An artificial intelligence-based wind power plant remote monitoring system

Abstract

The application relates to the field of wind power plant station monitoring, and discloses a wind power plant station remote monitoring system based on artificial intelligence. The station is divided into a plurality of inspection sub-areas, an artificial intelligence algorithm is used to automatically plan an inspection route for intelligent inspection equipment in the inspection sub-areas, and inspection and data collection are carried out. Through analysis and data fusion of image, temperature data and vibration data of wind power equipment in the inspection sub-areas, abnormal problems of the wind power equipment in the inspection sub-areas are comprehensively detected. Based on combination of historical power generation, voltage and current and real-time power generation, voltage and current, fault prediction is carried out on the abnormal wind power equipment in the inspection sub-areas. Remote monitoring and management are carried out by a remote monitoring platform, which is favorable for realizing comprehensive coverage and real-time monitoring of wind power plant equipment and areas, improving inspection efficiency and precision, and further improving the accuracy and reliability of fault prediction.

Description

Technical Field

[0001] This invention relates to the field of wind power airport station monitoring technology, and more specifically to a remote monitoring system for wind power airport stations based on artificial intelligence. Background Technology

[0002] With the rapid development of wind power, the number of wind turbines has increased dramatically, and the scale of wind farms has continued to expand, gradually elevating the status of wind power in the energy structure. However, wind farms are typically located in remote areas, covering vast areas with complex and variable environments, posing significant challenges to their operation and maintenance management. Therefore, a wind farm monitoring system can provide intelligent monitoring of wind farms. This system collects data via wired or wireless means and transmits it to a server through a network. The collected data is then analyzed in depth, various alarm and early warning rules are set, and various reports and trend charts are generated, enabling real-time monitoring and early warning feedback of the wind farm's operational status.

[0003] However, the above process still has the following drawbacks:

[0004] Firstly, the existing wind power airport monitoring system relies heavily on manual inspection, data analysis, and fault diagnosis, which cannot guarantee inspection efficiency and accuracy, and is difficult to fully cover all equipment and areas.

[0005] Secondly, existing wind farm monitoring systems mainly rely on simple data analysis tools and methods, which are often inadequate for complex data analysis and processing tasks, and lack in-depth analysis of wind farm equipment from multiple perspectives.

[0006] Third, existing wind power station monitoring systems lack the ability to accurately predict and quickly diagnose wind power equipment failures by combining historical and real-time data, and cannot provide a remote monitoring platform to enable managers to remotely monitor and manage the equipment operation status of new energy stations. Summary of the Invention

[0007] In order to overcome the above-mentioned defects of the prior art, the present invention provides a remote monitoring system for wind power airport stations based on artificial intelligence to solve the problems existing in the background art.

[0008] This invention provides the following technical solution: a remote monitoring system for wind power station based on artificial intelligence, comprising:

[0009] Inspection area division module: The station is divided into several inspection sub-areas according to the type of equipment in the new energy station, and numbered as 1, 2, 3...n respectively;

[0010] Inspection route planning module: By using artificial intelligence algorithms to automatically plan inspection routes for intelligent inspection equipment within the divided inspection sub-areas, the new energy power stations are then inspected according to the planned inspection routes.

[0011] Inspection data acquisition module: used to collect images, temperature data and vibration data of wind power equipment in each inspection sub-area. It collects images, temperature data and vibration data of wind power equipment in the inspection sub-area through drones and uploads the collected images, temperature data and vibration data of wind power equipment to the cloud server for processing.

[0012] Preliminary Analysis Module: By analyzing the images, temperature data, and vibration data of wind power equipment in the inspection sub-area, the module obtains the blade appearance condition index, tower appearance change index, temperature fluctuation index, and equipment wear impact index. It includes an image analysis unit, a temperature analysis unit, and a vibration analysis unit.

[0013] Data fusion module: By performing data fusion calculations on the data analysis results in the preliminary analysis module, the risk assessment coefficient for abnormal equipment condition is obtained;

[0014] Anomaly Detection Module: Based on the results of data fusion, the module compares the risk assessment coefficient of equipment condition anomaly with the risk threshold of equipment condition anomaly, thereby performing anomaly detection on wind power equipment in the inspection sub-area and transmitting the anomaly detection results to the fault prediction module.

