Wind power plant scheduling method and system based on fatigue distribution

Abstract

This invention provides a wind power plant scheduling method and system based on fatigue distribution. [Solution] The solution includes establishing multiple wind turbine points based on the parameters of the wind turbine unit, generating predicted power for each wind turbine point within the current adjustment cycle based on a predetermined power prediction model based on historical environmental parameters, generating an initial scheduling policy based on the power grid scheduling command and the predicted power for all wind turbine points within the current adjustment cycle, obtaining fatigue evaluation values ​​for each wind turbine point, determining whether or not to modify the initial scheduling policy based on all fatigue evaluation values, generating an initial scheduling policy based on the operating parameters of each wind turbine unit, optimizing and adjusting the initial scheduling policy, and optimizing the uniformity of the fatigue distribution of the wind power plant while assuming no loss of power generation.

Description

Technical Field

[0001] This application relates to the field of wind power plant technology, and particularly to a wind power plant scheduling method and system based on fatigue distribution.

Background Art

[0002] For mountainous and hilly areas, the altitude difference of the installation positions of wind turbines is large. However, the change in altitude affects the change in wind speed. Moreover, when the influence of the wake is added, the wind speed input to each wind turbine unit becomes significantly non-uniform, and the load received by the wind turbine also becomes uncertain.

[0003] Currently, the control policy regarding the effective power of a wind power plant generally focuses on whether the output power can meet the demand of the power grid scheduling center, thereby ignoring the operating conditions of the wind power plant itself. In this way, the operating burden of the wind turbine unit is increased, ultimately leading to an increase in the failure rate, a decrease in the service life, and a deterioration in the operating economy of the entire wind power plant.

Summary of the Invention

[0004] In order to solve the above technical problems, this application provides a wind power plant scheduling method and system based on fatigue distribution, aiming to improve the operating efficiency and operating benefits of wind turbine units (also called wind power generator units), extend the service life of wind turbine units, and reduce the operation and maintenance costs of wind power plants.

[0005] In some embodiments of this application, an initial scheduling policy is generated based on the operating parameters of each wind turbine unit, a fatigue evaluation value of each wind turbine unit is generated based on a preset feedback time node, the initial scheduling policy is optimized and adjusted based on the fatigue evaluation values of all wind turbine points, and on the premise of not losing the power generation amount, the uniformity of the fatigue distribution of the wind power plant is optimized, the service life of the unit is extended, and the operation and maintenance costs of the wind power plant are reduced.

[0006] In some embodiments of the present invention, by periodically monitoring the uniformity of the fatigue distribution of a wind power plant, the operating parameters of excessively worn wind turbine units are adjusted in a timely manner. This improves the fatigue characteristics of the wind turbine units by controlling the rotational speed and propeller pitch angle of the units or by performing stop maintenance, thereby avoiding a decrease in the operating efficiency and lifespan of the wind turbine units due to excessive wear.

[0007] In some embodiments of the present invention, a wind power plant scheduling method based on fatigue distribution is provided. Establishing multiple wind turbine points based on the parameters of the wind turbine unit, Based on historical environmental parameters, multiple adjustment cycles are established, and a predicted power is generated for each wind turbine point within the current adjustment cycle based on a pre-set power prediction model. The initial scheduling policy is generated based on the power grid scheduling commands within the current adjustment cycle and the predicted power of all wind turbine points, This involves obtaining fatigue evaluation values ​​for each wind turbine point based on pre-configured feedback time nodes, and determining whether or not to modify the initial scheduling policy based on the fatigue evaluation values ​​for all wind turbine points. Here, the process of establishing multiple wind turbine points based on the parameters of the wind turbine unit is as follows: The task is to generate a sequence of wind turbine points A, where A = (a1, a2…ai…an), where ai is the i-th wind turbine point and n is the number of wind turbine points.

