An intelligent inspection system for fan power generation optimized based on multiple scenarios

Abstract

The present invention belongs to the field of intelligent inspection of wind turbine power generation, and relates to data analysis technology. It is used to solve the problem that the existing wind turbine power generation inspection system cannot combine multiple technical means to ensure the inspection effect and efficiency. Specifically, it is an intelligent inspection system for wind turbine power generation based on multi-scenario optimization, including a wind turbine scale analysis module, an inspection mode analysis module, an inspection mode evaluation module, and an inspection optimization module. The wind turbine scale analysis module, the inspection mode analysis module, the inspection mode evaluation module, and the inspection optimization module are sequentially connected for communication; the wind turbine scale analysis module is used to analyze the scale level of the inspection object, and different inspection modes are adopted for different scale levels. The inspection mode evaluation module is used to evaluate the effect after the inspection is completed, and the inspection optimization module is used to optimize the inspection efficiency; by adopting different inspection modes according to the scale level of the inspection object, the inspection effect is ensured to meet the requirements and the inspection efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent inspection of wind turbine power generation, relates to data analysis technology, and specifically is an intelligent inspection system for wind turbine power generation based on multi-scenario optimization. Background Art

[0002] Under the background of today's energy transformation, wind turbine power generation, as a renewable energy production method, is playing an increasingly important role. Compared with other new energies, wind energy has outstanding advantages such as safety, cleanliness, local availability, and inexhaustibility. In recent years, the wind power generation in China has been increasing year by year.

[0003] Existing wind turbine power generation inspection systems often inspect wind turbines through a single technical means. For the differences in the scale of wind turbines in different wind turbine power generation scenarios, they cannot adopt a combination of multiple technical means to ensure the inspection effect, nor can they optimize the efficiency while ensuring the effect.

[0004] In view of the above technical problems, this application proposes a solution. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent inspection system for wind turbine power generation based on multi-scenario optimization, which is used to solve the problem that the existing wind turbine power generation inspection systems cannot adopt a combination of multiple technical means to ensure the inspection effect and efficiency for the differences in the scale of wind turbines in different wind turbine power generation scenarios;

[0006] The technical problem that the present invention needs to solve is: how to provide an intelligent inspection system for wind turbine power generation based on multi-scenario optimization that can adopt a combination of multiple technical means to ensure the inspection effect and efficiency.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] An intelligent inspection system for wind turbine power generation based on multi-scenario optimization includes a wind turbine scale analysis module, an inspection mode analysis module, an inspection mode evaluation module, and an inspection optimization module; the wind turbine scale analysis module, the inspection mode analysis module, the inspection mode evaluation module, and the inspection optimization module are sequentially communicatively connected;

[0009] The wind turbine scale analysis module is used to analyze the scale level of a wind farm: mark the wind farm as an inspection object, obtain the blade length YC of the wind turbines in the inspection object, the number of wind turbines SL, and the site area MJ, and perform numerical calculations to obtain the scale coefficient GM of the inspection object. According to the scale coefficient GM, the inspection object is respectively marked as a first-level scale object, a second-level scale object, and a third-level scale object;

[0010] The inspection mode analysis module is used to analyze the inspection mode according to the scale level of the inspection object: generate an inspection cycle with a non-fixed duration, conduct periodic inspections on the inspection object, and the implementation methods of the inspections include Measure A, Measure B, Measure C, and Measure D; the inspection modes include an effectiveness mode, a hybrid mode, and an economy mode; the first-level scale objects adopt the effectiveness mode, the second-level scale objects adopt the hybrid mode, and the third-level scale objects adopt the economy mode;

[0011] The inspection mode evaluation module is used to evaluate the effectiveness after the inspection is completed: after all the fans in the inspection object have completed the inspection, obtain the single-unit inspection duration SC, the inspection problem discovery rate FX, and the power generation non-conformity rate BH, and perform numerical calculations to obtain the effectiveness coefficient XG of the inspection object, determine whether the inspection mode adopted by the inspection object meets the requirements according to the effectiveness coefficient XG, and upgrade the inspection mode that does not meet the requirements;

[0012] The inspection optimization module is used to optimize the inspection of the inspection object whose inspection mode meets the requirements: determine whether the efficiency of the inspection mode meets the requirements through the single-unit inspection duration SC, and perform efficiency optimization analysis on the inspection mode that does not meet the requirements.

