Fan group classification control method and device of direct air cooling power station
By classifying and controlling the wind turbine group of the direct air-cooled power plant and adjusting the turbine frequency according to the degree of influence of environmental wind, the problem of unstable operation of the wind turbine group under complex terrain was solved, and the power generation efficiency and cooling performance were improved.
Patent Information
- Application Number
- CN202511537718.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-27
- Publication Date
- 2026-01-09
AI Technical Summary
In existing technologies, the wind turbine groups of direct air-cooled power plants cannot effectively cope with the influence of ambient wind under complex terrain conditions, resulting in reduced ventilation and hot air recirculation, thereby reducing power generation efficiency.
By analyzing the simulated operating parameters of each wind turbine, a sensitivity vector is generated, the wind turbine group is classified, and the operating frequency of the wind turbines in each category is adjusted to make them consistent. The frequency is also adjusted according to the degree of influence of the ambient wind, thereby achieving classified control.
It improves power generation efficiency, reduces the impact of ambient wind on the wind turbine, enhances cooling performance and operational stability, and brings significant economic benefits.
Smart Images
Figure FT_1 
Figure FT_2 
Figure FT_3
Abstract
Description
Technical Field
[0001] This invention relates to the field of wind turbine operation technology, and in particular to a method and device for classifying and controlling wind turbine groups in a direct air-cooled power plant. Background Technology
[0002] In direct air-cooled power plants, the operating status of the wind turbine group directly affects the cooling effect of the condenser. However, the operating status of the wind turbines is highly susceptible to factors such as ambient wind. Current technologies divide the wind turbine group into zones by row and column, or by windward and leeward sides, to perform variable frequency drive (VFD) regulation on the zoned turbines. However, these zoning and VFD methods often fail to accurately reflect the actual operating conditions of the wind turbines under strong ambient winds, especially in complex terrain conditions. They cannot address issues such as reduced ventilation and hot air recirculation, ultimately leading to decreased power generation efficiency.
[0003] Therefore, a new technical solution is urgently needed to solve the above-mentioned technical problems. Summary of the Invention
[0004] This invention provides a method and apparatus for classifying and controlling wind turbine groups in a direct air-cooled power plant. It can classify and control wind turbine groups according to the degree of influence of ambient wind on the turbines, adapt to complex terrain conditions, reduce the impact of ambient wind on the turbines, and improve power generation efficiency.
[0005] In a first aspect, the present invention provides a method for classifying and controlling a group of wind turbines in a direct air-cooled power plant, comprising: Based on the simulated operating parameters of each wind turbine in the direct air-cooled power plant group under a preset ambient wind speed, a sensitivity vector is obtained to represent the degree of influence of ambient wind on each wind turbine. Based on the sensitivity vector of each wind turbine, the wind turbine group in the direct air-cooled power plant is classified to obtain a preset number of target classifications. Based on the different degrees to which each target category is affected by environmental wind, the operating frequency of all wind turbines in each target category is adjusted to make the operating frequency of all wind turbines in each target category consistent, and the target categories show a decreasing trend in the order of the degree of influence of environmental wind from the most severe to the least severe, so as to classify and control the wind turbine group in the air-cooled power plant.
[0006] Secondly, the present invention provides a wind turbine group classification control device for a direct air-cooled power plant, comprising: The sensitivity vector acquisition module obtains a sensitivity vector representing the degree of influence of the ambient wind on each wind turbine based on the simulation operating parameters of each wind turbine in the direct air-cooled power plant's wind turbine group under a preset ambient wind speed. The wind turbine group classification module is connected to the sensitivity vector acquisition module. Based on the sensitivity vector of each wind turbine, it classifies the wind turbine group in the direct air-cooled power plant to obtain a preset number of target classifications. The operating frequency adjustment module, connected to the wind turbine group classification module, adjusts the operating frequency of all wind turbines in each target category based on the different degrees of influence of environmental wind on each target category, so that the operating frequency of all wind turbines in each target category is consistent, and the target categories show a decreasing trend in the order of the degree of influence of environmental wind from the most severe to the least severe, so as to classify and control the wind turbine group in the air-cooled power plant.
[0007] Thirdly, the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the method described in the first aspect of the present invention.
[0008] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the method described in the first aspect of the present invention.