[0008] In some embodiments of the present invention, the process of generating an initial scheduling policy based on power grid scheduling commands within the current adjustment cycle and the predicted power of all wind turbine points is as follows: The objective is to establish a predicted power sequence P within the current adjustment cycle, where P = (p1, p2…pi…pn), where pi is the predicted power of the i-th wind turbine point within the current adjustment cycle. To generate demand power b' based on power grid scheduling commands, To generate the primary power within the current adjustment cycle for each wind turbine point based on the predicted power sequence P and the demand power b', The objective is to establish the primary power sequence B, where B = (b1, b2…bi…bn), and bi is the primary power of the i-th wind turbine point within the current adjustment period. Here,

number

[0009] In some embodiments of the present invention, the process of determining whether to modify the initial scheduling policy based on the fatigue evaluation values ​​of all wind turbine points is as follows: Setting multiple feedback time nodes within the current adjustment cycle, Obtain the fatigue evaluation value for each wind turbine point in the current feedback time node, The objective is to establish a sequence of fatigue evaluation values ​​C, where C = (c1, c2…ci…cn), where ci is the fatigue evaluation value at the current feedback time node of the i-th wind turbine. Based on the fatigue evaluation sequence C, a modified evaluation value g of the current feedback time node is generated, This includes determining whether a correction instruction has been generated based on the correction evaluation value g.

[0010] In some embodiments of this application, the method for calculating the modified evaluation value g is:

number

[0011] In some embodiments of the present application, the process of determining whether to generate a correction command based on the correction evaluation value g includes: presetting a first correction evaluation value threshold G1 and a second correction evaluation value threshold G2; when g < G1, not generating a correction command; when G1 ≤ g < G2, generating a primary correction command and generating a power compensation coefficient for each wind turbine point based on the primary correction command; correcting the initial scheduling policy based on all the power compensation coefficients; when g ≥ G2, generating a secondary correction command and correcting the initial scheduling policy based on the secondary correction command.

[0012] In some embodiments of the present application, the process of correcting the initial scheduling policy based on the secondary correction command includes: generating a fatigue evaluation value threshold C1 for the current feedback time node; when ci > C1, removing the i-th wind turbine point and setting the i-th wind turbine point as a wind turbine point to be inspected; generating an inspection plan based on all the wind turbine points to be inspected; establishing a primary wind turbine point sequence A1 of the current feedback time node based on the removal result. A1 = (a11, a12…a1i…a1n1), where a1i is the i-th unremoved windmill point of the current feedback time node, and n1 is the number of unremoved windmill points of the current feedback time node, and n1 ≤ n. The distribution coefficient for each primary wind turbine point is generated based on the predicted power and fatigue evaluation value of each primary wind turbine point, This includes generating a primary scheduling policy for the current feedback time node based on the distribution coefficient and demand power b'.

[0013] In some embodiments of the present invention, a wind power plant scheduling system based on fatigue distribution is provided. A central control unit used to establish multiple wind turbine points based on the parameters of a wind turbine unit, A monitoring unit comprising a plurality of monitoring submodules, the monitoring submodules comprising a monitoring unit installed at a wind turbine point and used to collect operating parameters of each wind turbine point, The aforementioned central control unit is A first processing module used to establish multiple adjustment cycles based on historical environmental parameters, the first processing module further includes a first processing module used to generate predicted power for each wind turbine point within the current adjustment cycle based on a preset power prediction model, A second processing module, which is used to generate an initial scheduling policy based on the power grid scheduling command within the current adjustment period and the predicted power of all wind turbine points. This process includes establishing a predicted power series P within the current adjustment period, where P = (p1, p2... pi... pn), where pi is the predicted power of the i-th wind turbine point within the current adjustment period, generating a required power b' based on the power grid scheduling command, generating the primary power of each wind turbine point within the current adjustment period based on the predicted power series P and the required power b', establishing a primary power series B, where B = (b1, b2... bi... bn), and bi is the primary power of the i-th wind turbine point within the current adjustment period, where [Number] including generating an initial scheduling policy for the current adjustment point period based on the primary power series B, and a second processing module; A third processing module for obtaining the fatigue evaluation value of each wind turbine point based on a preset feedback time node; A modification module for determining whether to modify the initial scheduling policy based on the fatigue evaluation values of all wind turbine points; A fourth processing module, which is used to generate a wind turbine point series A, where A = (a1, a2... ai... an), where ai is the i-th wind turbine point and n is the number of wind turbine points.

[0014] In some embodiments of the present application, the third processing module further sets a plurality of feedback time nodes within the current adjustment period; obtains the fatigue evaluation value of each wind turbine point of the current feedback time node; and is used to establish a fatigue evaluation value series C, where C = (c1, c2... ci... cn), where ci is the fatigue evaluation value of the i-th wind turbine at the current feedback time node.