[0015] Fault prediction module: Based on the detection results of the anomaly detection module, the historical power generation, voltage and current are combined with the real-time power generation, voltage and current for analysis, and the fault prediction coefficient is calculated to predict the faults of abnormal wind power equipment in the inspection sub-area.

[0016] Fault diagnosis module: Based on the results of fault prediction, fault diagnosis is performed on abnormal wind power equipment in the inspection sub-area;

[0017] Remote monitoring module: By setting up a remote monitoring platform, it automatically generates wind power equipment inspection and monitoring reports, and transmits the fault diagnosis results of wind power equipment to the remote monitoring platform through the cloud server to provide early warning feedback to the management personnel.

[0018] Preferably, the inspection area division module divides the wind power airport station into several relatively independent inspection sub-areas according to the type of equipment. Each inspection sub-area should contain a certain number of wind power equipment of the same type, and each divided inspection sub-area is numbered, starting from 1 and increasing sequentially until n.

[0019] Preferably, the inspection route planning module selects a drone equipped with a high-definition camera, infrared thermal imager, and sensors as the intelligent inspection equipment for the new energy power station. It uses path optimization algorithms in artificial intelligence, combined with the equipment distribution and road conditions in the inspection sub-area, to intelligently plan and adjust the inspection route of the drone in real time, and automatically generates the optimal inspection route. Then, the drone inspects the inspection sub-area within the new energy power station according to the planned inspection route.

[0020] Preferably, the inspection data acquisition module activates the drone and collects inspection data for each sub-area according to a preset inspection route. The collected images, temperature data, and vibration data are then uploaded to a cloud server in real time via the drone's wireless transmission module. The cloud server performs noise reduction, image enhancement, and data cleaning on the images, temperature data, and vibration data. The specific data acquisition process includes:

[0021] By using drones equipped with high-resolution cameras to fly over wind farms, detailed visual inspections of wind power equipment are conducted, capturing real-time images of the equipment's appearance. Thermal imagers and vibration sensors installed on the drones are used to collect real-time temperature and vibration data of the equipment.

[0022] Preferably, the preliminary analysis module monitors the characteristic change trend of wind power equipment in each inspection sub-area in real time by collaboratively analyzing the images, temperature data, and vibration data of the wind power equipment in each inspection sub-area.

[0023] The image analysis unit uses deep learning algorithms to perform feature analysis on individual devices in the equipment images of wind turbines during operation, and calculates the blade appearance condition index C. ij Tower appearance change index I ij This allows for the automatic identification of blade surface damage and tower surface defects.

[0024] The temperature analysis unit analyzes the temperature change trend of individual wind power equipment operating within the inspection sub-region and calculates the temperature fluctuation index T. ij ′;

[0025] The vibration analysis unit analyzes the vibration data of individual wind turbines operating within the inspection sub-region, including wind speed, wind direction, vibration frequency, and external wind pressure, and calculates the equipment wear influence index D. ij .

[0026] Preferably, the data fusion module first standardizes the data of the blade appearance condition index, tower appearance change index, temperature fluctuation index, and equipment wear impact index, and then performs fusion calculation to obtain the specific calculation formula for the equipment condition abnormality risk assessment coefficient, which is Q. ij =ln(Cij +a)×ln(I ij +a)×ln(T ij ′+a)×ln(D ij +a), C ij I represents the blade appearance condition index. ij T represents the tower appearance change index. ij ′ represents the temperature fluctuation index, D ij This represents the influence index of equipment wear, where 'a' represents a constant.