[0009] This invention provides a method and apparatus for classifying and controlling a group of wind turbines in a direct air-cooled power plant. It classifies the wind turbines within the plant based on the degree to which they are affected by ambient wind, thus scientifically addressing the performance deviation of the units caused by mountain influences and reducing the impact of ambient wind on the turbines. The method employs a gradient-decreasing frequency adjustment strategy, moving the turbine frequency from the most affected category to the least affected category. This smooth frequency transition creates a synergistic resistance to wind pressure, improving the cooling performance, operational stability, and economic efficiency of the direct air-cooled system under harsh ambient wind conditions. Attached Figure Description
[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0011] Figure 1 This is a flowchart of a wind turbine group classification control method for a direct air-cooled power plant according to an embodiment of the present invention; Figure 2 This is a schematic block diagram of a wind turbine group classification control device for a direct air-cooled power plant according to an embodiment of the present invention; Figure 3This is an example of an asymmetric partitioning result for a wind turbine group provided in an embodiment of the present invention. Detailed Implementation
[0012] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.
[0013] Please refer to Figure 1 This invention provides a method for classifying and controlling a group of wind turbines in a direct air-cooled power plant, the method comprising: Step 100: Based on the simulation operating parameters of each wind turbine in the direct air-cooled power plant under the preset ambient wind speed, obtain the sensitivity vector to represent the degree of influence of the ambient wind on each wind turbine. Step 102: Based on the sensitivity vector of each wind turbine, classify the wind turbine group in the direct air-cooled power plant to obtain a preset number of target classifications; Step 104: Based on the different degrees of influence of environmental wind on each target category, adjust the operating frequency of all wind turbines in each target category to make the operating frequency of all wind turbines in each target category consistent, and make the target categories show a decreasing pattern in order of the degree of influence of environmental wind from heavy to light, so as to classify and control the wind turbine group in the air-cooled power plant.
[0014] In this embodiment of the invention, to analyze the degree of influence of ambient wind on wind turbines located at different positions in a direct air-cooled power plant, the operating state of the wind turbines is simulated under a preset ambient wind speed. Based on the simulated operating state, a sensitivity vector is obtained for each wind turbine, representing the degree of influence of ambient wind on each turbine. The wind turbine group within the direct air-cooled power plant is classified according to the sensitivity vectors, resulting in several target categories. This allows for the scientific arrangement of the operating frequency of the wind turbines within each target category. In this target classification result, wind turbines with different environmental influences are grouped into the same target category. All wind turbines in each target category have the same operating frequency, and the operating frequency of wind turbines decreases between different target categories. The target category with the highest wind turbine operating frequency is most severely affected by ambient wind, while the target category with the lowest wind turbine operating frequency is least affected by ambient wind.
[0015] by Figure 3 The target classification results include four target categories: F1, F2, F3, and F4, which will be used as an example for explanation. F1 is the area most severely affected by environmental winds, i.e., the hardest-hit area, mainly containing... Figure 3The central fan in the first row on the windward side is the area most severely impacted by the direct impact of ambient winds, and experiences the most significant backflow and hot air recirculation. Zone F2 is the next most severely affected area. Figure 3 The F1 zone is located behind and to both sides of the F1 zone, and is affected by both the airflow around the F1 zone and the induced hot air recirculation. The F3 zone is the affected zone, located further back, and is mainly affected by the pressure of the high-temperature plume. The F4 zone is the safe zone, located at the innermost part of the air-cooled island and on the leeward side, and is the area least affected by the ambient wind. Thus, the degree of influence from the ambient wind varies in each target category. Based on this classification standard, the operating frequency of the fans in the target categories is adjusted to achieve classified control of the fan group based on the fan operating parameters. In this invention, the fan operating frequency decreases from the windward target category to the leeward target category, i.e., F1 > F2 > F3 > F4.
[0016] In one embodiment of the present invention, based on the simulated operating parameters of each wind turbine in a direct air-cooled power plant under a preset ambient wind speed, a sensitivity vector representing the degree of influence of ambient wind on each wind turbine is obtained, including: The preset ambient wind speed is input into the simulation model of the direct air-cooled power plant to obtain the simulation operating parameters of each wind turbine output by the simulation model. Based on the simulation operating parameters and the baseline operating parameters under windless conditions, the sensitivity vector of each wind turbine is obtained using the following formula:
[0017] in, For the first The sensitivity vector of the typhoon generator. , For the first The first typhoon machine Simulation running parameters, For the first The first typhoon machine Reference operating parameters, This represents the total number of running parameters.