[0015] In some embodiments of the present application, the correction module further generates a correction evaluation value g of the current feedback time node based on the sequence C of fatigue evaluation values, and the calculation method of the correction evaluation value g is [Number] where Here, e1 is a preset first weight coefficient, e2 is a preset second weight coefficient, e3 is a preset third weight coefficient, Q1 is a preset first predetermined coefficient, Q2 is a preset second predetermined coefficient, Q3 is a preset third predetermined coefficient, c’ is the predicted fatigue evaluation value of the current feedback time node, Δc is the average value of all data in the sequence C of fatigue evaluation values, Y(i) is a selection coefficient, when (ci - c’) > 0, Y(i) = 1 / (ci - c’), and when (ci - c’) < 0, Y(i) = 0, It is used to determine whether a correction instruction is generated based on the correction evaluation value g.

[0016] In some embodiments of the present application, the process of determining whether to generate a correction instruction based on the correction evaluation value g includes presetting a first correction evaluation value threshold G1 and a second correction evaluation value threshold G2, when g < G1, not generating a correction instruction, when G1 ≤ g < G2, generating a primary correction instruction and generating a power compensation coefficient for each wind turbine point based on the primary correction instruction, correcting the initial scheduling policy based on all the power compensation coefficients, when g ≥ G2, generating a secondary correction instruction and correcting the initial scheduling policy based on the secondary correction instruction, The process of correcting the initial scheduling policy based on the secondary correction instruction To generate a fatigue evaluation threshold C1 for the current feedback time node, If ci > C1, remove the i-th wind turbine point and set the i-th wind turbine point as the wind turbine point to be inspected. To generate an inspection plan based on all wind turbine points to be inspected, The process involves establishing a sequence of primary wind turbine points A1 of the current feedback time node based on the removal results, where A1 = (a11, a12…a1i…a1n1), where a1i is the i-th unremoved wind turbine point of the current feedback time node, and n1 is the number of unremoved wind turbine points of the current feedback time node, and n1 ≤ n. The distribution coefficient for each primary wind turbine point is generated based on the predicted power and fatigue evaluation value of each primary wind turbine point, This includes generating a primary scheduling policy for the current feedback time node based on the distribution coefficient and demand power b'.

[0017] The wind power plant scheduling method and system based on fatigue distribution in the embodiment of this application have the following beneficial effects compared to the prior art.

[0018] The system generates an initial scheduling policy based on the operating parameters of each wind turbine unit, generates fatigue evaluation values ​​for each wind turbine unit based on pre-configured feedback time nodes, optimizes and adjusts the initial scheduling policy based on the fatigue evaluation values ​​of all wind turbine points, optimizes the uniformity of the fatigue distribution of the wind power plant while assuming no loss of power generation, extends the service life of the units, and reduces the operation and maintenance costs of the wind power plant.

[0019] By periodically monitoring the uniformity of fatigue distribution in wind power plants, the operating parameters of excessively worn wind turbine units can be adjusted in a timely manner. This allows for control of the unit's rotational speed and propeller pitch angle, or shutdown maintenance, thereby improving the fatigue characteristics of the wind turbine units and avoiding a decrease in operating efficiency and lifespan due to excessive wear. [Brief explanation of the drawing]

[0020] [Figure 1] This is a flowchart of a wind power plant scheduling method based on fatigue distribution in a preferred embodiment of the present invention. [Figure 2] This is a structural block diagram of a wind power plant scheduling system based on fatigue distribution in a preferred embodiment of the present invention. [Modes for carrying out the invention]

[0021] The following describes specific embodiments of the present application in more detail, linking them with drawings and examples. The following embodiments are for illustrative purposes only and are not intended to limit the scope of the present application.

[0022] The terms "first" and "second" are for descriptive purposes only and should not be understood as indicating or implying relative importance, or as specifying the number of technical features. Therefore, the features defining "first" and "second" may explicitly or implicitly include one or more features. In this description, unless otherwise specified, "multiple" means two or more.

[0023] In the description of this application, unless otherwise specifically defined and limited, the term "attachment" should be understood in a broad sense, and may include, for example, a fixed connection, a removable connection, or an integral connection; a mechanical connection, an electrical connection, a direct connection, an indirect connection through an intermediate medium, or communication between two elements. A person skilled in the art will be able to understand the specific meaning of the above term in this application depending on the specific circumstances.

