Power generation equipment detection method and system based on large model

Abstract

The application relates to a power generation equipment detection method and system based on a large model, which comprises the following steps: generating a power generation equipment detection task and an equipment detection time period in sequence through a preset power generation detection large model, selecting a power generation equipment detection personnel, setting a test detection task, and acquiring real-time environment sensing data; an estimated environment interference value of a target detection area in the equipment detection time period is generated according to the real-time environment sensing data; it is judged whether the estimated environment interference value is greater than or equal to a preset environment interference safety threshold value; if the judgment is yes, a detection task correction instruction is generated, and the power generation equipment detection personnel is prompted to adjust the detection time according to the detection task correction instruction. The application realizes the judgment of detection interference based on the actual environment, thereby improving the safety and feasibility of the detection task execution, and realizing efficient and high-safety power generation equipment maintenance.

Description

Technical Field

[0001] This application relates to the field of power generation equipment testing technology, and in particular to a power generation equipment testing method and system based on a large model. Background Technology

[0002] Power generation equipment refers to mechanical and electrical equipment used to convert various forms of energy into electrical energy. This equipment can be based on multiple energy types, such as fossil fuels, nuclear power, hydropower, wind power, solar power, and other renewable energy sources. Equipment that uses wind energy to generate electricity is called wind power generation equipment.

[0003] The inspection and maintenance of wind power generation equipment during use is extremely important. Regarding the inspection and maintenance of wind power equipment, an invention patent with publication number CN118428931A was published on August 2, 2024, specifically disclosing a method, system, equipment, and medium for wind power equipment inspection and maintenance, relating to the field of wind power technology. The system includes: an unplanned maintenance module for collecting and centrally managing defect tasks; a planned maintenance module for developing different maintenance projects and performing regular maintenance on equipment according to preset time cycles; an equipment change management module for initiating equipment change applications and determining different degrees of equipment change for corresponding approval processes; a maintenance knowledge base module for establishing a maintenance knowledge base and training a question-and-answer model based on data in the maintenance knowledge base to generate a question-and-answer robot to provide corresponding fault handling measures; and a scheduling module for calculating the priority order of tasks in the task pool using preset influence factors, and then setting corresponding task execution times.

[0004] The technical solution in the aforementioned patent document mainly achieves intelligent maintenance of wind power by detecting various data and based on multi-dimensional data. However, it still has some drawbacks. Specifically, it does not take into account that wind power equipment is mostly located outdoors and needs to be climbed during maintenance. If the interference caused by the environment is ignored, it may affect the maintenance and testing process and efficiency of the equipment, or even lead to safety issues. Summary of the Invention

[0005] Therefore, it is necessary to provide a method and system for detecting power generation equipment based on a large model that can make judgments on interference based on the actual environment, thereby improving the safety and feasibility of the detection task and realizing high efficiency and high security.

[0006] The technical solution of this invention is as follows:

[0007] A method for detecting power generation equipment based on a large model, the method comprising:

[0008] Based on a pre-set large-scale power generation detection model, the system generates power generation equipment detection tasks and equipment detection time periods according to the historical power generation operation data of the power generation equipment to be detected, and selects power generation equipment detection personnel according to the power generation equipment detection tasks.

[0009] The test and inspection task is set according to the power generation equipment inspection task and the power generation equipment to be inspected, and the real-time environmental sensing data collected by the power generation equipment inspection personnel when performing the test and inspection task in the target inspection area is obtained, wherein the target inspection area is the area where the power generation equipment to be inspected is located;

[0010] Based on the real-time environmental sensing data, an estimated environmental interference value for the target detection area is generated during the equipment detection time period. The estimated environmental interference value is used to represent the degree of interference of the external environment on the maintenance personnel of the power generation equipment during the equipment detection time period.

[0011] Determine whether the estimated environmental interference value is greater than or equal to the preset environmental interference safety threshold. If the determination is yes, generate a detection task correction instruction and prompt the power generation equipment inspection personnel to adjust the inspection time according to the detection task correction instruction.

[0012] Optionally, a test and inspection task is set according to the power generation equipment testing task and the power generation equipment to be tested, including:

[0013] The power generation components to be tested and the estimated testing duration are obtained based on the power generation equipment testing task.

[0014] A detection task execution path is generated based on the basic equipment structure of the power generation component to be tested and the equipment to be tested, wherein the detection task execution path includes multiple equipment detection path points;

[0015] A device test and detection area is generated based on the device detection path points, wherein one device detection path point corresponds to one device test and detection area;

[0016] Obtain the data collection category corresponding to each of the device detection path points, and set the test detection branch task according to the data collection category and the device test detection area, wherein one device test detection area corresponds to one test detection branch task.

[0017] Optionally, the equipment testing and detection area includes the nacelle exit area, the nacelle top dwell area, and the blade body area; the real-time environmental sensing data includes nacelle exit sensing data, nacelle top sensing data, and blade body sensing data.

[0018] Based on the real-time environmental sensing data, an estimated environmental interference value for the target detection area is generated within the device's detection time period, including:

[0019] Wind speed sensing information, temperature sensing information, and visibility sensing score are extracted from the sensor data at the nacelle exit. The visibility sensing score is a score set by the power generation equipment inspector based on the visibility outside the nacelle exit.

[0020] The average wind speed inside and outside the cabin is extracted based on the wind speed sensing information, and the real-time sensing temperature at the cabin exit at each data acquisition time point is extracted based on the temperature sensing information, as well as the maximum and minimum sensing temperatures among the real-time sensing temperatures, wherein the number of real-time sensing temperatures is n.

[0021] The real-time protective equipment of the personnel inspecting the power generation equipment is obtained, and a real-time suitable temperature is generated based on the real-time protective equipment, wherein the real-time suitable temperature is set based on the thickness of the real-time protective equipment of the personnel inspecting the power generation equipment.

[0022] The cabin exit interference value is generated based on the average wind speed, the average wind speed outside the cabin, the real-time sensed temperature, the maximum sensed temperature, the minimum sensed temperature, and the real-time suitable temperature.

[0023] The top dust accumulation information, top slope information, and top wind speed information are obtained from the sensing data at the top of the cabin, and the top interference value of the cabin is generated based on the top dust accumulation information, top slope information, and top wind speed information.

[0024] The blade wind speed information is extracted from the main body sensing data of the blade, and the blade environmental interference value is generated based on the blade wind speed information;

[0025] Obtain the estimated weather data for the device detection period, and generate an environmental difference coefficient based on the difference between the estimated weather data and the test detection weather data, wherein the test detection weather data is the weather data when the test detection task is performed;

[0026] Based on the nacelle exit disturbance value Dr, the nacelle top disturbance value Dc, the blade environmental disturbance value Db, and the environmental difference coefficient Ce, the estimated environmental disturbance value EDs is generated using the following formula:

[0027] EDs = Ce(Dr + Dc + Db);

[0028] Wherein, EDs is the estimated environmental disturbance value, Ce is the environmental difference coefficient, Dr is the nacelle outlet disturbance value, Dc is the nacelle top disturbance value, and Db is the blade environmental disturbance value.