[0018] In this embodiment of the invention, specifically, a high-fidelity digital twin model capable of accurately reproducing the real operating environment within a direct air-cooled power plant is established. This model includes a three-dimensional physical model of representative complex terrain (such as mountains and canyons) surrounding the power plant, and geometrically simplifies the main buildings in the plant area (boiler room, turbine room, etc.). The computational domain within the model employs a high-density or adaptive hybrid mesh to accurately capture the influence of terrain on the macroscopic flow field. In this simulation model, the simulation operating parameters are calculated through coupled iterative calculations using a CFD (Computational Fluid Dynamics) model and a principled thermal system model of the power plant established in MATLAB software. During the calculation process, preset operating condition parameters are input into the simulation model to obtain the output simulation operating parameters. To consider the scenario with the greatest environmental impact on the wind turbine, these preset operating condition parameters typically select one or more preset typical severe operating conditions (such as high wind weather) parameters. Through the aforementioned high-fidelity model, CFD simulation is performed to generate a database containing all detailed wind simulation operating parameters within the direct air-cooled power plant.
[0019] The preset ambient wind speed typically represents the wind speed corresponding to the most severe operating conditions of a direct air-cooled power plant, and uses the windless condition (i.e., ambient wind speed of 0 m / s) as the performance benchmark to obtain the corresponding benchmark operating parameters. The operating parameters include... The term is used to represent various performance parameters of the wind turbine. The vector formed by the difference between the simulated operating parameters and the baseline operating parameters is the sensitivity vector.
[0020] In one disclosed embodiment of the present invention, the simulation operating parameters of the fan include the following five items: input variable, mass flow rate, heat exchange, fan shaft power, heat exchanger inlet temperature, and outlet temperature. These five simulation operating parameters can comprehensively reflect the aerodynamic performance and thermodynamic properties of the fan.
[0021] In one embodiment of the present invention, the wind turbine group in a direct air-cooled power plant is classified based on the sensitivity vector of each wind turbine to obtain a preset number of target classifications, including: Based on the sensitivity vector of each wind turbine, the similarity between any two wind turbines is obtained; Each wind turbine is used as an initial target category, and the inter-class distance between any two target categories is calculated. The two target classifications with the smallest inter-class distance are merged to obtain a new target classification; Repeat the steps from calculating the inter-class distance between every two target categories to merging the two target categories with the smallest inter-class distance to obtain a new target category, until all wind turbines are assigned to a preset number of target categories.
[0022] In this embodiment of the invention, based on the sensitivity vector of each wind turbine, the similarity or difference between any two wind turbines is calculated and quantified. Each wind turbine is considered as an initial target category, and the inter-class distance between any two target categories is calculated. The calculation is iteratively performed on the initial target categories, calculating and merging any two existing target categories, determining the increment of the sum of squared deviations within the target categories resulting from the merger, and selecting the pair of initial target categories that minimizes this increment for merging. This "distance calculation-merging" process is repeated continuously, gradually reducing the number of target categories until a preset number of target categories is reached (e.g., ...). Figure 3 (4 of them), all wind turbines are automatically assigned to a preset number of target categories. Each target category has significantly different operating characteristics and is named according to the degree of impact on that target category (e.g., severely affected area, less severely affected area, affected area, and safe area).
[0023] In one embodiment of the present invention, the similarity between any two wind turbines is obtained by the following formula:
[0024] in, To determine the similarity between the two wind turbines, and These are the sensitivity vectors for the two wind turbines, respectively. and The first of the two wind turbines The difference between the simulation parameters and the baseline parameters. This represents the total number of running parameters.
[0025] In this embodiment, Euclidean distance is used to quantify the similarity between any two wind turbines. The smaller the Euclidean distance between two wind turbines, the more similar their response patterns (i.e., performance sensitivity) to severe operating conditions, and the more likely they should be classified into the same region.
[0026] In one embodiment of the present invention, the inter-class distance between every two target classifications is calculated using the following formula:
[0027] in, For inter-class distance, and They are two target classifications, Classify the target The number of medium-sized wind turbines Classify the target The center point, Classify the target The number of medium-sized wind turbines Classify the target The center point.