[0027] Preferably, the anomaly detection module sets an abnormal equipment condition risk threshold θ for wind power equipment in each inspection sub-area. i The risk assessment coefficient Q for abnormal equipment condition is... ij With the equipment condition abnormality risk threshold θ i Comparisons are made to detect abnormal wind power equipment within the inspection sub-area; when the equipment condition is abnormal, the risk assessment coefficient Q is used. ij ≤Equipment abnormality risk threshold θ i When this occurs, it indicates that no abnormal wind power equipment has been found in the inspected sub-area. Monitoring and analysis will continue. When the equipment condition abnormality risk assessment coefficient Q... ij >Equipment abnormality risk threshold θ i When the error occurs, it indicates that there is an abnormal problem with a single wind turbine in the inspection sub-area. All wind turbines with abnormal problems in the inspection sub-area are then selected and the selection results are transmitted to the fault prediction module.

[0028] Preferably, the fault prediction module performs a difference analysis by collecting historical average power generation, average voltage, and average current of each abnormal wind power device over a historical period, and real-time power generation, voltage, and current, and calculates the fault prediction coefficient. G im，实时 R represents the real-time power generation of the m-th abnormal wind turbine in the i-th inspection sub-region. im，实时 V represents the real-time current measured by the m-th abnormal wind turbine in the i-th inspection sub-region. im，实时 G represents the real-time voltage currently measured for the m-th abnormal wind power device in the i-th inspection sub-region. im，历史 R represents the historical average power generation of the m-th abnormal wind turbine in the i-th inspection sub-region. im，历史 V represents the historical average current of the m-th abnormal wind turbine in the i-th inspection sub-region. im，历史 This represents the historical average voltage of the m-th abnormal wind power device in the i-th inspection sub-region. This represents the standard deviation of the historical power generation of the m-th abnormal wind power device in the i-th inspection sub-region. This represents the standard deviation of the historical current of the m-th abnormal wind power device in the i-th inspection sub-region. It represents the standard deviation of the historical voltage of the m-th abnormal wind power equipment in the i-th inspection sub-region.

[0029] Preferably, the fault diagnosis module uses the fault prediction coefficient H im Compared with the preset fault threshold λ i By comparing the results, it can be determined whether there is a fault in the abnormal wind power equipment within the inspection sub-area. If the fault prediction coefficient H im >Preset fault threshold λ i If the abnormal wind power equipment in the inspection sub-area does not have a fault, then the abnormal wind power equipment needs to be monitored closely. If the fault prediction coefficient H im >Preset fault threshold λ i If the fault is detected, it is determined that a single abnormal wind power device in the inspection sub-area has a fault problem, and the fault diagnosis result is immediately fed back to the result feedback module.

[0030] Preferably, the remote monitoring module is used to receive automatically generated wind power equipment inspection and monitoring reports and wind power equipment fault diagnosis results transmitted from the cloud server. Managers can view the operating status and inspection results of the new energy power station anytime and anywhere through the remote monitoring platform, and receive early warning results, thereby realizing remote monitoring and management.

[0031] The technical effects and advantages of this invention are as follows:

[0032] This invention divides the wind farm into several inspection sub-regions using an inspection area division module, each numbered. An inspection route planning module uses artificial intelligence algorithms to automatically plan inspection routes for intelligent inspection equipment within each sub-region and conducts the inspections. An inspection data acquisition module collects real-time images, temperature data, and vibration data of the wind power equipment within each sub-region. A preliminary analysis module analyzes these data, and a data fusion module performs data fusion calculations to obtain an equipment anomaly risk assessment coefficient. An anomaly detection module compares this coefficient with an anomaly risk threshold to detect anomalies in the wind power equipment within the sub-region. A fault prediction module uses historical power generation data... The system combines voltage and current data with real-time power generation to predict faults in abnormal wind turbines within the inspection area. A fault diagnosis module diagnoses these faults, and a remote monitoring module establishes a platform for remote monitoring and management of the wind turbine inspection. Utilizing drones and AI-planned inspection routes facilitates comprehensive coverage and real-time monitoring of wind farm equipment and areas, improving inspection efficiency and accuracy. Integrating image analysis, temperature analysis, vibration analysis, data fusion, and anomaly detection modules enables comprehensive analysis and processing of wind turbine data, enhancing accuracy and reliability. Furthermore, combining historical and real-time data allows for accurate prediction and rapid diagnosis of wind turbine faults. Attached Figure Description