[0024] As shown in Figure 1, a wind power plant scheduling method based on the fatigue distribution of a preferred embodiment of the present invention is: S101 establishes multiple wind turbine points based on the parameters of the wind turbine unit, S102 involves establishing multiple adjustment cycles based on historical environmental parameters and generating predicted power for each wind turbine point within the current adjustment cycle based on a pre-set power prediction model. S103 generates an initial scheduling policy based on the power grid scheduling command within the current adjustment cycle and the predicted power of all wind turbine points, S104 involves obtaining fatigue evaluation values ​​for each wind turbine point based on pre-configured feedback time nodes, and determining whether or not to modify the initial scheduling policy based on all fatigue evaluation values ​​(i.e., fatigue evaluation values ​​for all wind turbine points), Here, the process of establishing multiple wind turbine points based on the parameters of the wind turbine unit is as follows: The method involves generating a sequence of wind turbine points A, where A = (a1, a2…ai…an), where ai is the i-th wind turbine point and n is the number of wind turbine points, and S104.

[0025] Specifically, one wind turbine point represents a model of one wind turbine unit, and the establishment of such a model can be performed using, for example, the OpenFAST open-source tool software, the GH Bladed software developed by DNV GL, or the ENFAST software developed by Enkyou Energy Inc., and the wind turbine unit parameters can be established in any of the above software, which belongs to the prior art in this field, and this application will not further describe the specific establishment process. The time length of a single adjustment cycle is set based on the historical demand fluctuation parameters and historical environmental fluctuation parameters of the power grid, and the more severe the fluctuation, the shorter the corresponding adjustment cycle time becomes, thereby ensuring the accuracy of the predicted values ​​within a single adjustment cycle of the power forecasting model and improving the scheduling efficiency for all wind turbine units in the wind power plant, and those skilled in the art can set the time length of a single adjustment cycle according to the actual situation, and this application is not specifically limited.

[0026] Specifically, the process of generating an initial scheduling policy based on the power grid scheduling command within the current adjustment cycle and the predicted power of all wind turbine points is as follows: The objective is to establish a predicted power sequence P within the current adjustment cycle, where P = (p1, p2…pi…pn), where pi is the predicted power of the i-th wind turbine point within the current adjustment cycle. To generate demand power b' based on power grid scheduling commands, To generate the primary power within the current adjustment cycle for each wind turbine point based on the predicted power sequence P and the demand power b', The objective is to establish the primary power sequence B, where B = (b1, b2…bi…bn), and bi is the primary power of the i-th wind turbine point within the current adjustment period. Here,

number

[0027] Specifically, the predicted power refers to the maximum active power that the corresponding wind turbine unit can provide within the current adjustment cycle, and the corresponding initial scheduling policy is generated based on the mean principle. Here, the pre-configured power prediction model may be any conventional calculation model capable of calculating the aforementioned maximum active power, and this application is not specifically limited.

[0028] To make it easier to understand, in the above embodiment, an initial scheduling policy for the output power of each wind turbine is generated based on the operating parameters of each wind turbine unit, a fatigue evaluation value for each wind turbine unit is generated based on a preset feedback time node, and the initial scheduling policy is optimized and adjusted based on all fatigue evaluation values. This optimizes the uniformity of the fatigue distribution of the wind power plant, extends the service life of the units, and reduces the operation and maintenance costs of the wind power plant, while ensuring no loss of power generation.

[0029] In a preferred embodiment of the present invention, the process for determining whether to modify the initial scheduling policy based on all fatigue evaluation values ​​is: Setting multiple feedback time nodes within the current adjustment cycle, Obtain the fatigue evaluation value for each wind turbine point in the current feedback time node, The objective is to establish a sequence of fatigue evaluation values ​​C, where C = (c1, c2…ci…cn), where ci is the fatigue evaluation value at the current feedback time node of the i-th wind turbine. Based on the fatigue evaluation sequence C, a modified evaluation value g of the current feedback time node is generated, This includes determining whether a correction instruction has been generated based on the correction evaluation value g.

[0030] Specifically, the fatigue load of a wind turbine unit is concentrated in the transmission system load due to shaft torsion and the tower structural load due to tower deflection. The fatigue load of the wind turbine unit can be determined by these parameters of shaft torque and tower thrust, thereby generating a corresponding fatigue evaluation value. This value can be calculated using the Palmgren-Miner linear cumulative damage theory, and a larger fatigue evaluation value indicates a greater degree of fatigue in the current wind turbine unit.

[0031] Specifically, by establishing multiple feedback time nodes, the fatigue state of each wind turbine unit is periodically monitored, thereby optimizing and correcting the initial scheduling policy, and improving the uniformity of the fatigue distribution within the wind power plant.

