alignment control of the target wind turbine.

[0104] The embodiment of the present invention provides a wind turbine yaw control method, as Figure 6 shown, the wind turbine yaw control method specifically includes the following steps:

[0105] Step S501: Use the wind turbine wind direction prediction method provided by another embodiment of the present invention to determine the current wind direction of the target wind turbine in the target area, where the target area includes multiple wind turbines.

[0106] Step S502: Control each wind turbine in the target area to perform yaw wind alignment based on the current wind direction.

[0107] Specifically, in practical applications, when the prediction result of the target wind turbine is obtained, the embodiment of the present invention can obtain the current wind direction corresponding to each wind turbine based on the wind turbine influence topology diagram under different wind directions, and control each wind turbine to perform yaw wind alignment according to the current wind direction corresponding to each wind turbine.

[0108] By performing the above steps, the yaw control method for a wind turbine provided by the embodiment of the present invention effectively predicts the current wind direction by using the wind direction prediction method for the wind turbine, and timely performs yaw control on the wind turbine according to the current wind direction, further improving the efficiency and accuracy of yaw control while ensuring the accuracy of wind direction data.

[0109] Specifically, in one embodiment, the following steps are further included:

[0110] Step S601: Obtain the operating state of the current wind turbine, where the current wind turbine is a wind turbine in the target area.

[0111] Step S602: When the current wind turbine is in a shutdown state and the difference between the wind direction prediction result and the first wind direction data does not exceed a preset threshold, use the wind direction prediction result to perform early yaw alignment on the current wind turbine.

[0112] Specifically, in practical applications, considering that the wind turbine may suddenly shut down, the embodiment of the present invention will obtain the operating state of the current wind turbine. If the current wind turbine is in a shutdown state, the current wind direction of the current wind turbine can be determined according to the wind turbine prediction result, so as to perform early yaw alignment on the current wind turbine, greatly shortening the yaw alignment time and improving the power generation efficiency of the wind turbine.

[0113] Specifically, in one embodiment, before performing the above step S602 to perform early yaw alignment on the current wind turbine by using the wind direction prediction result, the following steps are further included:

[0114] Step S701: Obtain the duration of the current wind direction.

[0115] Step S702: Based on the duration of the current wind direction, determine whether the current wind is a gust.

[0116] Step S703: When the current wind is a gust, use the current wind direction to perform early yaw alignment on the current wind turbine.

[0117] Specifically, in practical applications, the embodiment of the present invention can also judge whether the current wind is a gust according to the duration of the current wind direction, and thus perform early yaw alignment on the current wind turbine according to the judgment result, greatly improving the prediction efficiency and yaw control efficiency.

[0118] By establishing a fan influence topology map of the maximum correlation unit under different wind directions and terrains, the accuracy of wind direction prediction is improved. The predicted wind direction value is used to achieve yaw control of the fan in the case of wind vane failure, and the fan is pre-controlled to face the wind in case of sudden gusts, improving power generation efficiency. While enabling yaw control of each fan under severe weather conditions, the advantages of the wind direction prediction model are maximally exerted, the operation of the wind vane is synchronously monitored, and the data of the faulty wind vane is promptly given a warning prompt to assist the maintenance department in troubleshooting, greatly improving the power generation efficiency of the fan.

[0119] An embodiment of the present invention provides a yaw control device for a wind turbine, as Figure 7 shown. The yaw control device for the wind turbine includes:

[0120] An acquisition module 501, configured to use the above-mentioned wind direction prediction device for a wind turbine to determine the current wind direction of a target fan in a target area, where the target area includes multiple fans. For detailed content, refer to the relevant description of step S501 in the above method embodiment, and details will not be elaborated here.

[0121] A fourth processing module 502, configured to control each fan in the target area to perform yaw alignment based on the current wind direction. For detailed content, refer to the relevant description of step S502 in the above method embodiment, and details will not be elaborated here.

[0122] For a further description of the above-mentioned yaw control device for a wind turbine, refer to the relevant description of the yaw control method embodiment for a wind turbine above, and details will not be elaborated here.

[0123] Through the collaborative cooperation of the above-mentioned various components, the yaw control device for a wind turbine provided by the embodiment of the present invention effectively predicts the current wind direction by using the wind direction prediction method for a wind turbine, and timely performs yaw control on the wind turbine according to the current wind direction, further improving the efficiency and accuracy of yaw control while ensuring the accuracy of wind direction data.

[0124] An embodiment of the present invention provides a wind turbine, as Figure 8 shown. The wind turbine includes a fan 100 and a controller 900 connected to the fan, as Figure 9 shown. The controller 900 includes a processor 901 and a memory 902, and the memory 902 and the processor 901 are communicatively connected to each other, where the processor 901 and the memory 902 can be connected through a bus or other means, Figure 9 and taking the connection through a bus as an example.

[0125] The processor 901 may be a Central Processing Unit (CPU). The processor 901 may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., chips, or combinations of the above types of chips.

[0126] As a non-transitory computer-readable storage medium, the memory 902 can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the methods in the embodiments of the present invention. The processor 901 executes various functional applications and data processing of the processor 901 by running the non-transitory software programs, instructions, and modules stored in the memory 902, that is, implements the methods in the above method embodiments.

[0127] The memory 902 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created by the processor 901, etc. In addition, the memory 902 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory 902 may optionally include a memory remotely provided relative to the processor 901, and these remote memories can be connected to the processor 901 through a network. Examples of the above networks include, but are not limited to, the Internet, enterprise intranets, local area networks, mobile communication networks, and combinations thereof.

[0128] One or more modules are stored in the memory 902 and, when executed by the processor 901, implement the methods in the above method embodiments.