[0029] Optionally, the cabin exit interference value is generated based on the following formula:

[0030]

[0031] Where Dr is the cabin exit interference value, β1 is the hatch interference coefficient, Vout is the average wind speed outside the cabin, Vin is the average wind speed inside the cabin, Vs is the standard wind speed difference, β2 is the temperature interference coefficient, α1 is the first temperature interference coefficient, Ti is the i-th real-time sensing temperature, Ts is the real-time suitable temperature, α2 is the second temperature interference coefficient, Tmax is the maximum sensing temperature, Tmin is the minimum sensing temperature, and Vb is the visibility sensing score.

[0032] Optionally, the nacelle top interference value is generated based on the top dust accumulation information, top slope information, and top wind speed information, including:

[0033] Based on the dust accumulation information at the top, the estimated dust thickness and the humidity of the top surface are extracted, and the estimated walking slope is generated based on the top slope information.

[0034] Based on the top wind speed information, extract the top real-time wind speed at each data collection time point, generate the top average wind speed based on each top real-time wind speed, and generate the wind disturbance coefficient based on the top average wind speed.

[0035] Based on the estimated dust accumulation thickness, top surface humidity, estimated travel slope, and wind disturbance coefficient, the nacelle top disturbance value is generated using the following formula:

[0036]

[0037] Where Dc is the disturbance value at the top of the cabin, δ is the wind disturbance coefficient, Th is the estimated dust accumulation thickness, Ths is the preset safe dust accumulation thickness, Hu is the humidity of the top surface, Hus is the preset safe surface humidity, and Sp is the estimated walking slope.

[0038] Optionally, a power generation equipment testing system based on a large model, the system comprising:

[0039] The maintenance task setting module is used to generate power equipment inspection tasks and equipment inspection time periods based on a preset power generation inspection model and the historical power generation operation data of the power equipment to be inspected, and to select power equipment inspection personnel according to the power equipment inspection tasks.

[0040] The real-time data sensing module is used to set test and inspection tasks according to the power generation equipment inspection task and the power generation equipment to be inspected, and to acquire real-time environmental sensing data collected by the power generation equipment inspector when performing the test and inspection task in the target inspection area, wherein the target inspection area is the area where the power generation equipment to be inspected is located;

[0041] An interference data generation module is used to generate an estimated environmental interference value for the target detection area during the equipment detection time period based on the real-time environmental sensing data. The estimated environmental interference value is used to represent the degree of interference of the external environment to the maintenance personnel of the power generation equipment during the equipment detection time period.

[0042] The detection task execution module is used to determine whether the estimated environmental interference value is greater than or equal to the preset environmental interference safety threshold. If the determination is yes, a detection task correction instruction is generated, and the power generation equipment inspection personnel are prompted to adjust the detection time according to the detection task correction instruction.

[0043] Optionally, the real-time data sensing module is further configured to:

[0044] The power generation component to be tested and the estimated testing duration are obtained according to the power generation equipment testing task; a testing task execution path is generated according to the power generation component to be tested and the basic equipment structure of the equipment to be tested, wherein the testing task execution path includes multiple equipment testing path points; an equipment testing area is generated according to the equipment testing path points, wherein one equipment testing path point corresponds to one equipment testing area; the data acquisition category corresponding to each equipment testing path point is obtained, and a testing branch task is set according to the data acquisition category and the equipment testing area, wherein one equipment testing area corresponds to one testing branch task.

[0045] Optionally, the equipment testing and detection area includes the nacelle exit area, the nacelle top dwell area, and the blade body area; the real-time environmental sensing data includes nacelle exit sensing data, nacelle top sensing data, and blade body sensing data; the interference data generation module is further used for:

[0046] Wind speed sensing information, temperature sensing information, and visibility sensing score are extracted from the sensor data at the engine room exit. The visibility sensing score is a score set by the power equipment inspector based on the visibility outside the engine room exit. The average wind speed inside and outside the engine room is extracted from the wind speed sensing information. The real-time sensed temperature at the engine room exit at each data acquisition time point, as well as the maximum and minimum sensed temperatures among these real-time sensed temperatures, are extracted from the temperature sensing information. The number of real-time sensed temperatures is n. The real-time protective equipment of the power equipment inspector is obtained, and a real-time suitable temperature is generated based on the real-time protective equipment. The real-time suitable temperature is based on the real-time protective equipment of the power equipment inspector. The thickness of the equipment is set according to the following: The nacelle outlet interference value is generated based on the average wind speed, average wind speed outside the nacelle, real-time sensed temperature, maximum sensed temperature, minimum sensed temperature, and real-time suitable temperature; Nacelle top interference value is generated from the top dust accumulation information, top slope information, and top wind speed information in the top sensed data of the nacelle; Blade wind speed information is extracted from the blade body sensed data, and blade environmental interference value is generated based on the blade wind speed information; Estimated weather data for the equipment detection period is obtained, and an environmental difference coefficient is generated based on the difference between the estimated weather data and the test detection weather data, wherein the test detection weather data is the weather data during the execution of the test detection task;

[0047] Based on the nacelle exit disturbance value Dr, the nacelle top disturbance value Dc, the blade environmental disturbance value Db, and the environmental difference coefficient Ce, the estimated environmental disturbance value EDs is generated using the following formula:

[0048] EDs = Ce(Dr + Dc + Db);

[0049] Wherein, EDs is the estimated environmental disturbance value, Ce is the environmental difference coefficient, Dr is the nacelle outlet disturbance value, Dc is the nacelle top disturbance value, and Db is the blade environmental disturbance value.

[0050] Optionally, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps described in the above-described method for detecting power generation equipment based on a large model.

[0051] Optionally, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the steps described in the above-described method for detecting power generation equipment based on a large model.

