Wind turbine management method and device
Dynamically adjusting the control strategy of the wind turbine through wind speed and direction prediction, the frequent changes in the control strategy caused by static sector management are solved, and the safety and power generation capacity of the wind turbine are improved.
Patent Information
- Application Number
- CN202011060058.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-09-30
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2040-09-30
AI Technical Summary
The existing wind turbine sector management technology is a static technology and cannot be dynamically adjusted and optimized in actual operation, resulting in too frequent changes in control strategies, affecting power generation capacity and safety.
By predicting the wind speed and wind direction of the wind turbine, the control strategy for the next time period is determined, the control strategy level of the wind speed working range and the wind direction sector is dynamically divided, and the control strategy is adjusted according to the state transition probability.
Reduces the switching frequency of control strategies, reduces the workload of yaw and pitch mechanisms, and improves the safety and power generation capacity of wind turbines.
Smart Images

Figure CN114320768B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of wind power, and more specifically, to a method and device for managing a wind turbine generator set. Background Art
[0002] In the wind power industry, wind turbine sector management or wind turbine sector control technology is usually used in projects with complex terrain or densely arranged wind turbines in wind farms. The wind resources of each sector of the wind turbines in such projects vary greatly. By applying different control strategies to different wind turbine sectors, the power generation capacity of the wind turbine can be effectively improved and / or the safety of the wind turbine can be enhanced.
[0003] The main method of existing sector-based control technology is to divide the wind resource parameters and terrain parameters measured and calculated in the early stage of the project into several sectors, and configure different control strategy parameters in each sector.
[0004] However, the existing sector management or sector control technology belongs to "static" sector technology, that is, the sector division and the control technology of each sector are determined during project development or wind turbine design. Once confirmed, the wind turbine sector control strategy will not be dynamically adjusted and optimized during actual operation. However, in the actual operation of wind turbines, due to the uncertainty of the wind turbine operating state and external environment, the "static" sector control determined in this way often leads to too frequent changes in control strategy, which makes the power generation capacity or safety not optimal. Summary of the invention
[0005] According to an exemplary embodiment of the present invention, a wind turbine management method is provided, comprising: predicting wind speed and wind direction for the wind turbine; and determining a control strategy for the wind turbine to be executed in a next time period based on the wind speed and wind direction prediction results.
[0006] The step of predicting wind speed and wind direction for a wind turbine generator set may include: obtaining a wind speed working range transfer probability and a wind direction sector transfer probability; and obtaining a state transfer probability based on the wind speed working range transfer probability and the wind direction sector transfer probability.
[0007] The steps of obtaining the wind speed working interval transfer probability and the wind direction sector transfer probability may include: obtaining a first number of wind speed working intervals of the wind turbine group based on the wind speed; obtaining the wind speed working interval transfer probability between the first number of wind speed working intervals; obtaining a second number of wind direction sectors of the wind turbine group based on the wind direction; and obtaining the wind direction sector transfer probability between the second number of wind direction sectors.
[0008] The step of obtaining wind speed working interval transition probabilities between the first number of wind speed working intervals may include obtaining wind speed working interval transition probabilities between the first number of wind speed working intervals based on the probability density of the wind speed.
[0009] The step of obtaining wind direction sector transfer probabilities between the second number of wind direction sectors may include obtaining wind direction sector transfer probabilities between the second number of wind direction sectors based on a time series obtained by transposing wind speed measurements.
[0010] The actual wind speed can be inferred from the current operating status of the wind turbine to obtain the corresponding wind speed operating range.
[0011] The current operating state of the wind turbine generator set may include at least one of the rotation speed, torque, pitch angle and power of the wind turbine generator set.
[0012] The step of determining the control strategy of the wind turbine to be executed in the next time period may include: dividing the control strategy of the wind speed working range and wind direction sector of the wind turbine into multiple levels based on the operating constraint parameters of the wind turbine; if the maximum probability among the state transition probabilities of the next time period is greater than a predetermined threshold, and the level of the control strategy of the current time period is not between the level of the control strategy of the previous time period and the level of the control strategy corresponding to the maximum probability, then executing the control strategy of the previous time period in the next time period.
[0013] The operation constraint parameter of the wind turbine generator set may include at least one of the power and the critical load of the wind turbine generator set.
[0014] If the maximum probability among the state transition probabilities of the next time period is not greater than the predetermined threshold, or the level of the control strategy of the current time period is between the level of the control strategy of the previous time period and the level of the control strategy corresponding to the maximum probability, the control strategy of the current time period can be executed in the next time period.