[0028] In this embodiment, the Ward's method is used as the metric for inter-class distance. It iteratively merges the two target classes with the smallest increase in intra-class variance until a preset number of target classes are reached. This method's classification process is not based on a preset similarity threshold, but rather is an iterative merging process aimed at minimizing the increase in intra-class variance caused by each merge. The increment of the sum of squared intra-class deviations after merging all existing classes is calculated; this increment is defined as the inter-class distance. Choose to make The two target categories with the smallest values are merged to form a new target category.
[0029] In one embodiment of the present invention, the operating frequency of all wind turbines in each target category is adjusted by the following formula:
[0030] in, For the first The operating frequency of wind turbines in each target category is ranked as follows: All target categories are numbered in descending order of the degree of influence from environmental wind. , , The preset base frequency, .
[0031] In this embodiment of the invention, the operating frequency is set in a gradient decreasing pattern from the area most severely affected by ambient wind to the area least affected. It can be understood that the area most severely affected by ambient wind is typically the target category on the windward side, while the area least affected is typically the target category on the windward side. This degree of influence can also be represented by the sensitivity vector of all wind turbines within the target category.
[0032] In one embodiment of the present invention, the simulation operating parameters of the wind turbine are standardized using the following formula:
[0033] in, For the first The first typhoon machine Simulation running parameters, For the first The first typhoon machine The initial values of the simulation parameters. For all wind turbines The average initial values of the simulation parameters. For all wind turbines The standard deviation of the initial values of the simulation parameters.
[0034] In this embodiment, to avoid errors caused by differences in the data magnitude of various simulation parameters, the Z-score (Standard Score) method is used to standardize the various simulation parameters.
[0035] The technical solutions in the embodiments of the present invention will be explained and illustrated below through a specific example: Application verification was conducted at a 2×660MW direct air-cooled coal-fired power plant located in a certain region. The power plant is situated in complex mountainous terrain, surrounded by peaks and ridges 35-75 meters higher than the air-cooling platform to the north and west, representing a typical scenario for applying this invention.
[0036] The most severe operating condition posing the greatest threat to the unit—a forward wind of 13.5 m / s—is selected for an example demonstration. Under this condition, without any optimization measures, the windward fans of the unit will fail on a large scale, resulting in severe hot air recirculation and a huge loss of net output. A high-fidelity model was used to simulate the 13.5 m / s forward wind condition, and data such as mass flow rate, heat exchange, shaft power, and inlet / outlet temperature of 112 fans were obtained. This data was input into a system clustering algorithm to obtain four control zones: F1, F2, F3, and F4, which reflect the asymmetric influence of the mountain. The fan frequencies of the three windward zones (F1, F2, F3) most severely affected by the environmental wind were all overclocked to 110%, while the least affected zone, F4, maintained 100% of its rated frequency.
[0037] By comparing the performance data after implementing the present invention with the unoptimized baseline conditions, significant beneficial effects were obtained, as shown in Table 1.
[0038] Table 1: Performance Comparison of Optimal Adjustment Strategy (110% Overclocking in F1, F2, and F3 Zones) and Baseline Conditions
[0039] As can be seen from the data in Table 1, the technical solution disclosed in this invention can significantly improve cooling performance and bring huge economic benefits. The back pressure of both units is significantly reduced, with an average reduction of over 2.2 kPa, indicating that the cooling capacity of the air-cooled system has been fundamentally restored. The backflow phenomenon of the windward side fan has completely disappeared. The unit's power generation efficiency is significantly improved, and the average standard coal consumption is reduced by approximately 1.61 g / kWh, demonstrating extremely high economic value. Overclocking benefits exhibit diminishing marginal returns. Prioritizing overclocking the most severely affected F1 and F2 zones is the most cost-effective option. In normal windy weather, overclocking only F1 and F2 zones may be a more economical solution, while in extreme weather conditions, overclocking all windward areas (F1, F2, F3) is necessary to ensure unit safety. This embodiment fully demonstrates that through scientific zoning and coordinated control, the impact of strong winds in complex terrain can be effectively countered, breaking the vicious cycle of performance degradation and significantly improving the operational safety and economy of direct air-cooled units.