[0052] The technical effects achieved by this invention are as follows:

[0053] The aforementioned power generation equipment inspection method and system based on a large model sequentially generate inspection tasks and inspection time periods based on historical power generation operation data of the power generation equipment to be inspected, using a preset large model for power generation inspection. The system then selects inspection personnel based on the inspection tasks. Next, it sets up test inspection tasks based on the inspection tasks and the power generation equipment to be inspected, and acquires real-time environmental sensing data collected by the inspection personnel while performing the test inspection tasks in the target inspection area, where the target inspection area is the area where the power generation equipment to be inspected is located. Based on the real-time environmental sensing data, it generates an estimated environmental interference value for the target inspection area within the equipment inspection time period, where the estimated environmental interference value represents the degree of interference from the external environment to the power generation equipment maintenance personnel during the equipment inspection time period. Finally, it determines whether the estimated environmental interference value is greater than or equal to a preset environmental interference safety threshold. If the determination is yes, it generates an inspection task correction instruction and prompts the inspection personnel to adjust the inspection time based on the inspection task correction instruction. When it is necessary to inspect the power generation equipment to be tested, this invention no longer adopts the previous fixed-time period maintenance mode, but instead adopts targeted maintenance after analyzing the operating data. Specifically, it first obtains the historical power generation operation data of the power generation equipment to be tested, and then generates the power generation equipment inspection task and equipment inspection time period based on the historical power generation operation data through a preset power generation inspection big model. This realizes the operation data analysis based on the big model, and at the same time achieves high-efficiency generation of power generation equipment inspection tasks and equipment inspection time periods. After the equipment inspection time period is set, the power generation equipment inspection task needs to be executed within the equipment inspection time period.Next, to ensure suitable testing personnel can be found for the power generation equipment testing task, testing personnel are selected based on the power generation equipment testing task. Then, to consider the actual testing environment and the actual environment encountered during the execution of the task, a testing task is first set based on the power generation equipment testing task and the power generation equipment to be tested. Real-time environmental sensing data is then acquired by the testing personnel while performing the testing task in the target testing area. This real-time detection data is the data collected by the testing personnel during the testing process. This data accurately reflects the environmental data faced by the power generation equipment under testing at the current stage. Based on this data, analysis can be performed on subsequent complete testing. To assess the safety of the power generation equipment inspection task, and to further analyze the environment during the task execution period, an estimated environmental interference value for the target inspection area is generated based on real-time environmental sensing data. This estimated environmental interference value represents the degree of interference from the external environment to the power generation equipment maintenance personnel during the inspection period. The system then determines whether the estimated environmental interference value is greater than or equal to a preset environmental interference safety threshold. If the threshold is not exceeded, it indicates that the interference will not affect the execution of the inspection task. In this case, a maintenance task execution instruction is generated, instructing the maintenance personnel to perform equipment maintenance within the specified maintenance period. If the threshold is exceeded, it indicates that the environmental interference encountered during the planned maintenance is too strong, potentially posing a safety risk. In this case, a inspection task correction instruction is generated, prompting the power generation equipment inspection personnel to adjust the inspection time. Therefore, this invention first sets up the detection task through a large-scale power generation detection model to improve detection efficiency and accuracy. Then, it conducts detection tests before formal detection and obtains test data during the detection test process. Based on the test data and the equipment detection time period, it estimates the interference encountered when formally executing the power generation equipment detection task. This enables the judgment of detection interference based on the actual environment, thereby improving the safety and feasibility of the detection task execution and achieving efficient and safe power generation equipment maintenance. Attached Figure Description

[0054] Figure 1 This is a flowchart illustrating a power generation equipment detection method based on a large model in one embodiment;

[0055] Figure 2 This is a structural block diagram of a power generation equipment detection system based on a large model in one embodiment. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0057] In one embodiment, a terminal is provided, the terminal being configured to: generate a power generation equipment testing task and a testing time period based on a preset power generation testing model and historical power generation operation data of the power generation equipment to be tested, and select power generation equipment testing personnel according to the power generation equipment testing task; set a test testing task according to the power generation equipment testing task and the power generation equipment to be tested, and acquire real-time environmental sensing data collected by the power generation equipment testing personnel when performing the test testing task in a target testing area, wherein the target testing area is the area where the power generation equipment to be tested is located; generate an estimated environmental interference value for the target testing area within the equipment testing time period based on the real-time environmental sensing data, wherein the estimated environmental interference value is used to represent the degree of interference of the external environment to the power generation equipment maintenance personnel during the equipment testing time period; determine whether the estimated environmental interference value is greater than or equal to a preset environmental interference safety threshold, and if the determination is yes, generate a testing task correction instruction, and prompt the power generation equipment testing personnel to adjust the testing time according to the testing task correction instruction.

[0058] The terminal may be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices.

[0059] In one embodiment, such as Figure 1 As shown, a method for detecting power generation equipment based on a large model is provided, the method comprising:

[0060] Step S100: Based on the preset power generation detection model, generate power generation equipment detection tasks and equipment detection time periods according to the historical power generation operation data of the power generation equipment to be detected, and select power generation equipment detection personnel according to the power generation equipment detection tasks;

[0061] Step S200: Set a test and inspection task according to the power generation equipment inspection task and the power generation equipment to be inspected, and obtain real-time environmental sensing data collected by the power generation equipment inspector when performing the test and inspection task in the target inspection area, wherein the target inspection area is the area where the power generation equipment to be inspected is located;

[0062] Step S300: Generate an estimated environmental interference value for the target detection area during the equipment detection time period based on the real-time environmental sensing data, wherein the estimated environmental interference value is used to represent the degree of interference of the external environment on the maintenance personnel of the power generation equipment during the equipment detection time period;

[0063] Step S400: Determine whether the estimated environmental interference value is greater than or equal to the preset environmental interference safety threshold. If the determination is yes, generate a detection task correction instruction and prompt the power generation equipment inspection personnel to adjust the detection time according to the detection task correction instruction.

[0064] In this embodiment, when it is necessary to inspect the power generation equipment to be tested, the previous fixed time period maintenance mode is no longer used. Instead, targeted maintenance is carried out after analyzing the operating data. Specifically, the historical power generation operation data of the power generation equipment to be tested is first obtained. Then, the power generation equipment testing task and equipment testing time period are generated based on the historical power generation operation data through a preset power generation testing big model. This realizes the operation data analysis based on the big model, and at the same time, it achieves high-efficiency generation of power generation equipment testing tasks and equipment testing time periods. After the equipment testing time period is set, the power generation equipment testing task needs to be executed within the equipment testing time period. Next, to ensure suitable testing personnel can be found for the power generation equipment testing task, testing personnel are selected based on the power generation equipment testing task. Then, to consider the actual testing environment and the actual environment encountered during the execution of the task, a testing task is first set based on the power generation equipment testing task and the power generation equipment to be tested. Real-time environmental sensing data is then acquired by the testing personnel while performing the testing task in the target testing area. This real-time detection data is the data collected by the testing personnel during the testing process. This data accurately reflects the environmental data faced by the power generation equipment under testing at the current stage. Based on this data, analysis can be performed on subsequent complete testing. To assess the safety of the power generation equipment inspection task, and to further analyze the environment during the task execution period, an estimated environmental interference value for the target inspection area is generated based on real-time environmental sensing data. This estimated environmental interference value represents the degree of interference from the external environment to the power generation equipment maintenance personnel during the inspection period. The system then determines whether the estimated environmental interference value is greater than or equal to a preset environmental interference safety threshold. If the threshold is not exceeded, it indicates that the interference will not affect the execution of the inspection task. In this case, a maintenance task execution instruction is generated, instructing the maintenance personnel to perform equipment maintenance within the specified maintenance period. If the threshold is exceeded, it indicates that the environmental interference encountered during the planned maintenance is too strong, potentially posing a safety risk. In this case, a inspection task correction instruction is generated, prompting the power generation equipment inspection personnel to adjust the inspection time. Therefore, this invention first sets up the detection task through a large-scale power generation detection model to improve detection efficiency and accuracy. Then, it conducts detection tests before formal detection and obtains test data during the detection test process. Based on the test data and the equipment detection time period, it estimates the interference encountered when formally executing the power generation equipment detection task. This enables the judgment of detection interference based on the actual environment, thereby improving the safety and feasibility of the detection task execution and achieving efficient and safe power generation equipment maintenance.