[0015] According to an exemplary embodiment of the present invention, a wind turbine management device is provided, comprising: a prediction unit for predicting wind speed and wind direction for the wind turbine; and a control unit for determining a control strategy for the wind turbine to be executed in the next time period based on the wind speed and wind direction prediction results.
[0016] According to an exemplary embodiment of the present invention, a computing device is provided, characterized in that it comprises: a processor; and a memory storing program instructions that, when executed by the processor, enable the processor to execute the above-mentioned wind turbine management method.
[0017] According to an exemplary embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores program instructions that, when executed by a processor, enable the processor to execute the above-mentioned wind turbine management method.
[0018] Additional aspects and / or advantages of the present general inventive concept will be set forth in part in the following description and in part will be obvious from the description, or may be learned through practice of the present general inventive concept. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The above and other objects and features of the present invention will become more apparent from the following detailed description in conjunction with the accompanying drawings, in which:
[0020] Figure 1 is a flow chart showing a wind turbine management method according to an exemplary embodiment of the present invention;
[0021] Figure 2 is a flow chart showing a control strategy for determining a wind turbine generator system to be executed in a next time period according to an exemplary embodiment of the present invention;
[0022] Figure 3 is a block diagram showing a wind turbine management device according to an exemplary embodiment of the present invention;
[0023] Figure 4 is a block diagram illustrating a computing device according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION
[0024] Reference will now be made in detail to embodiments of the present invention, examples of which are shown in the accompanying drawings, wherein like reference numerals refer to like parts throughout. The embodiments will be described below with reference to the drawings in order to explain the present invention.
[0025] Figure 1 is a flow chart showing a wind turbine sector management method according to an exemplary embodiment of the present invention.
[0026] Reference Figure 1 In step S110, the wind speed and wind direction sector prediction can be performed for the wind turbine. Here, before this step, the wind turbine can be divided into several sectors based on wind resource data and terrain data in accordance with the prior art in the field, combined with the characteristics of the wind turbine, and each sector is configured with a corresponding control strategy, which will not be described in detail here.
[0027] In step S120, the control strategy of the wind turbine to be executed in the next time period may be determined based on the wind speed and wind direction prediction results. Here, in the case where the state transition probability is obtained as the wind speed and wind direction prediction results as described in the above step S110, the control strategy of the wind turbine to be executed in the next time period may be determined based on the state transition probability.
[0028] Step S110 and step S120 will be described in more detail below.
[0029] As an example only and not a limitation, in step S110, the step of predicting wind speed and wind direction for the wind turbine may include: obtaining a wind speed working range transition probability and a wind direction sector transition probability, and obtaining a state transition probability based on the wind speed working range transition probability and the wind direction sector transition probability.
[0030] Here, for example only and not limitation, the wind speed working interval transfer probability may be in matrix form, that is, the wind speed working interval transfer probability matrix M. More specifically, the step of predicting the wind speed working interval of the wind turbine may include obtaining a first number of wind speed working intervals of the wind turbine based on the wind speed, and obtaining a wind speed working interval transfer probability matrix between a first number (wherein the first number is a positive integer) of wind speed working intervals. Here, the wind speed working interval may be divided based on the wind speed in the parameter design stage and the wind speed working interval transfer probability matrix may be obtained, and during the actual operation of the wind turbine, the actual wind speed may be reversed based on the current operating state of the wind turbine to obtain the corresponding wind speed working interval, and then the wind speed working interval transfer probability of the actual wind speed may be obtained. Here, for example only and not limitation, the current operating state of the wind turbine may include at least one of the speed, torque, pitch angle and power of the wind turbine. More specifically, assuming that it is divided into n wind speed working intervals, m ij represents the probability of transferring from wind speed working interval i to wind speed working interval j. In the parameter design stage, the wind speed working interval transfer probability matrix M between n wind speed working intervals can be obtained based on the probability density of wind speed, as shown in the following equation 1.
[0031] [Equation 1]
[0032]
[0033] Subsequently, during the actual operation of the wind turbine, the probability that the sliding mean wind speed or the actual wind speed inferred from the actual wind speed at time t+1 is in the wind speed working interval i is (where t represents any time, M t+1 represents the wind speed working range transfer probability matrix at time t+1), the transfer probability m of the wind turbine group from wind speed working range j to wind speed working range i ji This is shown in Equation 2 below.
[0034] [Equation 2]
[0035] m ji =P(M t+1 =i|M t =j)
[0036] Since actual data is used to infer the actual wind speed during the actual operation of the wind turbine and then predict the wind speed working range, dynamic optimization of sector management can be achieved.