[0040] According to another embodiment, the present invention provides a wind turbine group classification control device for a direct air-cooled power plant. Figure 2 A schematic block diagram of a wind turbine group classification control device for a direct air-cooled power plant according to one embodiment is shown. It will be understood that this device can be implemented by any device, equipment, platform, or cluster of equipment with computing and processing capabilities. Figure 2 As shown, the device includes: a sensitivity vector acquisition module 200, a wind turbine group classification module 202, and an operating frequency adjustment module 204. The main functions of each component are as follows: The sensitivity vector acquisition module obtains a sensitivity vector representing the degree of influence of the ambient wind on each wind turbine based on the simulation operating parameters of each wind turbine in the direct air-cooled power plant's wind turbine group under a preset ambient wind speed. The wind turbine group classification module is connected to the sensitivity vector acquisition module. Based on the sensitivity vector of each wind turbine, it classifies the wind turbine group in the direct air-cooled power plant to obtain a preset number of target classifications. The operating frequency adjustment module, connected to the wind turbine group classification module, adjusts the operating frequency of all wind turbines in each target category based on the different degrees of influence of environmental wind on each target category, so that the operating frequency of all wind turbines in each target category is consistent, and the target categories show a decreasing trend in the order of the degree of influence of environmental wind from the most severe to the least severe, so as to classify and control the wind turbine group in the air-cooled power plant.
[0041] As a preferred embodiment, the step of obtaining a sensitivity vector representing the degree of influence of ambient wind on each wind turbine based on the simulation operating parameters of each wind turbine in the direct air-cooled power plant under a preset ambient wind speed includes: The preset ambient wind speed is input into the simulation model of the direct air-cooled power plant to obtain the simulation operating parameters of each wind turbine output by the simulation model. Based on the simulation operating parameters and the baseline operating parameters under windless conditions, the sensitivity vector of each wind turbine is obtained using the following formula:
[0042] in, For the first The sensitivity vector of the typhoon generator. , For the first The first typhoon machine Simulation running parameters, For the first The first typhoon machine Reference operating parameters, This represents the total number of running parameters.
[0043] As a preferred embodiment, the classification of the wind turbine group within the direct air-cooled power plant based on the sensitivity vector of each wind turbine to obtain a preset number of target classifications includes: Based on the sensitivity vector of each wind turbine, the similarity between any two wind turbines is obtained; Each wind turbine is used as an initial target category, and the inter-class distance between any two target categories is calculated. The two target classifications with the smallest inter-class distance are merged to obtain a new target classification; Repeat the steps from calculating the inter-class distance between every two target categories to merging the two target categories with the smallest inter-class distance to obtain a new target category, until all wind turbines are assigned to a preset number of target categories.
[0044] As a preferred implementation, the similarity between any two wind turbines is obtained using the following formula:
[0045] in, To determine the similarity between the two wind turbines, and These are the sensitivity vectors for the two wind turbines, respectively. and The first of the two wind turbines The difference between the simulation parameters and the baseline parameters. This represents the total number of running parameters.
[0046] As a preferred implementation, the inter-class distance between every two target classifications is calculated using the following formula:
[0047] in, For inter-class distance, and They are two target classifications, Classify the target The number of medium-sized wind turbines Classify the target The center point, Classify the target The number of medium-sized wind turbines Classify the target The center point.
[0048] As a preferred implementation, the operating frequency of all wind turbines in each target category is adjusted using the following formula:
[0049] in, For the first The operating frequency of wind turbines in each target category is ranked as follows: All target categories are numbered in descending order of the degree of influence from environmental wind. , , The preset base frequency, .
[0050] As a preferred embodiment, the simulation operating parameters of the wind turbine are standardized using the following formula:
[0051] in, For the first The first typhoon machine Simulation running parameters, For the first The first typhoon machine The initial values of the simulation parameters. For all wind turbines The average initial values of the simulation parameters. For all wind turbines The standard deviation of the initial values of the simulation parameters.
[0052] According to another embodiment, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed in a computer, causes the computer to perform a combination Figure 1 The method described.
[0053] According to another embodiment, an electronic device is also provided, including a memory and a processor, wherein executable code is stored in the memory, and when the processor executes the executable code, it implements a combination... Figure 1 The method.
[0054] The various embodiments in this invention are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.
[0055] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in this invention can be implemented using hardware, software, firmware, or any combination thereof. When implemented in software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium.
[0056] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solution of the present invention should be included within the scope of protection of the present invention.