[0065] In one embodiment, step S200: setting a test and detection task based on the power generation equipment detection task and the power generation equipment to be tested, including:

[0066] Step S211: Obtain the power generation component to be tested and the estimated testing duration according to the power generation equipment testing task;

[0067] Step S212: Generate a detection task execution path based on the basic equipment structure of the power generation component to be tested and the equipment to be tested, wherein the detection task execution path includes multiple equipment detection path points;

[0068] Step S213: Generate a device test detection area based on the device detection path points, wherein one device detection path point corresponds to one device test detection area;

[0069] Step S214: Obtain the data collection category corresponding to each of the device detection path points, and set the test detection branch task according to the data collection category and the device test detection area, wherein one device test detection area corresponds to one test detection branch task.

[0070] In this embodiment, the power generation component to be tested is the component that needs to be tested. After obtaining the power generation component to be tested, the testing time of the power generation component to be tested is obtained by comparing it with a preset standard testing component time database, which is also the estimated monitoring duration. In this step, because different testing times are preset for different components, the estimated testing duration can be efficiently obtained after obtaining the power generation component to be tested. This is beneficial for subsequent testing tasks to be performed based on the estimated testing duration, and using this time as a testing unit to estimate the testing market for subsequent actual tasks, thereby improving safety. Next, a device testing area is generated based on the device testing path points, where one device testing path point corresponds to one device testing area. In this step, taking three device testing path points as an example, they are the nacelle outlet, the top of the nacelle, and the blade of the wind turbine. The corresponding device testing areas are the nacelle outlet area, the top of the nacelle dwelling area, and the blade body area, respectively. Among them, the area along the nacelle outlet and located on the top of the wind turbine, used for personnel to briefly stay, is the top of the nacelle dwelling area. When setting the equipment testing and inspection area, the area is formed by expanding outwards by a preset distance from the equipment inspection path point. Specifically, the cabin exit area is formed by uniformly expanding outwards by a first distance from the airport exit. The cabin top area is formed by uniformly expanding outwards by a second distance from the cabin top. The blade body area is formed by uniformly expanding outwards by a third distance from the airport exit. The first distance is 0.5 meters. The second distance is 1 meter. The third distance is 2 meters. It should be noted that the equipment testing and inspection area is not limited to a planar area; it can also be a three-dimensional area. For example, when inspecting a blade, the area is formed by uniformly expanding outwards by 2 meters from the entire blade, and this area is three-dimensional. Considering the randomness of the inspection, the power equipment inspectors are not necessarily conducting inspections in a planar area; they are more likely to conduct a circumferential inspection to ensure complete inspection. Therefore, a three-dimensional inspection method is set to improve the accuracy of the inspection. Then, the data collection categories of each equipment inspection path point are obtained, and test and inspection branch tasks are set according to the data collection categories and the equipment testing and inspection area. One equipment testing and inspection area corresponds to one test and inspection branch task. The correspondence between the data acquisition categories and the device detection path points is pre-set and stored. Therefore, when the device detection path points are obtained, the corresponding data acquisition categories can be obtained. By integrating the data acquisition categories and the device testing and detection areas, the setting of the testing and detection branch tasks is realized.

[0071] Furthermore, by setting the test and detection branch task, when acquiring real-time environmental sensing data collected by the power generation equipment inspector during the execution of the test and detection task in the target detection area, the test and detection branch task is used to instruct the power generation equipment inspector. In addition, the time for the power generation equipment inspector to collect each set of data is at least the estimated detection duration. Generally, multiple sets of data are used, that is, multiple sets of data with the estimated detection duration as the collection time unit are collected as real-time environmental sensing data.

[0072] In one embodiment, the equipment testing and detection area includes the nacelle exit area, the nacelle top dwell area, and the blade body area; the real-time environmental sensing data includes nacelle exit sensing data, nacelle top sensing data, and blade body sensing data.

[0073] Step S300: Generate an estimated environmental interference value for the target detection area within the device detection time period based on the real-time environmental sensing data, including:

[0074] Step S310: Extract wind speed sensing information, temperature sensing information and visibility sensing score from the sensor data at the nacelle exit, wherein the visibility sensing score is a score set by the power generation equipment inspector based on the visibility outside the nacelle exit.

[0075] In this step, the wind speed sensing information refers to the pressure detected both outside and inside the cabin exit, meaning this information represents the pressure inside and outside the cabin. The temperature sensing information refers to the temperature data outside the cabin exit.

[0076] Step S320: Extract the average wind speed inside the cabin and the average wind speed outside the cabin based on the wind speed sensing information, and extract the real-time sensing temperature at the cabin outlet at each data acquisition time point based on the temperature sensing information, as well as the maximum and minimum sensing temperatures among the real-time sensing temperatures, wherein the number of real-time sensing temperatures is n.

[0077] In this step, the wind speed sensing information is obtained through multiple tests. That is, the wind speed sensing information includes multiple sets of wind speeds inside and outside the cabin. The average value of each wind speed inside the cabin is calculated to generate the average wind speed inside the cabin Vin, and the average value of each pressure outside the cabin is calculated to generate the average wind speed outside the cabin Vout.

[0078] Step S330: Obtain the real-time protective equipment of the power generation equipment inspector and generate a real-time suitable temperature based on the real-time protective equipment, wherein the real-time suitable temperature is set based on the thickness of the real-time protective equipment of the power generation equipment inspector.