[0129] The specific details of the above wind turbine can be understood by referring to the corresponding relevant descriptions and effects in the above method embodiments, and will not be elaborated here.

[0130] Those skilled in the art can understand that to implement all or part of the processes in the above method embodiments, it can be completed by instructing relevant hardware through a computer program. The implemented program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memories.

[0131] Obviously, the above embodiments are only examples for clear illustration and not limitations on the implementation manners. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to enumerate all the implementation manners here. And the obvious changes or modifications derived therefrom are still within the protection scope of the present invention.

Claims

1. A wind turbine wind direction prediction method, characterized in that, Including: Obtain the position data of each wind turbine in the target area, the target wind turbine to be monitored, and the first wind direction data collected by the wind vane corresponding to the target wind turbine, where the target wind turbine is located in the target area; Based on the wind turbine position data, determine the first wind turbine closest to the target wind turbine, and obtain the second wind direction data collected by the wind vane corresponding to the first wind turbine; Input the second wind direction data, the position data of the target wind turbine and the first wind turbine into a wind direction prediction model for wind direction prediction to obtain the wind direction prediction result of the target wind turbine; The wind direction prediction model is constructed in the following manner: Obtain the climate data of the target area and the position data of each wind turbine in the target area; Based on the climate data and the position data of each wind turbine, perform wind direction influence analysis and calculation among wind turbines under different wind directions to obtain the wind turbine correlation calculation result; Based on the wind turbine correlation calculation result, construct a wind turbine influence topology diagram under different wind directions; Based on the wind turbine influence topology diagram under different wind directions and the climate data, construct a wind direction prediction model; The constructing a wind direction prediction model based on the wind turbine influence topology diagram under different wind directions and the climate data includes: based on the wind turbine influence topology diagram under different wind directions, calculate the wind direction lag time between the current wind turbine and adjacent wind turbines under different wind direction data; Based on the wind direction lag time, the wind turbine influence topology diagram under different wind directions and the climate data, construct a wind direction prediction model; Based on the relationship between the wind direction prediction result and the first wind direction data, determine the current wind direction of the target wind turbine.

2. The method according to claim 1, wherein The determining the current wind direction of the target wind turbine based on the relationship between the wind direction prediction result and the first wind direction data includes: Calculate the difference between the wind direction prediction result and the first wind direction data; Judge whether the difference is greater than a preset threshold; When the difference is greater than the preset threshold, correct the wind direction prediction result according to the second wind direction data, and determine the current wind direction of the target wind turbine based on the corrected wind direction prediction result; When the difference is not greater than the preset threshold, determine the current wind direction of the target wind turbine based on the wind direction prediction result.

3. A yaw control method for a wind turbine, characterized in that, Including: Adopt the wind turbine wind direction prediction method described in any one of claims 1-2 to determine the current wind direction of the target wind turbine in the target area, where the target area includes multiple wind turbines; Based on the current wind direction, control each wind turbine in the target area to perform yaw alignment.

4. The method according to claim 3, wherein The method further includes: Obtain the operating state of the current wind turbine, where the current wind turbine is a wind turbine in the target area; When the current wind turbine is in a shutdown state and the difference between the wind direction prediction result and the first wind direction data does not exceed the preset threshold, use the wind direction prediction result to perform early yaw alignment on the current wind turbine.

5. The method according to claim 4, wherein Before using the wind direction prediction result to perform early yaw alignment on the current wind turbine, the method further includes: Obtain the duration of the current wind direction; Based on the duration of the current wind direction, judge whether the current wind is a gust; When the current wind is a gust, use the current wind direction to perform early yaw alignment on the current wind turbine.

6. A wind turbine wind direction prediction device, characterized in that, Including: An acquisition module, configured to acquire the position data of each wind turbine in a target area, a target wind turbine to be monitored, and first wind direction data collected by a wind vane corresponding to the target wind turbine, where the target wind turbine is located in the target area; A first processing module, configured to determine a first wind turbine closest to the target wind turbine based on the wind turbine position data, and acquire second wind direction data collected by a wind vane corresponding to the first wind turbine; A second processing module, configured to input the second wind direction data, the position data of the target wind turbine and the first wind turbine into a wind direction prediction model for wind direction prediction to obtain a wind direction prediction result of the target wind turbine; The wind direction prediction model is constructed in the following manner: Acquire the climate data of the target area and the position data of each wind turbine in the target area; Based on the climate data and the position data of each wind turbine, perform an analysis and calculation of the wind direction influence between wind turbines under different wind directions to obtain a wind turbine correlation calculation result; Based on the wind turbine correlation calculation result, construct a wind turbine influence topology diagram under different wind directions; Based on the wind turbine influence topology diagram under different wind directions and the climate data, construct a wind direction prediction model; The constructing a wind direction prediction model based on the wind turbine influence topology diagram under different wind directions and the climate data includes: calculating the wind direction lag time between the current wind turbine and adjacent wind turbines under different wind direction data based on the wind turbine influence topology diagram under different wind directions; constructing a wind direction prediction model based on the wind direction lag time, the wind turbine influence topology diagram under different wind directions and the climate data; A third processing module, configured to determine the current wind direction of the target wind turbine based on the relationship between the wind direction prediction result and the first wind direction data.

7. A yaw control device for a wind turbine, characterized in that Comprising: A collection module, configured to use the wind turbine wind direction prediction device as described in claim 6 to determine the current wind direction of a target wind turbine in a target area, where the target area includes multiple wind turbines; A fourth processing module, configured to control each wind turbine in the target area to perform yaw alignment based on the current wind direction.

8. A wind turbine, characterized in that, Comprising: A wind turbine and a controller connected to the wind turbine, where the controller includes: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the method as described in any one of claims 1-2, or execute the method as described in any one of claims 3-5.

Images