[0013] Furthermore, the process of obtaining the fan blade length YC includes: marking the distance from the tip to the center position of the root of the fan blade as the single-blade length, and marking the average value of the single-blade lengths of all the fans in the inspection object as the fan blade length YC; the process of obtaining the site area MJ includes: determining the coordinates of each fan on the map through satellite signals, plotting points on the map according to the coordinates, connecting any two of the coordinate points to form several convex polygons, and when there are no coordinate points outside the convex polygon, it is the largest convex polygon, and marking the actual area corresponding to the area of the largest convex polygon on the map as the site area MJ.

[0014] Furthermore, the process of classifying the scale level of the inspection object specifically includes: performing numerical calculations on the fan blade length YC, the number of fans SL, and the site area MJ to obtain the scale coefficient GM of the inspection object; comparing the scale coefficient GM of the inspection object with the preset scale high value GMmax and scale low value GMmin to classify the scale level of the inspection object: if the scale coefficient GM is greater than or equal to the scale high value GMmax, then mark this inspection object as a first-level scale object; if the scale coefficient GM is less than the scale high value GMmax and greater than or equal to the scale low value GMmin, then mark this inspection object as a second-level scale object; if the scale coefficient GM is less than the scale low value GMmin, then mark this inspection object as a third-level scale object.

[0015] Furthermore, the implementation methods of the inspection tour specifically include: Measure A is to collect the operating status of the internal equipment of the fan in real time using temperature sensors and vibration sensors; Measure B is to conduct aerial inspections of the fan at different heights and angles using a drone equipped with a high-definition camera and an infrared thermal imager; Measure C is to use an intelligent robot carrying sensors to inspect the internal equipment structure and line connections of the fan along a predetermined route; Measure D is for the inspection personnel to carry inspection equipment to check the blades, tower barrels, and internal equipment of the fan in turn.

[0016] Furthermore, the implementation methods adopted by different inspection tour modes specifically include: The measure combination adopted when inspecting objects of the first-level scale using the effect mode is Measure A + Measure B + Measure C; The measure combination adopted when inspecting objects of the second-level scale using the hybrid mode is Measure A + Measure B; The measure combination adopted when inspecting objects of the third-level scale using the economic mode is Measure A + Measure D.

[0017] Furthermore, the specific process of evaluating the effect of the inspection tour mode includes: The single-machine inspection tour duration SC is the ratio of the inspection tour duration after all fans have been inspected to the number of fans SL. The process of obtaining the inspection problem discovery rate FX includes: Mark the total number of problems found in the inspection tour history as the number of problems WT. After each inspection, the value of the inspection tour times XJ is incremented by 1. Numerical calculations are performed on the number of problems WT, the inspection tour times XJ, and the number of fans SL to obtain the inspection problem discovery rate; The process of obtaining the power generation non-conformance rate BH includes: Mark the total number of fans with power generation not meeting the theoretical requirements in the inspection tour history as the number of power generation non-compliance FW. Numerical calculations are performed on the number of power generation non-compliance FW, the total number of inspections XJ, and the number of fans SL to obtain the power generation non-conformance rate BH; Numerical calculations are performed on the inspection problem discovery rate FX and the power generation non-conformance rate BH to obtain the inspection effect coefficient XG of the inspection tour unit adopting this inspection tour mode; Compare the inspection effect coefficient XG with the preset inspection effect threshold XGmax: If the inspection effect coefficient XG is greater than or equal to the inspection effect threshold XGmax, it is determined that the inspection tour mode adopted by this inspection object meets the requirements, and the single-machine inspection tour duration SC of the inspection object is sent to the inspection tour optimization module; If the inspection effect coefficient XG is less than the inspection effect threshold XGmax, it is determined that the inspection tour mode adopted by this inspection object does not meet the requirements, and the inspection tour mode needs to be upgraded: If the inspection object adopts the economic mode, it is upgraded to the hybrid mode; If the inspection object adopts the hybrid mode, it is upgraded to the effect mode; If the inspection object adopts the effect mode, the inspection tour mode is upgraded through upgrade measures.