[0032] Specifically, the calculation method for the corrected evaluation value g is:

number

[0033] Specifically, the preset first weight coefficient e1, the preset second weight coefficient e2, and the preset third weight coefficient e3 may be set according to the actual situation in the art. This application is not specifically limited. Also, by presetting the first predetermined coefficient Q1, the second predetermined coefficient Q2, and the third predetermined coefficient Q3, normalization processing is performed on all parameters in the corrected evaluation value g, thereby making each parameter within the same value range.

[0034] Specifically, an estimated fatigue evaluation value of the current feedback time node is generated based on historical parameters, and the estimated fatigue evaluation value means the fatigue loss that occurs when the wind turbine unit operates in an ideal state and reaches the current feedback time node with the accumulation of operation time.

[0035] Specifically, the larger the corrected evaluation value, the worse the uniformity of the fatigue distribution in the current wind power plant, indicating that there are more wind turbine units with a fatigue degree greater than expected. It is necessary to timely correct and optimize the current initial scheduling policy.

[0036] As can be understood, in the above embodiment, by periodically monitoring the uniformity of the fatigue distribution of the wind power plant, the operation parameters of the overly worn wind turbine units are timely adjusted, and the fatigue characteristics of the wind turbine units are improved by controlling the rotation speed or propeller pitch angle of the units or performing stop maintenance, etc., to avoid the reduction of the operation efficiency and the reduction of the operation years of the wind turbine units due to excessive wear.

[0037] In a preferred embodiment of the embodiment of this application, the process of determining whether to generate a correction command based on the corrected evaluation value g is presetting a first corrected evaluation value threshold G1 and a second corrected evaluation value threshold G2, and when g < G1, not generating a correction command, and when G1 ≤ g < G2, generating a primary correction command, and generating a power compensation coefficient for each wind turbine point based on the primary correction command. Modify the initial scheduling policy based on all power compensation factors, This includes, if g ≥ G2, generating a secondary modification directive and modifying the initial scheduling policy based on the secondary modification directive.

[0038] Specifically, the first and second modified evaluation thresholds may be set based on historical parameters.

[0039] Specifically, when generating primary correction commands, the system indicates that the uniformity of fatigue distribution within the current wind power plant is low. Based on the output capacity and fatigue level of each wind turbine unit, higher-level scheduling commands are distributed proportionally. Through optimization processing, power compensation coefficients are generated for each wind turbine unit, thereby achieving scheduling optimization for each unit. Assuming no loss of power generation, the system optimizes the uniformity of fatigue distribution in the wind power plant, extends the service life of the units, and reduces the operation and maintenance costs of the wind power plant.

[0040] Specifically, the process of modifying the initial scheduling policy based on the secondary modification directive is as follows: To generate a fatigue evaluation threshold C1 for the current feedback time node, If ci > C1, remove the i-th wind turbine point and set the i-th wind turbine point as the wind turbine point to be inspected. To generate an inspection plan based on all wind turbine points to be inspected, Based on the removal results, establish the sequence of primary wind turbine points A1 of the current feedback time node. A1 = (a11, a12…a1i…a1n1), where a1i is the i-th unremoved windmill point of the current feedback time node, n1 is the number of unremoved windmill points of the current feedback time node, and n1 ≤ n. The distribution coefficient for each primary wind turbine point is generated based on the predicted power and fatigue evaluation value of each primary wind turbine point, This includes generating a primary scheduling policy for the current feedback time node based on the distribution coefficient and demand power b'.

[0041] Specifically, the fatigue evaluation threshold may be set based on historical parameters. If ci > C1, it indicates that there is an abnormal loss in the i-th wind turbine unit, requiring timely inspection, thereby improving the operating life of the wind turbine unit.

[0042] Specifically, by stopping some wind turbine units that have abnormal losses, the losses are reduced, the operating life of the wind turbine units is improved, and at the same time, the remaining primary wind turbine points are proportionally allocated to the higher-level scheduling command based on their output capacity and fatigue level, and after optimization processing, a primary scheduling policy is generated.

[0043] Specifically, if the total predicted power of the remaining primary wind turbine points is lower than the demand power b', each primary wind turbine point will generate power based on the predicted power, and the operating parameters of each removed wind turbine point will be set based on the power difference between the total predicted power and the demand power b'.