[0079] In this step, the real-time protective equipment refers to the protective clothing worn by the personnel inspecting the power generation equipment during inspection. Different thicknesses of protective clothing provide different levels of discomfort to the inspectors; excessively thick clothing can cause discomfort after prolonged work. Therefore, a survey is conducted beforehand, recording the results of multiple personnel wearing different clothing during a unit of working time. This establishes the relationship between different thicknesses of protective equipment and their corresponding suitable temperatures. The unit of working time is pre-set, typically 1 hour. For example, the first thickness of protective equipment is suitable for operation at 26°C. The second thickness is suitable for operation at 16°C. The third thickness is suitable for operation at 12°C. Generally, a unit of working time of 1 hour is considered relatively long. In this application, the inspection time for components is generally less than 1 hour, meaning the estimated inspection duration is less than 1 hour. Since the suitable operating temperature for 1 hour has been pre-calculated, this temperature is likely acceptable within 1 hour. Therefore, the unit of working time is set to be longer than the estimated inspection duration.

[0080] Step S340: Generate cabin exit interference value based on average wind speed, average wind speed outside the cabin, real-time sensed temperature, maximum sensed temperature, minimum sensed temperature, and real-time suitable temperature;

[0081] Step S350: From the top dust accumulation information, top slope information and top wind speed information in the top sensing data of the cabin, generate the top interference value of the cabin;

[0082] Step S360: Extract blade wind speed information from the blade body sensing data, and generate blade environmental interference value based on the blade wind speed information;

[0083] Step S370: Obtain the estimated weather data for the device detection period, and generate an environmental difference coefficient based on the difference between the estimated weather data and the test detection weather data, wherein the test detection weather data is the weather data when the test detection task is performed;

[0084] In this step, to determine whether the external environment is suitable for testing during the equipment testing period, it is necessary to compare the weather data during the testing period with the data obtained during the test to obtain the difference between the two. This allows for the estimation of future actual testing based on the actual data obtained during the test, and because the testing time is relatively close to the equipment testing period, the accuracy of the predicted data is higher. Specifically, the estimated weather data for the equipment testing period is first obtained, and then the two are compared. The difference between the estimated weather data and the test weather data is obtained, and a coefficient is generated based on the percentage difference to represent the difference in environmental data. Specifically, an environmental difference coefficient is generated based on the difference between the estimated weather data and the test weather data. For example, if the wind speed during the test is level 3, and the estimated weather data shows that the wind speed suddenly increases to level 6 during the equipment testing period, then the corresponding environmental difference coefficient value is the first value. If the estimated weather data shows that the wind speed suddenly increases to level 9 during the equipment testing period, then the corresponding environmental difference coefficient value is the second value. The second value is greater than the first value; generally, the second value is at least twice the first value. Of course, the generation of the environmental difference coefficient does not rely solely on a single environmental parameter; the above is merely an example and not a specific limitation. In actual generation of the environmental difference coefficient, multiple environmental parameters can be weighted, and each environmental parameter can be compared with the tested weather data to generate a comparison coefficient. Then, the comparison coefficients are summed to finally generate the environmental difference coefficient.

[0085] Step S380: Based on the nacelle exit disturbance value Dr, the nacelle top disturbance value Dc, the blade environmental disturbance value Db, and the environmental difference coefficient Ce, generate the estimated environmental disturbance value EDs using the following formula:

[0086] EDs = Ce(Dr + Dc + Db);

[0087] Wherein, EDs is the estimated environmental disturbance value, Ce is the environmental difference coefficient, Dr is the nacelle outlet disturbance value, Dc is the nacelle top disturbance value, and Db is the blade environmental disturbance value.

[0088] In this embodiment, to improve the accuracy and reference value of the estimated environmental interference value, wind speed sensing information, temperature sensing information, and visibility sensing score are first extracted from the nacelle exit sensing data. Then, the average wind speed inside and outside the nacelle are extracted based on the wind speed sensing information, and the real-time sensing temperature at the nacelle exit at each data acquisition time point, as well as the maximum and minimum sensing temperatures among the real-time sensing temperatures, are extracted based on the temperature sensing information. Next, the real-time protective equipment of the power generation equipment inspection personnel is obtained, and a real-time suitable temperature is generated based on the real-time protective equipment as a reference. The nacelle exit interference value is generated based on the average wind speed, the average wind speed outside the nacelle, the real-time sensing temperature, the maximum and minimum sensing temperatures, and the real-time suitable temperature. Then, the nacelle top interference value, the blade environmental interference value, and the environmental difference coefficient are generated respectively. Finally, the above data are combined to generate the estimated environmental interference value, so that the estimated environmental interference value includes as much environmental interference as possible that may be encountered in the entire maintenance path, thereby improving its reference value.

[0089] In one embodiment, the cabin exit disturbance value is generated based on the following formula:

[0090]

[0091] Where Dr is the cabin exit interference value, β1 is the hatch interference coefficient, Vout is the average wind speed outside the cabin, Vin is the average wind speed inside the cabin, Vs is the standard wind speed difference, β2 is the temperature interference coefficient, α1 is the first temperature interference coefficient, Ti is the i-th real-time sensing temperature, Ts is the real-time suitable temperature, α2 is the second temperature interference coefficient, Tmax is the maximum sensing temperature, Tmin is the minimum sensing temperature, and Vb is the visibility sensing score.

[0092] In one embodiment, step S350, generating a nacelle top disturbance value based on the top dust accumulation information, top slope information, and top wind speed information, includes:

[0093] Step S351: Extract the estimated dust thickness and top surface humidity based on the top dust information, and generate the estimated walking slope based on the top slope information;

[0094] Step S352: Extract the real-time top wind speed at each data collection time point based on the top wind speed information, generate the average top wind speed based on each of the real-time top wind speeds, and generate the wind disturbance coefficient based on the average top wind speed.

[0095] In this step, the average wind speed at the top is directly proportional to the wind disturbance coefficient; that is, the higher the average wind speed at the top, the higher the wind disturbance coefficient. The interference experienced at different wind speeds is pre-measured by testing personnel, and an interference coefficient is generated. Therefore, the correspondence between wind speed and interference impact can be established. Thus, after obtaining the average wind speed at the top, the wind disturbance coefficient can be generated.

[0096] Step S353: Based on the estimated dust accumulation thickness, top surface humidity, estimated travel slope, and wind disturbance coefficient, generate the nacelle top disturbance value using the following formula:

[0097]

[0098] Where Dc is the disturbance value at the top of the cabin, δ is the wind disturbance coefficient, Th is the estimated dust accumulation thickness, Ths is the preset safe dust accumulation thickness, Hu is the humidity of the top surface, Hus is the preset safe surface humidity, and Sp is the estimated walking slope.

[0099] In this step, both the safe dust accumulation thickness and the safe surface humidity are pre-measured and set based on the protective footwear uniformly provided by the power generation equipment inspectors. These settings provide a reference for better assessing the current slipperiness of the nacelle roof. The estimated walking slope is measured by the power generation equipment inspectors using a mini level; alternatively, the slope can be set based on their experience, although this method has lower accuracy. Generally, measurements are already taken during wind turbine assembly, so only data extraction is required at this stage.