[0018] Further, the specific process of evaluating the efficiency of the inspection mode includes: comparing the single-machine inspection duration SC with the preset single-machine inspection duration threshold SCmax. If the single-machine inspection duration SC is less than the single-machine inspection duration threshold SCmax, it is determined that the efficiency of the inspection object adopting this inspection mode meets the requirements and no processing is required. If the single-machine inspection duration SC is greater than the single-machine inspection duration threshold SCmax, it is determined that the efficiency of the inspection object adopting this inspection mode does not meet the requirements, and efficiency optimization analysis is carried out.

[0019] Further, the specific process of efficiency optimization analysis includes: marking the time for moving between each fan during the drone inspection or manual inspection as the moving duration YD; numerically calculating the average value and standard deviation of all the moving durations YD to obtain the maximum allowable duration ZD; among the inspection objects, if the moving duration YD from a certain fan to other fans is greater than the maximum allowable duration ZD, then mark this fan as an optimized fan, and configure an independent drone or inspection personnel to inspect the optimized fan.

[0020] The present invention has the following beneficial effects:

[0021] By calculating and analyzing the blade length, the number of fans, and the site area of the wind farm, the scale coefficient is obtained, and thus the scale level of the wind farm is classified according to the scale coefficient, ensuring that the scale level of the wind farm in different power generation scenarios can be judged;

[0022] By adopting a variety of inspection technical means, different inspection modes are generated, and corresponding inspection modes are adopted for inspection objects of different scale levels, ensuring that inspection objects from large to small can adopt inspection modes with both effectiveness and efficiency;

[0023] By calculating and analyzing the inspection problem discovery rate and power generation unqualified rate after the inspection is completed, the effectiveness coefficient of the inspection object adopting the corresponding inspection mode is obtained, and thus the effectiveness of the inspection is evaluated according to the effectiveness coefficient, and the inspection mode of the inspection object that does not meet the effectiveness requirements is upgraded;

[0024] 4. By analyzing the single-machine inspection duration after the inspection is completed, the inspection objects with unqualified inspection efficiency are determined, and the optimized fans are found through efficiency optimization analysis for efficiency optimization, ensuring that the inspection efficiency is also improved on the premise that the inspection effectiveness meets the requirements. Brief Description of the Drawings

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0026] Figure 1 It is the system block diagram of the whole present invention. Detailed implementation manners

[0027] The following will clearly and completely describe the technical solutions of the present invention in combination with the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0028] As Figure 1 shown, an intelligent inspection system for wind turbine power generation based on multi-scenario optimization includes a wind turbine scale analysis module, an inspection mode analysis module, an inspection mode evaluation module, and an inspection optimization module; the wind turbine scale analysis module, the inspection mode analysis module, the inspection mode evaluation module, and the inspection optimization module are sequentially communicatively connected.

[0029] The fan scale analysis module is used to analyze the scale level of a wind farm: mark the wind farm as an inspection object, and obtain the fan blade length YC, the number of fans SL, and the site area MJ of the inspection object. Among them, the process of obtaining the fan blade length YC includes: marking the distance from the tip to the center position of the root of the fan blade as the single blade length, and marking the average value of the single blade lengths of all fans in the inspection object as the fan blade length YC. The process of obtaining the site area MJ includes: determining the coordinates of each fan on the map through satellite signals, and plotting points on the map according to the coordinates. Connect any two of the coordinate points to form several convex polygons. When there are no coordinate points outside the convex polygon, it is the largest convex polygon, and mark the actual area corresponding to the area of the largest convex polygon on the map as the site area MJ. Obtain the scale coefficient GM of the inspection object through the formula GM = k1 * SL + k2 * MJ + k3 * YC; where k1, k2, and k3 are all proportionality coefficients, and k1 > k2 > k3 > 1. Compare the scale coefficient GM of the inspection object with the preset scale high value GMmax and the scale low value GMmin, and classify the scale level of the inspection object: if the scale coefficient GM is greater than or equal to the scale high value GMmax, mark the inspection object as a first-level scale object; if the scale coefficient GM is less than the scale high value GMmax and greater than or equal to the scale low value GMmin, mark the inspection object as a second-level scale object; if the scale coefficient GM is less than the scale low value GMmin, mark the inspection object as a third-level scale object. Calculate and analyze the fan blade length, the number of fans, and the site area of the wind farm to obtain the scale coefficient, so as to classify the scale level of the wind farm according to the scale coefficient, ensuring that the scale level of wind farms in different power generation scenarios can be judged.