[0037] In addition, as an example only and not a limitation, the wind direction sector transfer probability may be in a matrix form, that is, a wind direction sector transfer probability matrix S. More specifically, the step of performing wind direction sector prediction on a wind turbine may include obtaining a second number (wherein the second number is a positive integer) of wind direction sectors of the wind turbine based on the wind direction, and obtaining a wind direction sector transfer probability matrix between the second number of wind direction sectors. As an example only and not a limitation, the wind direction sectors may be divided according to geographic space, with due north as 0°. Here, assuming that k wind direction sectors are divided, s ij Representing the probability of transferring from sector p to sector q, the wind direction sector transfer probability matrix S can be obtained as shown in the following equation 3. Here, as an example but not a limitation, the probability in the wind direction sector transfer probability matrix can be obtained from the time series obtained by transposing the wind speed measurement of the wind tower or other equipment in the design stage.
[0038] [Equation 3]
[0039]
[0040] In addition, the state transition probability can be obtained by multiplying the wind speed working interval transition probability and the wind direction sector transition probability. More specifically, for the transition from the wind speed working interval i to the working interval j, the probability of the wind direction sector transitioning from p to q is shown in the following equation 4.
[0041] [Equation 4]
[0042] P ij,pq =M ij *S pq
[0043] Here, it should be noted that the Markov chain in step S110 according to the embodiment of the present invention is only an example and not a limitation, and those skilled in the art may also use other Markov chains to perform step S110. For example, those skilled in the art may also use methods such as Kalman filtering and fuzzy logic to predict wind speed and wind direction.
[0044] The following will refer to Figure 2 Step S120 is described in more detail.
[0045] Figure 2 is a flow chart illustrating a method for determining a control strategy of a wind turbine to be executed in a next time period according to an exemplary embodiment of the present invention.
[0046] Reference Figure 2In step S210, the control strategies of the wind speed working range and the wind direction sector may be divided into multiple levels. Here, for example only and not limitation, the control strategies of the wind speed working range and the wind direction sector may be divided into multiple levels based on the operation constraint parameters of the wind turbine. Here, for example only and not limitation, the operation constraint parameters of the wind turbine may include at least one of power and critical load.
[0047] In step S220, it may be determined whether the maximum probability of the state transition probabilities in the next time period is greater than a predetermined threshold. Here, the predetermined threshold may be set by those skilled in the art according to actual conditions.
[0048] If the maximum probability of the state transition probability of the next time period is greater than the predetermined threshold, then in step S230, it is determined whether the level of the control strategy of the current time period is between the level of the control strategy of the previous time period and the level of the control strategy corresponding to the maximum probability. Here, the predetermined threshold can be set by those skilled in the art according to actual conditions, and is only used as an example and not a limitation. Here, it can be set to P75.
[0049] If the level of the control strategy of the current time period is not between the level of the control strategy of the previous time period and the level of the control strategy corresponding to the maximum probability, then in step S240, the control strategy of the previous time period is executed in the next time period.
[0050] In addition, if the maximum probability among the state transition probabilities of the next time period is not greater than a predetermined threshold, or the level of the control strategy of the current time period is between the level of the control strategy of the previous time period and the level of the control strategy corresponding to the maximum probability, then in step S250, the control strategy of the current time period is executed in the next time period.
[0051] Through the above-mentioned selective control processing of the control strategy, the switching frequency of the control strategy can be reduced, thereby reducing the workload of actuators such as yaw and pitch, and improving the safety and power generation capacity of the wind turbine.
[0052] Figure 3 is a block diagram showing a wind turbine sector management device according to an exemplary embodiment of the present invention.
[0053] Reference Figure 3 , a wind turbine sector management device according to an exemplary embodiment of the present invention may include a prediction unit 310 and a control unit 320 .
[0054] The prediction unit 310 can predict the wind speed and wind direction of the wind turbine.
[0055] The control unit 320 may determine a control strategy for the wind turbine to be executed in the next time period based on the wind speed and wind direction prediction results.
[0056] Figure 4 is a block diagram illustrating a computing device according to an exemplary embodiment of the present invention.
[0057] Reference Figure 4 , a computing device according to an exemplary embodiment of the present invention may include a processor 410 and a memory 420 .
[0058] The memory 420 may store a program that, when executed by the processor, causes the processor to execute the reference Figure 1 The program instructions of the wind turbine sector management method are not described in detail here.
[0059] According to an exemplary embodiment of the present invention, dynamic optimization of sector management can be achieved, thereby reducing the switching frequency of control strategies, reducing the workload of actuators such as yaw and pitch control, and improving the safety and power generation capacity of wind turbines.