[0100] In this embodiment, the estimated dust thickness and top surface humidity are first extracted based on the dust accumulation information at the top, and the estimated walking slope is generated based on the top slope information. The real-time wind speed at the top is extracted at each data collection time point, and the average wind speed at the top is generated based on the real-time wind speed at the top. The wind disturbance coefficient is generated based on the average wind speed at the top. Thus, the interference value at the top of the nacelle is generated by combining the estimated dust thickness, top surface humidity, estimated walking slope, and wind disturbance coefficient. This enables data-driven calculation of the interference received when working at the top of the nacelle.

[0101] In one embodiment, step S360, generating a blade environmental disturbance value based on the blade wind speed information, includes:

[0102] In this embodiment, the average value of the real-time wind speed in the blade area contained in the blade wind speed information is calculated to obtain the average wind speed Vp in the blade area. Then, the actual weight M, the estimated windward area A, and the normal inspection posture of the power generation equipment inspector are obtained, and the drag coefficient Cd is generated based on the normal inspection posture.

[0103] Next, the environmental disturbance value of the blade is generated based on the following formula:

[0104] FA=M*Cd*A*ρ*Vp 2 ;

[0105] Where FA is the environmental disturbance value of the blade, M is the actual weight of the person inspecting the power generation equipment, Cd is the drag coefficient, A is the estimated windward area, Vp is the average wind speed in the blade area, and ρ is the air density.

[0106] In this embodiment, the blade environmental interference value is generated by combining the blade environmental interference value, the actual weight of the power generation equipment inspector, the drag coefficient, the estimated windward area, and the average wind speed in the blade area.

[0107] In one embodiment, step S100, selecting power generation equipment inspection personnel according to the power generation equipment inspection task, includes:

[0108] In this embodiment, the detection difficulty of the power generation equipment detection task is first obtained, and the detection personnel who have passed the detection difficulty are processed according to the detection difficulty. Then, the detection personnel who have no work schedule during the equipment detection time period are selected, and the finally determined personnel are the power generation equipment detection personnel.

[0109] In one embodiment, the setup steps for the large-scale power generation detection model include:

[0110] First, routine operating data of wind power equipment in various regions during regular time periods are collected. This routine operating data includes: wind speed and direction, blade rotation speed, main shaft vibration data, generator vibration data, temperature, humidity, pressure, historical fault and maintenance records of power output. Next, features are extracted, specifically vibration amplitude features, frequency features, wind speed fluctuations, and frequency domain features. Then, a model based on LSTM (Long Short-Term Memory) or Convolutional Neural Network (CNN) is developed. The data is then divided into training, validation, and test sets. Next, the model is trained using the training set and validated using the validation set. Based on the model's evaluation results, continuous optimization is performed, such as by eliminating irrelevant or redundant features through feature importance assessment, or by adjusting hyperparameters through grid search or Bayesian optimization to improve model accuracy. Finally, the trained model is deployed in the wind power equipment monitoring system to analyze operating data in real time, predict components requiring inspection or maintenance, and generate equipment inspection tasks and time periods based on the historical power generation operation data of the equipment to be inspected.

[0111] like Figure 2 As shown, a power generation equipment testing system based on a large model is also provided, the system comprising:

[0112] The maintenance task setting module is used to generate power equipment inspection tasks and equipment inspection time periods based on a preset power generation inspection model and the historical power generation operation data of the power equipment to be inspected, and to select power equipment inspection personnel according to the power equipment inspection tasks.

[0113] The real-time data sensing module is used to set test and inspection tasks according to the power generation equipment inspection task and the power generation equipment to be inspected, and to acquire real-time environmental sensing data collected by the power generation equipment inspector when performing the test and inspection task in the target inspection area, wherein the target inspection area is the area where the power generation equipment to be inspected is located;

[0114] An interference data generation module is used to generate an estimated environmental interference value for the target detection area during the equipment detection time period based on the real-time environmental sensing data. The estimated environmental interference value is used to represent the degree of interference of the external environment to the maintenance personnel of the power generation equipment during the equipment detection time period.

[0115] The detection task execution module is used to determine whether the estimated environmental interference value is greater than or equal to the preset environmental interference safety threshold. If the determination is yes, a detection task correction instruction is generated, and the power generation equipment inspection personnel are prompted to adjust the detection time according to the detection task correction instruction.

[0116] In another embodiment, the real-time data sensing module is further configured to:

[0117] The power generation component to be tested and the estimated testing duration are obtained according to the power generation equipment testing task; a testing task execution path is generated according to the power generation component to be tested and the basic equipment structure of the equipment to be tested, wherein the testing task execution path includes multiple equipment testing path points; an equipment testing area is generated according to the equipment testing path points, wherein one equipment testing path point corresponds to one equipment testing area; the data acquisition category corresponding to each equipment testing path point is obtained, and a testing branch task is set according to the data acquisition category and the equipment testing area, wherein one equipment testing area corresponds to one testing branch task.

[0118] In another embodiment, the equipment testing and detection area includes the nacelle exit area, the nacelle top dwell area, and the blade body area; the real-time environmental sensing data includes nacelle exit sensing data, nacelle top sensing data, and blade body sensing data; the interference data generation module is further used for:

[0119] Wind speed sensing information, temperature sensing information, and visibility sensing score are extracted from the sensor data at the engine room exit. The visibility sensing score is a score set by the power equipment inspector based on the visibility outside the engine room exit. The average wind speed inside and outside the engine room is extracted from the wind speed sensing information. The real-time sensed temperature at the engine room exit at each data acquisition time point, as well as the maximum and minimum sensed temperatures among these real-time sensed temperatures, are extracted from the temperature sensing information. The number of real-time sensed temperatures is n. The real-time protective equipment of the power equipment inspector is obtained, and a real-time suitable temperature is generated based on the real-time protective equipment. The real-time suitable temperature is based on the real-time protective equipment of the power equipment inspector. The thickness of the equipment is set according to the following: The nacelle outlet interference value is generated based on the average wind speed, average wind speed outside the nacelle, real-time sensed temperature, maximum sensed temperature, minimum sensed temperature, and real-time suitable temperature; Nacelle top interference value is generated from the top dust accumulation information, top slope information, and top wind speed information in the top sensed data of the nacelle; Blade wind speed information is extracted from the blade body sensed data, and blade environmental interference value is generated based on the blade wind speed information; Estimated weather data for the equipment detection period is obtained, and an environmental difference coefficient is generated based on the difference between the estimated weather data and the test detection weather data, wherein the test detection weather data is the weather data during the execution of the test detection task;

[0120] Based on the nacelle exit disturbance value Dr, the nacelle top disturbance value Dc, the blade environmental disturbance value Db, and the environmental difference coefficient Ce, the estimated environmental disturbance value EDs is generated using the following formula:

[0121] EDs = Ce(Dr + Dc + Db);

[0122] Wherein, EDs is the estimated environmental disturbance value, Ce is the environmental difference coefficient, Dr is the nacelle outlet disturbance value, Dc is the nacelle top disturbance value, and Db is the blade environmental disturbance value.