[0030] The inspection mode analysis module is used to analyze the inspection mode according to the scale level of the inspection object: generate an inspection cycle with a non-fixed duration, and conduct periodic inspections on the inspection object. The implementation means of the inspections include: Measure A, Measure B, Measure C, and Measure D; Measure A is to use temperature sensors and vibration sensors to collect the operating status of the internal equipment of the fan in real time; Measure B is to use an unmanned aerial vehicle equipped with a high-definition camera and an infrared thermal imager to conduct aerial inspections of the fan at different heights and angles; Measure C is to use an intelligent robot carrying sensors to inspect the internal equipment structure and line connections of the fan according to a predetermined route; Measure D is for inspection personnel to carry detection equipment to inspect the blades, the tower barrel, and the internal equipment of the fan in turn.

[0031] According to the different scale levels of the inspection objects, corresponding inspection modes are adopted: the inspection mode for first-level scale objects is the effectiveness mode, the inspection mode for second-level scale objects is the hybrid mode, and the inspection mode for third-level inspection objects is the economy mode; the measure combination adopted when using the effectiveness mode to inspect first-level scale objects is Measure A + Measure B + Measure C; the measure combination adopted when using the hybrid mode to inspect second-level scale objects is Measure A + Measure B; the measure combination adopted when using the economy mode to inspect third-level scale objects is Measure A + Measure D; by adopting a variety of inspection technical means, different inspection modes are generated, and corresponding inspection modes are adopted for inspection objects of different scale levels, ensuring that inspection objects from large to small can adopt inspection modes that combine effectiveness and efficiency.

[0032] The patrol inspection mode evaluation module is used to evaluate the effect after the completion of the patrol inspection: after all the fans in the patrol inspection object have completed the patrol inspection, obtain the single-machine patrol inspection duration SC, the patrol inspection problem discovery rate FX, and the power generation non-conformity rate BH; among them, the single-machine patrol inspection duration SC is the ratio of the patrol inspection duration after all the fans have completed the patrol inspection to the number of fans SL; the process of obtaining the patrol inspection problem discovery rate FX includes: marking the total number of problems found in the patrol inspection history as the number of problems WT, adding 1 to the value of the patrol inspection times XJ after each patrol inspection, and calculating the numerical values of the number of problems WT, the patrol inspection times XJ, and the number of fans SL through the formula FX = WT / (XJ * SL) to obtain the patrol inspection problem discovery rate; the process of obtaining the power generation non-conformity rate BH includes: marking the total number of fans with power generation not meeting the theoretical requirements in the patrol inspection history as the number of power generation non-compliance FW, and calculating the numerical values of the number of power generation non-compliance FW, the total number of patrol inspections XJ, and the number of fans SL through the formula BH = FW / (XJ * SL) to obtain the power generation non-conformity rate BH; obtain the patrol inspection effect coefficient XG of the patrol inspection unit adopting this patrol inspection mode through the formula XG = α1 * FX - α2 * BH; where α1 and α2 are both proportionality coefficients, and α1 > α2 > 1; compare the patrol inspection effect coefficient XG with the preset patrol inspection effect threshold XGmax: if the patrol inspection effect coefficient XG is greater than or equal to the patrol inspection effect threshold XGmax, it is judged that the patrol inspection mode adopted by the patrol inspection object meets the requirements, and the single-machine patrol inspection duration SC of the patrol inspection object is sent to the patrol inspection optimization module; if the patrol inspection effect coefficient XG is less than the patrol inspection effect threshold XGmax, it is judged that the patrol inspection mode adopted by the patrol inspection object does not meet the requirements, and the patrol inspection mode needs to be upgraded: if the patrol inspection object adopts the economic mode, it is upgraded to the hybrid mode; if the patrol inspection object adopts the hybrid mode, it is upgraded to the effect mode; if the patrol inspection object adopts the effect mode, the patrol inspection mode is upgraded through upgrade measures; the upgrade measures include increasing the number of drones, intelligent robots, sensors, increasing the patrol inspection frequency, and increasing the manual patrol inspection; by calculating and analyzing the patrol inspection problem discovery rate and the power generation non-conformity rate after the completion of the patrol inspection, the effect coefficient of the patrol inspection object adopting the corresponding patrol inspection mode is obtained, so as to evaluate the effect of the patrol inspection according to the effect coefficient and upgrade the patrol inspection mode of the patrol inspection object that does not meet the effect requirements.