[0060] According to an example embodiment of the present invention, the various steps of the method described above may be written as a program or software. Based on the block diagrams and flow charts shown in the accompanying drawings and the corresponding descriptions in the specification, any programming language may be used to write the program or software. In one example, the program or software may include machine code directly executed by one or more processors or computers, such as machine code generated by a compiler. In another example, the program or software includes a higher level code executed by one or more processors or computers using an interpreter. The program or software may be recorded, stored or fixed in one or more non-transitory computer-readable storage media. In one example, the program or software or one or more non-transitory computer-readable storage media may be distributed on a computer system.
[0061] According to an exemplary embodiment of the inventive concept, each step of the method described above may be implemented on a computing device including a processor and a memory. The memory stores program instructions for controlling the processor to implement the operations of each unit described above.
[0062] Although specific example embodiments of the present invention have been described in detail above with reference to the accompanying drawings, the present invention may be modified in various forms without departing from the spirit and scope of the present invention. Suitable results may be achieved if the described techniques are performed in a different order, and / or if the components in the described systems, architectures, or devices are combined in a different manner, and / or replaced or supplemented by other components or their equivalents. Therefore, the scope of the present disclosure is not limited by specific embodiments, but by the claims and their equivalents, and all changes within the scope of the claims and their equivalents will be interpreted as being included in the present disclosure.
[0063] While the invention has been shown and described with reference to the particular exemplary embodiments, it will be understood by those skilled in the art that various changes in form and details may be made without departing from the spirit and scope of the invention as defined by the claims and their equivalents.
Claims
1. A wind turbine management method, include: Predict wind speed and direction for wind turbines; The wind speed and wind direction forecast results are used to determine the wind turbine control strategy to be executed in the next time period. The steps of predicting wind speed and wind direction for wind turbines include: Obtain the wind speed working range transfer probability and wind direction sector transfer probability; The state transition probability is obtained based on the wind speed working range transition probability and the wind direction sector transition probability. The step of determining the control strategy of the wind turbine generator set to be executed in the next time period includes: Based on the operating constraint parameters of the wind turbine, the control strategies of the wind speed working range and wind direction sector of the wind turbine are divided into multiple levels; If the maximum probability of the state transition probability in the next time period is greater than a predetermined threshold, and the level of the control strategy in the current time period is not between the level of the control strategy in the previous time period and the level of the control strategy corresponding to the maximum probability, the control strategy of the previous time period is executed in the next time period. Among them, if the maximum probability among the state transition probabilities of the next time period is not greater than the predetermined threshold, or the level of the control strategy of the current time period is between the level of the control strategy of the previous time period and the level of the control strategy corresponding to the maximum probability, the control strategy of the current time period is executed in the next time period.
2. The wind turbine management method according to claim 1, in, The steps of obtaining the wind speed working range transfer probability and the wind direction sector transfer probability include: Obtaining a first number of wind speed operating intervals of the wind turbine generator system based on the wind speed; Obtaining wind speed working interval transition probabilities between a first number of wind speed working intervals; Obtaining a second number of wind direction sectors of the wind turbine generator system based on the wind direction; A wind direction sector transition probability between a second number of wind direction sectors is obtained.
3. The wind turbine management method according to claim 2, in, The step of obtaining the wind speed working interval transition probability between the first number of wind speed working intervals includes: A wind speed operating interval transition probability between a first number of wind speed operating intervals is obtained based on the probability density of the wind speed.
4. The wind turbine management method according to claim 2, in, The step of obtaining the wind direction sector transition probability between the second number of wind direction sectors comprises: The wind direction sector transition probability between the second number of wind direction sectors is obtained based on the time series obtained by transposing the wind speed measurement.
5. The wind turbine management method according to claim 2, in, The actual wind speed is inferred from the current operating status of the wind turbine to obtain the corresponding wind speed operating range.
6. The wind turbine management method according to claim 5, in, The current operating state of the wind turbine generator set includes at least one of the rotation speed, torque, pitch angle and power of the wind turbine generator set.
7. The wind turbine management method according to claim 1, in, The operation constraint parameter of the wind turbine generator set includes at least one of the power and the key load of the wind turbine generator set.
8. A wind turbine management device, used to implement the wind turbine management method according to claim 1, wherein the wind turbine management device include: Prediction unit, which predicts wind speed and direction for wind turbines; The control unit determines a control strategy for the wind turbine to be executed in the next time period based on the wind speed and wind direction prediction results.
9. A computing device, It is characterized in that include: processor; A memory storing program instructions which, when executed by a processor, enable the processor to execute the wind turbine management method according to any one of claims 1 to 7.
10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores program instructions which, when executed by a processor, enable the processor to execute the wind turbine management method according to any one of claims 1 to 7.