[0033] Figure 1 This is a flowchart of a remote monitoring system for wind power airport stations based on artificial intelligence, according to the present invention. Detailed Implementation

[0034] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. In addition, the forms of the various structures described in the following embodiments are merely illustrative. The remote monitoring system for wind power airport stations based on artificial intelligence involved in the present invention is not limited to the structures described in the following embodiments. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0035] like Figure 1 The embodiment shown provides an artificial intelligence-based remote monitoring system for wind power station, including:

[0036] Inspection area division module: The station is divided into several inspection sub-areas according to the type of equipment in the new energy station, and numbered as 1, 2, 3...n respectively.

[0037] In this embodiment, the inspection area division module divides the wind power airport station into several relatively independent inspection sub-areas according to the type of equipment. Each inspection sub-area should contain a certain number of wind power equipment of the same type. Each divided inspection sub-area is numbered, starting from 1 and increasing sequentially until n.

[0038] It should be noted that, based on the type and distribution of equipment within the new energy power station, the station is divided into multiple inspection sub-areas. When dividing the inspection sub-areas, terrain, climate, and traffic must be considered. As the station's operating time increases and the equipment ages, the division of inspection sub-areas needs to be dynamically adjusted.

[0039] Inspection route planning module: By using artificial intelligence algorithms to automatically plan inspection routes for intelligent inspection equipment within the divided inspection sub-areas, the new energy power stations are then inspected according to the planned inspection routes.

[0040] In this embodiment, the inspection route planning module selects a drone equipped with a high-definition camera, an infrared thermal imager, and sensors as the intelligent inspection equipment for the new energy power station. Using path optimization algorithms in artificial intelligence, combined with the equipment distribution and road conditions within the inspection sub-area, the module intelligently plans and adjusts the drone's inspection route in real time, automatically generates the optimal inspection route, and then enables the drone to inspect the inspection sub-area within the new energy power station according to the planned inspection route.

[0041] It should be noted that when planning inspection routes, the battery life of the inspection equipment, the priority of the inspection tasks, and historical data on equipment failures should be taken into account. If equipment failures or road congestion are encountered, the inspection route should be adjusted in real time through artificial intelligence algorithms.

[0042] Inspection data acquisition module: Used to collect images, temperature data and vibration data of wind power equipment in each inspection sub-area. It collects images, temperature data and vibration data of wind power equipment in the inspection sub-area through drones and uploads the collected images, temperature data and vibration data of wind power equipment to the cloud server for processing.

[0043] In this embodiment, the inspection data acquisition module activates the drone and collects inspection data for each sub-area according to a preset inspection route. The collected images, temperature data, and vibration data are then uploaded to a cloud server in real time via the drone's wireless transmission module. The cloud server performs noise reduction, image enhancement, and data cleaning on the images, temperature data, and vibration data. The specific data acquisition process includes:

[0044] By using drones equipped with high-resolution cameras to fly over wind farms, detailed visual inspections of wind power equipment are conducted, capturing real-time images of the equipment's appearance. Thermal imagers and vibration sensors installed on the drones are used to collect real-time temperature and vibration data of the equipment.

[0045] It should be specifically explained that the inspection task is issued to the drone through the remote monitoring system, including the inspection route and data collection; when the drone receives the task, it takes off automatically and flies along the preset route. After the drone reaches the designated location, it automatically adjusts its attitude, activates the sensors and high-definition camera to collect data, and then the cloud server receives the drone's location information and the collected data in real time.

[0046] Preliminary Analysis Module: By analyzing the images, temperature data, and vibration data of wind power equipment in the inspection sub-area, the module obtains the blade appearance condition index, tower appearance change index, temperature fluctuation index, and equipment wear impact index. It includes an image analysis unit, a temperature analysis unit, and a vibration analysis unit.

[0047] In this embodiment, the preliminary analysis module collaboratively analyzes the images, temperature data, and vibration data of the wind power equipment in each inspection sub-area, thereby monitoring the characteristic change trend of the wind power equipment in the inspection sub-area in real time.