[0033] The patrol inspection optimization module is used to optimize the patrol inspection efficiency of patrol inspection objects whose patrol inspection modes meet the requirements: compare the single - machine patrol inspection duration SC with the preset single - machine patrol inspection duration threshold SCmax. If the single - machine patrol inspection duration SC is less than the single - machine patrol inspection duration threshold SCmax, it is determined that the efficiency of the patrol inspection object adopting this patrol inspection mode meets the requirements and no processing is required. If the single - machine patrol inspection duration SC is greater than the single - machine patrol inspection duration threshold SCmax, it is determined that the efficiency of the patrol inspection object adopting this patrol inspection mode does not meet the requirements, and efficiency optimization analysis is carried out: mark the time spent moving between each fan during the drone patrol inspection or manual patrol inspection as the moving duration YD; calculate the average value and standard deviation of all moving durations YD to obtain the moving average duration YP and the moving duration standard deviation YB, and obtain the maximum allowable duration ZD through the formula ZD = YD + 2*YB. Among the patrol inspection objects, if the moving duration YD from a certain fan to other fans is greater than the maximum allowable duration ZD, mark this fan as an optimized fan, and configure an independent drone or patrol personnel to inspect the optimized fan. By analyzing the single - machine patrol inspection duration after the patrol inspection is completed, determine the patrol inspection objects whose patrol inspection efficiency does not meet the requirements, and find the optimized fans through efficiency optimization analysis for efficiency optimization, ensuring that the patrol inspection efficiency is improved on the premise that the patrol inspection effect meets the requirements.

[0034] A wind turbine power generation intelligent patrol inspection system based on multi - scenario optimization. During operation, mark the wind farm as the patrol inspection object, obtain the blade length YC of the fans, the number of fans SL, and the site area MJ of the patrol inspection object and perform numerical calculations to obtain the scale coefficient, and classify the scale level of the patrol inspection object according to the scale coefficient; generate multiple patrol inspection modes by combining various inspection technical means, and adopt corresponding patrol inspection modes according to different scale levels; after the patrol inspection is completed, calculate the patrol inspection problem discovery rate FX and the power generation non - compliance rate BH numerically to obtain the effect coefficient, and determine and upgrade the non - compliant patrol inspection modes according to the effect coefficient; finally, determine the patrol inspection efficiency of the patrol inspection modes whose patrol inspection effects meet the requirements according to the single - machine patrol inspection duration, and find the optimized fans through efficiency optimization analysis for efficiency optimization.

[0035] The above content is only an example and explanation of the structure of the present invention. Those skilled in the art of this technology can make various modifications, supplements, or use similar methods to replace the specific embodiments described, as long as they do not deviate from the structure of the invention or exceed the scope defined by this claim book, they should fall within the protection scope of the present invention.

[0036] The above formulas are all obtained by collecting a large amount of data for software simulation and selecting a formula close to the true value. The coefficients in the formula are set by those skilled in the art according to the actual situation. For example, the formula GM = k1*SL + k2*MJ + k3*YC; those skilled in the art collect multiple groups of sample data and set corresponding scale coefficients for each group of sample data; substitute the set scale coefficients and the collected sample data into the formula, and any three formulas form a system of linear equations with three variables. Screen the calculated coefficients and take the average value to obtain the values of k1, k2, and k3 as 3.39, 2.01, and 1.64 respectively.