[0123] The interference data generation module is also used to generate cabin exit interference values ​​based on the following formula:

[0124]

[0125] Where Dr is the cabin exit interference value, β1 is the hatch interference coefficient, Vout is the average wind speed outside the cabin, Vin is the average wind speed inside the cabin, Vs is the standard wind speed difference, β2 is the temperature interference coefficient, α1 is the first temperature interference coefficient, Ti is the i-th real-time sensing temperature, Ts is the real-time suitable temperature, α2 is the second temperature interference coefficient, Tmax is the maximum sensing temperature, Tmin is the minimum sensing temperature, and Vb is the visibility sensing score.

[0126] In another embodiment, the interference data generation module is further configured to: extract the estimated dust thickness and top surface humidity based on the top dust information, and generate an estimated walking slope based on the top slope information; extract the real-time top wind speed at each data collection time point based on the top wind speed information, generate the top average wind speed based on each of the real-time top wind speeds, and generate a wind disturbance coefficient based on the top average wind speed; and generate a cabin top interference value based on the following formula, using the estimated dust thickness, top surface humidity, estimated walking slope, and wind disturbance coefficient:

[0127]

[0128] Where Dc is the disturbance value at the top of the cabin, δ is the wind disturbance coefficient, Th is the estimated dust accumulation thickness, Ths is the preset safe dust accumulation thickness, Hu is the humidity of the top surface, Hus is the preset safe surface humidity, and Sp is the estimated walking slope.

[0129] In another embodiment, the interference data generation module is further configured to: calculate the average value of the real-time wind speed in the blade area contained in the blade wind speed information, and obtain the average wind speed Vp in the blade area; then, obtain the actual weight M, the estimated windward area A, and the normal inspection posture of the power generation equipment inspector; and generate the drag coefficient Cd based on the normal inspection posture.

[0130] Next, the environmental disturbance value of the blade is generated based on the following formula:

[0131] FA=M*Cd*A*ρ*Vp 2 ;

[0132] Where FA is the environmental disturbance value of the blade, M is the actual weight of the person inspecting the power generation equipment, Cd is the drag coefficient, A is the estimated windward area, Vp is the average wind speed in the blade area, and ρ is the air density.

[0133] In another embodiment, the maintenance task setting module is further configured to: obtain the inspection difficulty of the power generation equipment inspection task, process the inspection personnel who have passed the inspection difficulty according to the inspection difficulty, select the inspection personnel who have no work schedule during the equipment inspection time period, and finally determine the personnel as the power generation equipment inspection personnel.

[0134] In another embodiment, the maintenance task setting module is further used to: collect routine operating data of publicly available wind power equipment for regular time periods in various regions. This routine operating data includes: wind speed and direction, blade rotation speed, main shaft, generator vibration data, temperature, humidity, pressure, historical fault and maintenance records of power output. Next, features are extracted, specifically including vibration amplitude features, frequency features, wind speed fluctuations, and frequency domain features. Then, a model is built based on LSTM (Long Short-Term Memory) or Convolutional Neural Network (CNN). The data is then divided into training, validation, and test sets. Next, the model is trained using the training set and validated using the validation set. Based on the model's evaluation results, continuous optimization is performed, such as by eliminating irrelevant or redundant features through feature importance assessment, or by adjusting hyperparameters through grid search or Bayesian optimization to improve model accuracy. Finally, the trained model is set up in the wind power equipment monitoring system to analyze operating data in real time, predict components requiring inspection or maintenance, and generate power equipment inspection tasks and equipment inspection time periods based on the historical power generation operation data of the power generation equipment to be inspected.

[0135] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps described in the above-described method for detecting power generation equipment based on a large model.

[0136] In one embodiment, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the steps described in the above-described method for detecting power generation equipment based on a large model.

[0137] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0138] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0139] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for detecting power generation equipment based on a large model, characterized in that, The method includes: Based on a pre-set large-scale power generation detection model, the system generates power generation equipment detection tasks and equipment detection time periods according to the historical power generation operation data of the power generation equipment to be detected, and selects power generation equipment detection personnel according to the power generation equipment detection tasks. The test and inspection task is set according to the power generation equipment inspection task and the power generation equipment to be inspected, and the real-time environmental sensing data collected by the power generation equipment inspection personnel when performing the test and inspection task in the target inspection area is obtained, wherein the target inspection area is the area where the power generation equipment to be inspected is located; Based on the real-time environmental sensing data, an estimated environmental interference value for the target detection area is generated during the device detection time period. The estimated environmental interference value is used to represent the degree of interference of the external environment on the personnel inspecting the power generation equipment during the device detection time period. Determine whether the estimated environmental interference value is greater than or equal to the preset environmental interference safety threshold. If the determination is yes, generate a detection task correction instruction and prompt the power generation equipment inspection personnel to adjust the inspection time according to the detection task correction instruction.

2. The power generation equipment detection method based on a large model according to claim 1, characterized in that, The test and inspection tasks are set according to the power generation equipment testing tasks and the power generation equipment to be tested, including: The power generation components to be tested and the estimated testing duration are obtained based on the power generation equipment testing task. A detection task execution path is generated based on the basic equipment structure of the power generation component to be tested and the power generation equipment to be tested, wherein the detection task execution path includes multiple equipment detection path points; A device test and detection area is generated based on the device detection path points, wherein one device detection path point corresponds to one device test and detection area; Obtain the data collection category corresponding to each of the device detection path points, and set the test detection branch task according to the data collection category and the device test detection area, wherein one device test detection area corresponds to one test detection branch task.