[0048] The image analysis unit uses deep learning algorithms to perform feature analysis on equipment images during wind power operation and calculates the blade appearance condition index and tower appearance change index, thereby automatically identifying blade appearance damage and tower appearance defects.

[0049] The temperature analysis unit analyzes the temperature change trend of wind power equipment in the inspection sub-area and calculates the temperature fluctuation index.

[0050] The vibration analysis unit analyzes the vibration data of wind power equipment operating in the inspection sub-area, including wind speed, wind direction, vibration frequency, and external wind pressure, and calculates the equipment wear impact index.

[0051] It should be specifically noted that the image analysis unit uses deep learning algorithms to analyze the leaf appearance condition index in the following way:

[0052] Step S411: Identify the total area A of the damaged leaf region in the image by training a damage recognition model. ij ;

[0053] Step S412: By using a deep learning model to compare the difference between the actual shape and the standard shape of the blade, the blade shape deviation is obtained. (x ijk yijk (x) represents the k-th corresponding point on the blade profile of the j-th wind turbine in the i-th inspection sub-region, obtained from actual measurements. i ′ jk y i ′ jk ) represents the k-th point on the ideal blade profile of the j-th wind turbine in the i-th inspection sub-region, and K represents the total number of points on the blade profile;

[0054] Step S413: By analyzing the area A of the damaged blade region of each wind turbine within the inspection sub-region... ij And the degree of deviation of blade shape SI ij The analysis was performed, and the blade appearance condition index was calculated to be C. ij =w1×A ij +w2×M×SI ij M represents the total number of blades in a wind turbine.

[0055] The image analysis unit uses deep learning algorithms to analyze the tower appearance change index in the following way:

[0056] Step S421: Extract image features using a pre-trained deep learning model;

[0057] Step S422: Compare the tower image features at different time points to identify changes in appearance;

[0058] Step S423: Assume f ij0 and f ij1 These are the feature vectors extracted at time points t0 and t1, respectively, from which the tower appearance change index is calculated. ||f ij1 -f ij0 ||1 represents vector f ij0 and f ij1 The distance from L1 Manhattan, ||f ij1 -f ij0 ||2 represents vector f ij0 and f ij1 The distance to L2 Manhattan;

[0059] The specific formula for calculating the temperature fluctuation index is as follows: T ij This represents the operating temperature of the j-th wind turbine in the i-th inspection sub-region. This represents the average operating temperature of all wind power equipment within the i-th inspection sub-region;

[0060] The specific formula for calculating the equipment wear factor index is D. ij =f(v ij d ij rij p i ), v ij d represents the wind speed of the j-th wind turbine in the i-th inspection sub-region. ij r represents the wind direction of the j-th wind turbine in the i-th inspection sub-region. ij p represents the vibration frequency of the j-th wind turbine in the i-th inspection sub-region. i This represents the external wind pressure experienced by the i-th inspection sub-region.

[0061] Data fusion module: By performing data fusion calculations on the data analysis results in the preliminary analysis module, the risk assessment coefficient for abnormal equipment condition is obtained.

[0062] In this embodiment, the data fusion module first standardizes the data of the blade appearance condition index, tower appearance change index, temperature fluctuation index, and equipment wear impact index, and then performs fusion calculation to obtain the specific calculation formula for the equipment condition abnormality risk assessment coefficient, which is Q. ij =ln(C ij +a)×ln(I ij +a)×ln(T′ ij +a)×ln(D ij +a), C ij I represents the blade appearance condition index. ij T′ represents the tower appearance change index. ij D represents the temperature fluctuation index. ij This represents the influence index of equipment wear, where 'a' represents a constant.

[0063] Anomaly Detection Module: Based on the results of data fusion, the module compares the equipment condition anomaly risk assessment coefficient with the equipment condition anomaly risk threshold to detect anomalies in the wind power equipment within the inspection sub-area and transmits the anomaly detection results to the fault prediction module.