Claims
1. A method for classifying and controlling a group of wind turbines in a direct air-cooled power plant, characterized in that, include: Based on the simulated operating parameters of each wind turbine in the direct air-cooled power plant group under a preset ambient wind speed, a sensitivity vector is obtained to represent the degree of influence of ambient wind on each wind turbine. Based on the sensitivity vector of each wind turbine, the wind turbine group in the direct air-cooled power plant is classified to obtain a preset number of target classifications. Based on the different degrees to which each target category is affected by environmental wind, the operating frequency of all wind turbines in each target category is adjusted to make the operating frequency of all wind turbines in each target category consistent, and the target categories show a decreasing trend in the order of the degree of influence of environmental wind from the most severe to the least severe, so as to classify and control the wind turbine group in the air-cooled power plant.
2. The method according to claim 1, characterized in that, The sensitivity vector obtained based on the simulation operating parameters of each wind turbine in the direct air-cooled power plant under a preset ambient wind speed, representing the degree of influence of ambient wind on each wind turbine, includes: The preset ambient wind speed is input into the simulation model of the direct air-cooled power plant to obtain the simulation operating parameters of each wind turbine output by the simulation model. Based on the simulation operating parameters and the baseline operating parameters under windless conditions, the sensitivity vector of each wind turbine is obtained using the following formula: in, For the first The sensitivity vector of the typhoon generator. , For the first The first typhoon machine Simulation running parameters, For the first The first typhoon machine Reference operating parameters, This represents the total number of running parameters.
3. The method according to claim 2, characterized in that, The classification process, based on the sensitivity vector of each wind turbine, is performed on the wind turbine group within the direct air-cooled power plant to obtain a preset number of target classifications, including: Based on the sensitivity vector of each wind turbine, the similarity between any two wind turbines is obtained; Each wind turbine is used as an initial target category, and the inter-class distance between any two target categories is calculated. The two target classifications with the smallest inter-class distance are merged to obtain a new target classification; Repeat the steps from calculating the inter-class distance between every two target categories to merging the two target categories with the smallest inter-class distance to obtain a new target category, until all wind turbines are assigned to a preset number of target categories.
4. The method according to claim 3, characterized in that, The similarity between any two wind turbines can be obtained using the following formula: in, To determine the similarity between the two wind turbines, and These are the sensitivity vectors for the two wind turbines, respectively. and The first of the two wind turbines The difference between the simulation parameters and the baseline parameters. This represents the total number of running parameters.
5. The method according to claim 3, characterized in that, The inter-class distance between any two target categories is calculated using the following formula: in, For inter-class distance, and They are two target classifications, Classify the target The number of medium-sized wind turbines Classify the target The center point, Classify the target The number of medium-sized wind turbines Classify the target The center point.
6. The method according to claim 1, characterized in that, The operating frequency of all wind turbines in each target category is adjusted using the following formula: in, For the first The operating frequency of wind turbines in each target category is ranked as follows: All target categories are numbered in descending order of the degree of influence from environmental wind. , , The preset base frequency, .
7. The method according to claim 1, characterized in that, The method further includes: The simulation operating parameters of the wind turbine are standardized using the following formula: in, For the first The first typhoon machine Simulation running parameters, For the first The first typhoon machine The initial values of the simulation parameters. For all wind turbines The average initial values of the simulation parameters. For all wind turbines The standard deviation of the initial values of the simulation parameters.
8. A wind turbine group classification control device for a direct air-cooled power plant, characterized in that, include: The sensitivity vector acquisition module obtains a sensitivity vector representing the degree of influence of the ambient wind on each wind turbine based on the simulation operating parameters of each wind turbine in the direct air-cooled power plant's wind turbine group under a preset ambient wind speed. The wind turbine group classification module is connected to the sensitivity vector acquisition module. Based on the sensitivity vector of each wind turbine, it classifies the wind turbine group in the direct air-cooled power plant to obtain a preset number of target classifications. The operating frequency adjustment module, connected to the wind turbine group classification module, adjusts the operating frequency of all wind turbines in each target category based on the different degrees of influence of environmental wind on each target category, so that the operating frequency of all wind turbines in each target category is consistent, and the target categories show a decreasing trend in the order of the degree of influence of environmental wind from the most severe to the least severe, so as to classify and control the wind turbine group in the air-cooled power plant.
9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor, when executing the computer program, implements the method as described in any one of claims 1-7.
10. A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the method of any one of claims 1-7.