[0037] The magnitude of the coefficient is a specific value obtained by quantifying each parameter, which is convenient for subsequent comparison. Regarding the magnitude of the coefficient, it depends on the amount of sample data and the scale coefficients initially set by those skilled in the art for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantified value, for example, the scale coefficient is directly proportional to the value of the number of fans.

[0038] In the description of this specification, the descriptions referring to terms such as "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0039] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not elaborate on all details and do not limit the present invention to only the specific implementation manners. Obviously, many modifications and variations can be made according to the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the present invention, so that those skilled in the art in the relevant technical field can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A wind turbine power generation intelligent inspection system based on multi-scenario optimization, including a wind turbine scale analysis module, an inspection mode analysis module, an inspection mode evaluation module and an inspection optimization module; The wind turbine scale analysis module, the inspection mode analysis module, the inspection mode evaluation module and the inspection optimization module are sequentially connected in communication, and are characterized by: The wind turbine scale analysis module is used to analyze the scale level of the wind farm: mark the wind farm as an inspection object, obtain the wind turbine blade length YC, the number of wind turbines SL and the site area MJ of the inspection object, and perform numerical calculation to obtain the scale coefficient GM of the inspection object, and mark the inspection object as a first-level scale object, a second-level scale object and a third-level scale object according to the scale coefficient GM; The inspection mode analysis module is used to analyze the inspection mode according to the scale level of the inspection object: generate an inspection cycle of non-fixed duration, perform periodic inspection on the inspection object, and the implementation methods of the inspection include measures A, measures B, measures C and measures D; the inspection mode includes effect mode, mixed mode and economic mode; the first-level scale object adopts the effect mode, the second-level scale object adopts the mixed mode, and the third-level scale object adopts the economic mode; The inspection mode evaluation module is used to evaluate the effect after the inspection is completed: after all wind turbines in the inspection object have completed the inspection, the single-machine inspection time SC, the inspection problem discovery rate FX and the power generation failure rate BH are obtained, and the effect coefficient XG of the inspection object is obtained by numerical calculation. According to the effect coefficient XG, it is determined whether the inspection mode adopted by the inspection object meets the requirements, and the inspection mode that does not meet the requirements is upgraded; The inspection optimization module is used to optimize the inspection efficiency of the inspection objects whose inspection modes meet the requirements: determine whether the efficiency of the inspection mode meets the requirements through the single-machine inspection duration SC, and perform efficiency optimization analysis on the inspection modes that do not meet the requirements; The specific implementation methods of the inspection include: Measure A is to use temperature sensors and vibration sensors to collect the operating status of the internal equipment of the wind turbine in real time; Measure B is to use drones equipped with high-definition cameras and infrared thermal imagers to conduct aerial inspections of the wind turbine at different heights and angles; Measure C is to use intelligent robots carrying sensors to inspect the equipment structure and line connections inside the wind turbine along a predetermined route; Measure D is for inspection personnel to carry detection equipment to inspect the blades, tower and internal equipment of the wind turbine in turn.

2. According to claim 1, a wind turbine power generation intelligent inspection system based on multi-scenario optimization is characterized in that: The process of obtaining the fan blade length YC includes: marking the distance from the tip of the fan blade to the center of the blade root as the single blade length, and marking the average value of the single blade lengths of all fans in the inspection object as the fan blade length YC; the process of obtaining the site area MJ includes: determining the coordinates of each fan on the map through satellite signals, and drawing points on the map according to the coordinates, connecting any two of the coordinate points to form a number of convex polygons, then the convex polygon is the largest convex polygon when there is no coordinate point outside, and the actual area corresponding to the area of ​​the largest convex polygon on the map is marked as the site area MJ.