[0064] In this embodiment, the anomaly detection module sets an abnormal equipment condition risk threshold θ for the wind power equipment in each inspection sub-area. i The risk assessment coefficient Q for abnormal equipment condition is... ij With the equipment condition abnormality risk threshold θ i Comparisons are made to detect abnormal wind power equipment within the inspection sub-area; when the equipment condition is abnormal, the risk assessment coefficient Q is used. ij ≤Equipment abnormality risk threshold θ i When this occurs, it indicates that no abnormal wind power equipment has been found in the inspected sub-area. Monitoring and analysis will continue. When the equipment condition abnormality risk assessment coefficient Q... ij >Equipment abnormality risk threshold θ iWhen the error occurs, it indicates that there is an abnormal problem with a single wind turbine in the inspection sub-area. All wind turbines with abnormal problems in the inspection sub-area are then selected and the selection results are transmitted to the fault prediction module.

[0065] Fault prediction module: Based on the detection results of the anomaly detection module, the historical power generation, voltage and current are combined with the real-time power generation, voltage and current for analysis, and the fault prediction coefficient is calculated to predict the faults of abnormal wind power equipment in the inspection sub-area.

[0066] In this embodiment, the fault prediction module performs a difference analysis by collecting historical average power generation, average voltage, and average current of each abnormal wind power device over a historical period, and real-time power generation, voltage, and current, and calculates the fault prediction coefficient. G im，实时 R represents the real-time power generation of the m-th abnormal wind turbine in the i-th inspection sub-region. im，实时 V represents the real-time current measured by the m-th abnormal wind turbine in the i-th inspection sub-region. im，实时 G represents the real-time voltage currently measured for the m-th abnormal wind power device in the i-th inspection sub-region. im，历史 R represents the historical average power generation of the m-th abnormal wind turbine in the i-th inspection sub-region. im，历史 V represents the historical average current of the m-th abnormal wind turbine in the i-th inspection sub-region. im，历史 This represents the historical average voltage of the m-th abnormal wind power device in the i-th inspection sub-region. This represents the standard deviation of the historical power generation of the m-th abnormal wind power device in the i-th inspection sub-region. This represents the standard deviation of the historical current of the m-th abnormal wind power device in the i-th inspection sub-region. It represents the standard deviation of the historical voltage of the m-th abnormal wind power equipment in the i-th inspection sub-region.

[0067] Fault diagnosis module: Based on the results of fault prediction, fault diagnosis is performed on abnormal wind power equipment in the inspection sub-area.

[0068] In this embodiment, the fault diagnosis module uses the fault prediction coefficient H im Compared with the preset fault threshold λ i By comparing the results, it can be determined whether there is a fault in the abnormal wind power equipment within the inspection sub-area. If the fault prediction coefficient H im >Preset fault threshold λ i If the abnormal wind power equipment in the inspection sub-area does not have a fault, then the abnormal wind power equipment needs to be monitored closely. If the fault prediction coefficient H im >Preset fault threshold λ iIf the fault is detected, it is determined that a single abnormal wind power device in the inspection sub-area has a fault problem, and the fault diagnosis result is immediately fed back to the result feedback module.

[0069] Remote monitoring module: By setting up a remote monitoring platform, it automatically generates wind power equipment inspection and monitoring reports, and transmits the fault diagnosis results of wind power equipment to the remote monitoring platform through the cloud server to provide early warning feedback to the management personnel.

[0070] In this embodiment, the remote monitoring module is used to receive automatically generated wind power equipment inspection and monitoring reports and wind power equipment fault diagnosis results transmitted from the cloud server. Managers can view the operating status and inspection results of new energy power stations anytime and anywhere through the remote monitoring platform, and receive early warning results, thereby realizing remote monitoring and management.

[0071] It should be noted that the fault diagnosis results and wind power equipment inspection and monitoring reports are automatically generated by the system and then transmitted to the remote monitoring platform via the cloud server. The remote monitoring platform displays real-time data and statistical analysis results, including power generation trend charts, equipment health status curves, and fault alarm responses. Managers can log in to the platform to view the wind farm's operating status, inspection reports, and fault diagnosis results. Managers are also allowed to remotely execute control commands, including starting and stopping equipment and adjusting parameters, thereby remotely scheduling inspection tasks and viewing inspection progress and results.