3. The power generation equipment detection method based on a large model according to claim 2, characterized in that, The equipment testing and detection area includes the nacelle exit area, the nacelle top dwell area, and the blade body area; the real-time environmental sensing data includes nacelle exit sensing data, nacelle top sensing data, and blade body sensing data. Based on the real-time environmental sensing data, an estimated environmental interference value for the target detection area is generated within the device's detection time period, including: Wind speed sensing information, temperature sensing information, and visibility sensing score are extracted from the sensor data at the nacelle exit. The visibility sensing score is a score set by the power generation equipment inspector based on the visibility outside the nacelle exit. The average wind speed inside and outside the cabin is extracted based on the wind speed sensing information, and the real-time sensing temperature at the cabin exit at each data acquisition time point is extracted based on the temperature sensing information, as well as the maximum and minimum sensing temperatures among the real-time sensing temperatures, wherein the number of real-time sensing temperatures is n. The real-time protective equipment of the personnel inspecting the power generation equipment is obtained, and a real-time suitable temperature is generated based on the real-time protective equipment, wherein the real-time suitable temperature is set based on the thickness of the real-time protective equipment of the personnel inspecting the power generation equipment. The cabin exit interference value is generated based on the average wind speed, the average wind speed outside the cabin, the real-time sensed temperature, the maximum sensed temperature, the minimum sensed temperature, and the real-time suitable temperature. The top dust accumulation information, top slope information, and top wind speed information are obtained from the sensing data at the top of the cabin, and the top interference value of the cabin is generated based on the top dust accumulation information, top slope information, and top wind speed information. The blade wind speed information is extracted from the main body sensing data of the blade, and the blade environmental interference value is generated based on the blade wind speed information; Obtain the estimated weather data for the device detection period, and generate an environmental difference coefficient based on the difference between the estimated weather data and the test detection weather data, wherein the test detection weather data is the weather data when the test detection task is performed; Based on the nacelle exit disturbance value Dr, the nacelle top disturbance value Dc, the blade environmental disturbance value Db, and the environmental difference coefficient Ce, the estimated environmental disturbance value EDs is generated using the following formula: ； Wherein, EDs is the estimated environmental disturbance value, Ce is the environmental difference coefficient, Dr is the nacelle outlet disturbance value, Dc is the nacelle top disturbance value, and Db is the blade environmental disturbance value.

4. The power generation equipment detection method based on a large model according to claim 3, characterized in that, The cabin exit interference value is generated based on the following formula: ； Where Dr represents the cabin exit interference value. Vout is the hatch interference coefficient, Vin is the average wind speed outside the hatch, Vs is the average wind speed inside the hatch, and Vs is the standard wind speed difference. The temperature interference coefficient is... Let Ti be the first temperature interference coefficient, Ti be the i-th real-time sensed temperature, and Ts be the real-time suitable temperature. Tmax is the second temperature interference coefficient, Tmin is the maximum sensing temperature, and Vb is the visibility sensing score.

5. The method for detecting power generation equipment based on a large model according to claim 3, characterized in that, Based on the aforementioned top dust accumulation information, top slope information, and top wind speed information, a nacelle top interference value is generated, including: Based on the dust accumulation information at the top, the estimated dust thickness and the humidity of the top surface are extracted, and the estimated walking slope is generated based on the top slope information. Based on the top wind speed information, extract the top real-time wind speed at each data collection time point, generate the top average wind speed based on each top real-time wind speed, and generate the wind disturbance coefficient based on the top average wind speed. The cabin top disturbance value is generated based on the estimated dust thickness, top surface humidity, estimated travel slope, and wind disturbance coefficient.

6. A power generation equipment testing system based on a large model, characterized in that, The system includes: The maintenance task setting module is used to generate power equipment inspection tasks and equipment inspection time periods based on a preset power generation inspection model and the historical power generation operation data of the power equipment to be inspected, and to select power equipment inspection personnel according to the power equipment inspection tasks. The real-time data sensing module is used to set test and inspection tasks according to the power generation equipment inspection task and the power generation equipment to be inspected, and to acquire real-time environmental sensing data collected by the power generation equipment inspector when performing the test and inspection task in the target inspection area, wherein the target inspection area is the area where the power generation equipment to be inspected is located; An interference data generation module is used to generate an estimated environmental interference value for the target detection area during the device detection time period based on the real-time environmental sensing data. The estimated environmental interference value is used to represent the degree of interference of the external environment to the personnel inspecting the power generation equipment during the device detection time period. The detection task execution module is used to determine whether the estimated environmental interference value is greater than or equal to the preset environmental interference safety threshold. If the determination is yes, a detection task correction instruction is generated, and the power generation equipment inspection personnel are prompted to adjust the detection time according to the detection task correction instruction.

7. The power generation equipment detection system based on a large model according to claim 6, characterized in that, The real-time data sensing module is also used for: The following steps are taken: First, the generator component to be tested and the estimated testing duration are obtained based on the generator component and the basic equipment structure of the generator. Second, a testing task execution path is generated based on the generator component and the generator. This execution path includes multiple equipment testing path points. Third, an equipment testing area is generated based on these path points, with each path point corresponding to one testing area. Fourth, the data acquisition category corresponding to each path point is obtained, and a testing branch task is set based on the data acquisition category and the testing area, with each testing area corresponding to one testing branch task.

8. The power generation equipment detection system based on a large model according to claim 7, characterized in that, The equipment testing and detection area includes the nacelle exit area, the nacelle top dwell area, and the blade body area; the real-time environmental sensing data includes nacelle exit sensing data, nacelle top sensing data, and blade body sensing data; the interference data generation module is also used for: Wind speed sensing information, temperature sensing information, and visibility sensing score are extracted from the sensor data at the engine room exit. The visibility sensing score is a score set by the power equipment inspector based on the visibility outside the engine room exit. The average wind speed inside and outside the engine room is extracted from the wind speed sensing information. The real-time sensed temperature at the engine room exit at each data acquisition time point, as well as the maximum and minimum sensed temperatures among these real-time sensed temperatures, are extracted from the temperature sensing information. The number of real-time sensed temperatures is n. The real-time protective equipment of the power equipment inspector is obtained, and a real-time suitable temperature is generated based on the real-time protective equipment. The real-time suitable temperature is based on the real-time protective equipment of the power equipment inspector. The thickness of the equipment is set according to the following: The nacelle outlet interference value is generated based on the average wind speed, average wind speed outside the nacelle, real-time sensed temperature, maximum sensed temperature, minimum sensed temperature, and real-time suitable temperature; Nacelle top interference value is generated from the top dust accumulation information, top slope information, and top wind speed information in the top sensed data of the nacelle; Blade wind speed information is extracted from the blade body sensed data, and blade environmental interference value is generated based on the blade wind speed information; Estimated weather data for the equipment detection period is obtained, and an environmental difference coefficient is generated based on the difference between the estimated weather data and the test detection weather data, wherein the test detection weather data is the weather data during the execution of the test detection task; Based on the nacelle exit disturbance value Dr, the nacelle top disturbance value Dc, the blade environmental disturbance value Db, and the environmental difference coefficient Ce, the estimated environmental disturbance value EDs is generated using the following formula: ； Wherein, EDs is the estimated environmental disturbance value, Ce is the environmental difference coefficient, Dr is the nacelle outlet disturbance value, Dc is the nacelle top disturbance value, and Db is the blade environmental disturbance value.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images