[0044] Based on another preferred embodiment of the fatigue distribution-based wind power plant scheduling method in any of the above preferred embodiments, this preferred embodiment provides a fatigue distribution-based wind power plant scheduling system, referring to Figure 2, the fatigue distribution-based wind power plant scheduling system is A central control unit used to establish multiple wind turbine points based on the parameters of a wind turbine unit, A monitoring unit comprising a plurality of monitoring submodules, the monitoring submodules being installed at wind turbine points and used to collect operating parameters of each wind turbine point, The central control unit is A first processing module used to establish multiple adjustment cycles based on historical environmental parameters, the first processing module further includes a first processing module used to generate predicted power for each wind turbine point within the current adjustment cycle based on a preset power prediction model, A second processing module for generating an initial scheduling policy based on the power grid scheduling command within the current adjustment cycle and the predicted power of all wind turbine points, A third processing module for obtaining fatigue evaluation values ​​for each wind turbine point based on a pre-set feedback time node, A modification module for determining whether or not to modify the initial scheduling policy based on all fatigue evaluation values, A fourth processing module is used to generate a sequence of wind turbine points A, where A = (a1, a2…ai…an), where ai is the i-th wind turbine point and n is the number of wind turbine points. The second processing module further, The objective is to establish a predicted power sequence P within the current adjustment cycle, where P = (p1, p2…pi…pn), where pi is the predicted power of the i-th wind turbine point within the current adjustment cycle. To generate demand power b' based on power grid scheduling commands, To generate the primary power within the current adjustment cycle for each wind turbine point based on the predicted power sequence P and the demand power b', The objective is to establish the primary power sequence B, where B = (b1, b2…bi…bn), and bi is the primary power of the i-th wind turbine point within the current adjustment period. Here,

number

[0045] Specifically, the third processing module further sets a plurality of feedback time nodes within the current adjustment period, obtains the fatigue evaluation value of each windmill point of the current feedback time node, and establishes a sequence C of fatigue evaluation values, where C = (c1, c2... ci... cn), and ci is used as the fatigue evaluation value at the current feedback time node of the i-th windmill.

[0046] In a preferred embodiment of the embodiment of the present application, the correction module further generates a correction evaluation value g of the current feedback time node based on the sequence C of fatigue evaluation values, judges whether a correction instruction has been generated based on the correction evaluation value g,

Number

[0047] Specifically, the process of judging whether to generate a correction instruction based on the correction evaluation value g presets a first correction evaluation value threshold G1 and a second correction evaluation value threshold G2, when g < G1, does not generate a correction instruction, When G1 ≤ g < G2, generate a primary correction instruction and generate a power compensation coefficient for each wind turbine point based on the primary correction instruction. Modify the initial scheduling policy based on all the power compensation coefficients. When g ≥ G2, generate a secondary correction instruction and modify the initial scheduling policy based on the secondary correction instruction. This includes the above.

[0048] According to the first concept of the present application, an initial scheduling policy is generated based on the operating parameters of each wind turbine unit, a fatigue evaluation value of each wind turbine unit is generated based on a preset feedback time node, the initial scheduling policy is optimized and adjusted based on all the fatigue evaluation values, and on the premise of not losing the power generation amount, the uniformity of the fatigue distribution of the wind farm is optimized, the service life of the unit is extended, and the operation and maintenance cost of the wind farm is reduced.

[0049] According to the second concept of the present application, by periodically monitoring the uniformity of the fatigue distribution of the wind farm, the operating parameters of the wind turbine units that are excessively worn are adjusted in a timely manner, and the fatigue characteristics of the wind turbine units are improved by controlling the rotation speed and propeller pitch angle of the units or stopping maintenance, etc., to avoid the reduction of the operating efficiency and the reduction of the operating years of the wind turbine units due to excessive wear.

[0050] The above are only preferred embodiments of the present application. It should be pointed out that for those skilled in the art, several improvements and replacements can be made on the premise of not departing from the technical principle of the present application, and these improvements and replacements should also be regarded as within the protection scope of the present application.