[0072] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0073] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A remote monitoring system for wind power station based on artificial intelligence, characterized in that: include: Inspection area division module: The station is divided into several inspection sub-areas according to the type of equipment in the new energy station, and numbered as 1, 2, 3...n respectively; Inspection route planning module: By using artificial intelligence algorithms to automatically plan inspection routes for intelligent inspection equipment within the divided inspection sub-areas, the new energy power stations are then inspected according to the planned inspection routes. Inspection data acquisition module: used to collect images, temperature data and vibration data of wind power equipment in each inspection sub-area. It collects images, temperature data and vibration data of wind power equipment in the inspection sub-area through drones and uploads the collected images, temperature data and vibration data of wind power equipment to the cloud server for processing. Preliminary Analysis Module: By analyzing the images, temperature data, and vibration data of wind power equipment in the inspection sub-area, the module obtains the blade appearance condition index, tower appearance change index, temperature fluctuation index, and equipment wear impact index. It includes an image analysis unit, a temperature analysis unit, and a vibration analysis unit. Data fusion module: By performing data fusion calculations on the data analysis results in the preliminary analysis module, the risk assessment coefficient for abnormal equipment condition is obtained; The data fusion module first standardizes the data of the blade appearance condition index, tower appearance change index, temperature fluctuation index, and equipment wear impact index, and then performs fusion calculations to obtain the specific calculation formula for the equipment condition anomaly risk assessment coefficient. , This indicates the index of blade appearance condition. Indicates the tower appearance change index, Indicates the temperature fluctuation index. This represents the influence index of equipment wear, where 'a' represents a constant. Anomaly Detection Module: Based on the results of data fusion, the module compares the risk assessment coefficient of equipment condition anomaly with the risk threshold of equipment condition anomaly, thereby performing anomaly detection on wind power equipment in the inspection sub-area and transmitting the anomaly detection results to the fault prediction module. The anomaly detection module sets an equipment condition anomaly risk for each wind power device in each inspection sub-area. The risk assessment coefficient for abnormal equipment condition Risk threshold for abnormal equipment condition By making comparisons, abnormal wind power equipment within the inspected sub-area can be detected; When the equipment condition is abnormal, the risk assessment coefficient When the equipment condition abnormality risk threshold is reached, it indicates that no abnormal wind power equipment has been found in the inspected sub-area. Monitoring and analysis will continue. When the equipment condition abnormality risk assessment coefficient... Equipment abnormality risk threshold When this occurs, it indicates that there is an abnormal problem with a single wind turbine in the inspection sub-area, and all wind turbines with abnormal problems in the inspection sub-area are screened out and the screening results are transmitted to the fault prediction module. Fault prediction module: Based on the detection results of the anomaly detection module, the historical power generation, voltage and current are combined with the real-time power generation, voltage and current for analysis, and the fault prediction coefficient is calculated to predict the faults of abnormal wind power equipment in the inspection sub-area. The fault prediction module performs a difference analysis by collecting historical average power generation, average voltage, and average current of each abnormal wind turbine over a historical period, and comparing them with real-time power generation, voltage, and current, and calculates the fault prediction coefficient. , This represents the real-time power generation currently measured by the m-th abnormal wind power device in the i-th inspection sub-region. This represents the real-time current measured by the m-th abnormal wind power device in the i-th inspection sub-region. This represents the real-time voltage currently measured for the m-th abnormal wind power device in the i-th inspection sub-region. This represents the historical average power generation of the m-th abnormal wind turbine in the i-th inspection sub-region. Let represent the historical average current of the m-th abnormal wind power device in the i-th inspection sub-region. This represents the historical average voltage of the m-th abnormal wind power device in the i-th inspection sub-region. This represents the standard deviation of the historical power generation of the m-th abnormal wind power device in the i-th inspection sub-region. This represents the standard deviation of the historical current of the m-th abnormal wind power device in the i-th inspection sub-region. This represents the standard deviation of the historical voltage of the m-th abnormal wind power device in the i-th inspection sub-region; Fault diagnosis module: Based on the results of fault prediction, fault diagnosis is performed on abnormal wind power equipment in the inspection sub-area; The fault diagnosis module uses fault prediction coefficients. Compared with the preset fault threshold By comparing the results, it can be determined whether there is a fault in the abnormal wind power equipment within the inspection sub-area. If the fault prediction coefficient... Preset fault threshold If the abnormal wind power equipment in the inspection sub-area does not have a fault, then the abnormal wind power equipment needs to be monitored closely. If the fault prediction coefficient is... Preset fault threshold If the fault is detected, it is determined that a single abnormal wind power device in the inspection sub-area has a fault problem, and the fault diagnosis result is immediately fed back to the result feedback module. Remote monitoring module: By setting up a remote monitoring platform, it automatically generates wind power equipment inspection and monitoring reports, and transmits the fault diagnosis results of wind power equipment to the remote monitoring platform through the cloud server to provide early warning feedback to the management personnel.