3. According to claim 2, a wind turbine power generation intelligent inspection system based on multi-scenario optimization is characterized in that: The process of grading the scale level of the inspection object specifically includes: performing numerical calculations on the fan blade length YC, the number of fans SL and the site area MJ to obtain the scale coefficient GM of the inspection object; comparing the scale coefficient GM of the inspection object with the preset high scale value GMmax and low scale value GMmin, and grading the scale level of the inspection object: if the scale coefficient GM is greater than or equal to the high scale value GMmax, the inspection object is marked as a first-level scale object; if the scale coefficient GM is less than the high scale value GMmax and greater than or equal to the low scale value GMmin, the inspection object is marked as a second-level scale object; if the scale coefficient GM is less than the low scale value GMmin, the inspection object is marked as a third-level scale object.

4. The wind turbine power generation intelligent inspection system based on multi-scenario optimization according to claim 3 is characterized in that: The implementation methods adopted by different inspection modes specifically include: when the effect mode is used to inspect the first-level scale objects, the combination of measures adopted is measure A + measure B + measure C; when the mixed mode is used to inspect the second-level scale objects, the combination of measures adopted is measure A + measure B; when the economic mode is used to inspect the third-level scale objects, the combination of measures adopted is measure A + measure D.

5. The wind turbine power generation intelligent inspection system based on multi-scenario optimization according to claim 4 is characterized in that: The specific process of evaluating the effectiveness of the inspection mode includes: the single-machine inspection time SC is the ratio of the inspection time after all wind turbines have completed the inspection to the number of wind turbines SL; the process of obtaining the inspection problem detection rate FX includes: marking the total number of problems found in the inspection history records as the number of problems WT, adding 1 to the number of inspections XJ after each inspection, and numerically calculating the number of problems WT, the number of inspections XJ and the number of wind turbines SL to obtain the inspection problem detection rate; the process of obtaining the power generation failure rate BH includes: marking the total number of wind turbines whose power generation does not meet the theoretical requirements in the inspection history records as the power generation failure number FW, and numerically calculating the power generation failure number FW, the total number of inspections XJ and the number of wind turbines SL to obtain the power generation failure rate BH; the inspection problem detection rate FX and the power generation failure rate BH are compared. Perform numerical calculation to obtain the inspection effect coefficient XG of the inspection mode adopted by the inspection unit; compare the inspection effect coefficient XG with the preset inspection effect threshold XGmax: if the inspection effect coefficient XG is greater than or equal to the inspection effect threshold XGmax, then it is judged that the inspection mode adopted by the inspection object meets the requirements, and the single-machine inspection duration SC of the inspection object is sent to the inspection optimization module; if the inspection effect coefficient XG is less than the inspection effect threshold XGmax, then it is judged that the inspection mode adopted by the inspection object does not meet the requirements, and the inspection mode needs to be upgraded: if the inspection object adopts the economic mode, it is upgraded to the mixed mode; if the inspection object adopts the mixed mode, it is upgraded to the effect mode; if the inspection object adopts the effect mode, the inspection mode is upgraded through upgrade measures.

6. The wind turbine power generation intelligent inspection system based on multi-scenario optimization according to claim 5 is characterized in that: The specific process of evaluating the efficiency of the inspection mode includes: comparing the single-machine inspection time SC with the preset single-machine inspection time threshold SCmax: if the single-machine inspection time SC is less than the single-machine inspection time threshold SCmax, it is judged that the efficiency of the inspection object adopting this inspection mode meets the requirements and no processing is required; if the single-machine inspection time SC is greater than the single-machine inspection time threshold SCmax, it is judged that the efficiency of the inspection object adopting this inspection mode does not meet the requirements, and efficiency optimization analysis is performed.

7. The wind turbine power generation intelligent inspection system based on multi-scenario optimization according to claim 6 is characterized in that: The specific process of efficiency optimization analysis includes: marking the time of movement between each wind turbine during drone inspection or manual inspection as movement time YD; numerically calculating the average value and standard deviation of all movement time YD to obtain the maximum allowable time ZD; among the inspection objects, if the movement time YD from a certain wind turbine to other wind turbines is greater than the maximum allowable time ZD, then the wind turbine is marked as the optimized wind turbine, and an independent drone or inspection personnel is configured to inspect the optimized wind turbine.

Images