Claims

1. A wind power plant scheduling method based on fatigue distribution, Establishing multiple wind turbine points based on the parameters of the wind turbine unit, Based on historical environmental parameters, multiple adjustment cycles are established, and a predicted power is generated for each wind turbine point within the current adjustment cycle based on a pre-set power prediction model. The initial scheduling policy is generated based on the power grid scheduling commands within the current adjustment cycle and the predicted power of all wind turbine points, This involves obtaining fatigue evaluation values ​​for each wind turbine point based on pre-configured feedback time nodes, and determining whether or not to modify the initial scheduling policy based on the fatigue evaluation values ​​for all wind turbine points. Here, establishing multiple wind turbine points based on the parameters of the wind turbine unit is A wind power plant scheduling method based on fatigue distribution, characterized by generating a sequence of wind turbine points A, where A = (a1, a2...ai...an), where ai is the i-th wind turbine point and n is the number of wind turbine points.

2. Generating an initial scheduling policy based on the power grid scheduling command within the current adjustment cycle and the predicted power of all wind turbine points is, The objective is to establish a predicted power sequence P within the current adjustment cycle, where P = (p1, p2...pi...pn), where pi is the predicted power of the i-th wind turbine point within the current adjustment cycle. To generate demand power b' based on power grid scheduling commands, To generate the primary power within the current adjustment cycle for each wind turbine point based on the predicted power sequence P and the demand power b', The objective is to establish the primary power sequence B, where B = (b1, b2...bi...bn), where bi is the primary power of the i-th wind turbine point within the current adjustment cycle. Here, [Math 1] That is, A wind power plant scheduling method based on fatigue distribution according to claim 1, characterized by comprising generating an initial scheduling policy for the current adjustment period based on the primary power sequence B.

3. Determining whether or not to modify the initial scheduling policy based on the fatigue assessment values ​​of all wind turbine points is Setting multiple feedback time nodes within the current adjustment cycle, Obtain the fatigue evaluation value for each wind turbine point in the current feedback time node, The objective is to establish a sequence C of fatigue evaluation values, where C = (c1, c2...ci...cn), where ci is the fatigue evaluation value at the current feedback time node of the i-th wind turbine. Based on the sequence of fatigue evaluation values ​​C, a corrected evaluation value g for the current feedback time node is generated, The wind power plant scheduling method based on fatigue distribution according to claim 2, characterized in that it includes determining whether or not a correction command has been generated based on a corrected evaluation value g.

4. The calculation method for the aforementioned corrected evaluation value g is: [Math 2] And, Herein, e1 is a preset first weight coefficient, e2 is a preset second weight coefficient, e3 is a preset third weight coefficient, Q1 is a preset first predetermined coefficient, Q2 is a preset second predetermined coefficient, Q3 is a preset third predetermined coefficient, c' is the predicted fatigue evaluation value of the current feedback time node, Δc is the average value of all data in the fatigue evaluation value sequence C, Y(i) is a selection coefficient, where Y(i) = 1 / (ci - c') if (ci - c') > 0, and Y(i) = 0 if (ci - c') < 0, characterized in that a wind power plant scheduling method based on fatigue distribution according to claim 3.

5. Determining whether or not to generate a correction command based on the correction evaluation value g is, The first corrected evaluation threshold G1 and the second corrected evaluation threshold G2 are set in advance, If g < G1, no correction command is generated. If G1 ≤ g < G2, a primary correction command is generated, and power compensation coefficients for each wind turbine point are generated based on the primary correction command. Modify the initial scheduling policy based on all power compensation factors, A wind power plant scheduling method based on fatigue distribution according to claim 4, characterized in that, if g ≥ G2, a secondary correction command is generated, and the initial scheduling policy is modified based on the secondary correction command.

6. Modifying the initial scheduling policy based on the secondary modification directive means To generate a fatigue evaluation threshold C1 for the current feedback time node, If ci > C1, the i-th wind turbine point is removed, and the i-th wind turbine point is set as the wind turbine point to be inspected. To generate an inspection plan based on all wind turbine points to be inspected, The process involves establishing a sequence of primary wind turbine points A1 of the current feedback time node based on the removal results, where A1 = (a11, a12...a1i...a1n1), where a1i is the i-th unremoved wind turbine point of the current feedback time node, and n1 is the number of unremoved wind turbine points of the current feedback time node, and n1 ≤ n. The distribution coefficient for each primary wind turbine point is generated based on the predicted power and fatigue evaluation value of each primary wind turbine point, A wind power plant scheduling method based on fatigue distribution according to claim 5, comprising generating a primary scheduling policy for the current feedback time node based on the distribution coefficient and the demand power b'.