2. The remote monitoring system for wind power station based on artificial intelligence according to claim 1, characterized in that: The inspection area division module divides the wind power airport station into several relatively independent inspection sub-areas according to the type of equipment. Each inspection sub-area should contain a certain number of wind power equipment of the same type. Each divided inspection sub-area is numbered, starting from 1 and increasing sequentially until n.

3. The remote monitoring system for wind power station based on artificial intelligence according to claim 1, characterized in that: The inspection route planning module selects drones equipped with high-definition cameras, infrared thermal imagers, and sensors as intelligent inspection equipment for new energy power stations. Utilizing path optimization algorithms in artificial intelligence, and combining the equipment distribution and road conditions within the inspection sub-area, it intelligently plans and adjusts the drone's inspection route in real time, automatically generating the optimal inspection route. The drone then inspects the inspection sub-area within the new energy power station according to the planned inspection route.

4. The remote monitoring system for wind power station based on artificial intelligence according to claim 1, characterized in that: The inspection data acquisition module activates the drone and collects inspection data for each sub-area according to a preset inspection route. The collected images, temperature data, and vibration data are then uploaded to a cloud server in real time via the drone's wireless transmission module. The cloud server performs noise reduction, image enhancement, and data cleaning on the images, temperature data, and vibration data. The specific data acquisition process includes: By using drones equipped with high-resolution cameras to fly over wind farms, detailed visual inspections of wind power equipment can be carried out, capturing real-time images of the equipment's appearance. Thermal imagers and vibration sensors installed on the drones can also collect real-time temperature and vibration data of the equipment.

5. The remote monitoring system for wind power station based on artificial intelligence according to claim 1, characterized in that: The preliminary analysis module monitors the characteristic change trends of wind power equipment in each inspection sub-area in real time by collaboratively analyzing the images, temperature data, and vibration data of the wind power equipment in each inspection sub-area. The image analysis unit uses deep learning algorithms to perform feature analysis on individual devices in the equipment images of wind turbines during operation and calculates the blade appearance condition index. Tower appearance change index This allows for the automatic identification of blade surface damage and tower surface defects. The temperature analysis unit analyzes the temperature change trend of individual wind power equipment operating within the inspection sub-region and calculates the temperature fluctuation index. ; The vibration analysis unit analyzes the vibration data of individual wind turbines operating within the inspection sub-region, including wind speed, wind direction, vibration frequency, and external wind pressure, and calculates the equipment wear impact index. .

6. The remote monitoring system for wind power station based on artificial intelligence according to claim 1, characterized in that: The remote monitoring module is used to receive automatically generated wind power equipment inspection and monitoring reports and wind power equipment fault diagnosis results transmitted from the cloud server. Managers can view the operation status and inspection results of new energy power stations anytime and anywhere through the remote monitoring platform, and receive early warning results, thereby realizing remote monitoring and management.

Images