7. A wind power plant scheduling system based on fatigue distribution, employing a wind power plant scheduling method based on fatigue distribution as described in any one of claims 1 to 6 above, A central control unit used to establish multiple wind turbine points based on the parameters of a wind turbine unit, It includes multiple monitoring submodules, each containing a monitoring unit installed at a wind turbine point and used to collect operating parameters for each wind turbine point, The aforementioned central control unit is A first processing module used to establish multiple adjustment cycles based on historical environmental parameters, and further used to generate predicted power for each wind turbine point within the current adjustment cycle based on a pre-configured power prediction model, Used to generate an initial scheduling policy based on the power grid scheduling command for the current adjustment cycle and the predicted power of all wind turbine points, establishing a predicted power sequence P for the current adjustment cycle, where P = (p1, p2...pi...pn), where pi is the predicted power of the i-th wind turbine point for the current adjustment cycle; generating demand power b' based on the power grid scheduling command; generating primary power for each wind turbine point for the current adjustment cycle based on the predicted power sequence P and demand power b'; and establishing a primary power sequence B, where B = (b1, b2...bi...bn), where bi is the primary power of the i-th wind turbine point for the current adjustment cycle, where [Math 3] A second processing module includes the following: that , and that generate an initial scheduling policy for the current adjustment point period based on the primary power sequence B; A third processing module for obtaining fatigue evaluation values ​​for each wind turbine point based on a pre-set feedback time node, A modification module for determining whether or not to modify the initial scheduling policy based on the fatigue evaluation values ​​of all wind turbine points, A wind power plant scheduling system based on fatigue distribution, characterized by including a fourth processing module used to generate a sequence of wind turbine points A, where A = (a1, a2...ai...an), where ai is the i-th wind turbine point and n is the number of wind turbine points.

8. The third processing module described above further, Setting multiple feedback time nodes within the current adjustment cycle, Obtain the fatigue evaluation value for each wind turbine point in the current feedback time node, A wind power plant scheduling system based on a fatigue distribution according to claim 7, characterized in that a sequence C of fatigue evaluation values ​​is established, where C = (c1, c2...ci...cn), where ci is used as the fatigue evaluation value at the current feedback time node of the i-th wind turbine.

9. The aforementioned modification module further, The method for calculating the corrected evaluation value g of the current feedback time node is to generate a corrected evaluation value g of the current feedback time node based on a sequence of fatigue evaluation values ​​C, [Math 4] And, Here, e1 is a predetermined first weight coefficient, e2 is a predetermined second weight coefficient, e3 is a predetermined third weight coefficient, Q1 is a predetermined first coefficient, Q2 is a predetermined second coefficient, Q3 is a predetermined third coefficient, c' is the predicted fatigue evaluation value of the current feedback time node, Δc is the average value of all data in the fatigue evaluation value sequence C, Y(i) is the selection coefficient, and if (ci - c') > 0, Y(i) = 1 / (ci - c'), and if (ci - c') < 0, Y(i) = 0. The wind power plant scheduling system based on fatigue distribution according to claim 8, characterized in that it is used to determine whether or not a correction command has been generated based on the corrected evaluation value g.

10. Determining whether or not to generate a correction command based on the correction evaluation value g is, The first corrected evaluation threshold G1 and the second corrected evaluation threshold G2 are set in advance, If g < G1, no correction command is generated. If G1 ≤ g < G2, a primary correction command is generated, and power compensation coefficients for each wind turbine point are generated based on the primary correction command. Modify the initial scheduling policy based on all power compensation factors, If g ≥ G2, this includes generating a secondary modification directive and modifying the initial scheduling policy based on the secondary modification directive, Modifying the initial scheduling policy based on the secondary modification directive means To generate a fatigue evaluation threshold C1 for the current feedback time node, If ci > C1, the i-th wind turbine point is removed, and the i-th wind turbine point is set as the wind turbine point to be inspected. To generate an inspection plan based on all wind turbine points to be inspected, The process involves establishing a sequence of primary wind turbine points A1 of the current feedback time node based on the removal results, where A1 = (a11, a12...a1i...a1n1), where a1i is the i-th unremoved wind turbine point of the current feedback time node, and n1 is the number of unremoved wind turbine points of the current feedback time node, and n1 ≤ n. The distribution coefficient for each primary wind turbine point is generated based on the predicted power and fatigue evaluation value of each primary wind turbine point, A wind power plant scheduling system based on fatigue distribution according to claim 9, comprising generating a primary scheduling policy for the current feedback time node based on a distribution coefficient and demand power b'.

Images