Intelligent ocean wind power inspection system and operation method thereof

Through the intelligent marine wind power inspection system, independent navigation unmanned ships and multiple sensors are used to generate real-time monitoring and maintenance suggestions for wind farms, solving the safety risks and low efficiency of traditional manual inspections, and achieving efficient and accurate Fan monitoring and maintenance.

CN119005945AInactive Publication Date: 2024-11-22XIAMEN YINHAITU MARINE TECH CO LTD

Patent Information

Application Number
CN202411083066.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-08
Publication Date
2024-11-22
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Traditional marine wind farm maintenance relies on manual inspection, which poses safety risks, is time-consuming and labor-intensive, and lacks autonomy, energy efficiency and data processing capabilities, making it difficult to achieve efficient and accurate fan monitoring and maintenance.

Method used

Design an intelligent marine wind power patrol system, equipped with autonomous navigation unmanned ships and a variety of sensors, including cameras, infrared thermal imagers, lidars, ultrasonic flaw detectors and meteorological sensors, and the central control unit performs data processing and analysis to generate patrols Inspection reports and maintenance recommendations, and use wireless communication modules and energy management modules to achieve data transmission and power supply.

Benefits of technology

It greatly reduces the dependence on manual operation, improves patrol safety and efficiency, realizes real-time monitoring and maintenance suggestions for fans, reduces operation and maintenance costs, and improves the operating efficiency and equipment life of the wind farm.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119005945A_ABST
    Figure CN119005945A_ABST
Patent Text Reader

Abstract

The invention provides an intelligent ocean wind power inspection system and an operation method thereof, and the system comprises an unmanned ship which is provided with a plurality of sensors for detecting offshore wind turbines; the central control unit is installed on the unmanned ship and used for receiving and processing detection data from the multiple sensors and generating inspection reports and maintenance suggestions according to the detection data of the multiple sensors and a preset algorithm; the wireless communication module is mounted on the unmanned ship and used for transmitting data and control instructions among the unmanned ship, the central control unit and the shore-based station; the energy management module is mounted on the unmanned ship and used for supplying power to the unmanned ship, the central control unit, the wireless communication module, the autonomous navigation module and the various sensors; and the autonomous navigation module is mounted on the unmanned ship and is used for realizing autonomous navigation and obstacle avoidance of the unmanned ship by adopting various navigation devices. According to the invention, efficient, automatic and safe maintenance operation of the ocean wind power plant can be realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of marine wind power detection, and in particular to an intelligent marine wind power inspection system and an operation method thereof. Background Art

[0002] As the global demand for renewable energy grows, offshore wind power has been widely developed and applied as an important clean energy source. Offshore wind farms are usually located far offshore. Due to the harsh environmental conditions and high maintenance costs, conventional wind turbine inspection and maintenance work faces great challenges. In addition, the operating status of wind turbines is directly related to energy output efficiency and equipment life, so efficient and accurate monitoring and maintenance methods are required to ensure their long-term stable operation.

[0003] Traditional wind farm maintenance relies on manual inspections, which is not only time-consuming and labor-intensive, but also carries a high safety risk when performing such operations in an offshore environment. With the advancement of technology, unmanned ships and automated detection technologies have been proposed to improve such problems, but there is still room for improvement, especially in terms of autonomy, energy efficiency, and data processing capabilities. Summary of the invention

[0004] In view of this, an object of an embodiment of the present invention is to provide an intelligent marine wind power inspection system and an operation method thereof to solve the above technical problems.

[0005] To achieve the above objectives, in a first aspect, the present invention provides an intelligent marine wind power inspection system, which comprises:

[0006] The autonomous unmanned boat is equipped with a variety of sensors for detecting offshore wind turbines; the sensors include: a camera for obtaining visible light image data of the external structure of the wind turbine; an infrared thermal imager for obtaining temperature distribution data inside the wind turbine; a laser radar for obtaining three-dimensional point cloud data of the wind turbine structure; an ultrasonic flaw detector for obtaining defect and damage data of the wind turbine foundation and underwater structure; and a meteorological sensor for obtaining environmental perception data including wind speed, wind direction, temperature and humidity.

[0007] A central control unit, installed on the unmanned vessel, for receiving and processing detection data from a variety of sensors, and generating inspection reports and maintenance recommendations based on the detection data from the multiple sensors and a preset algorithm;

[0008] A wireless communication module, installed on the unmanned ship, for transmitting data and control instructions between the unmanned ship, the central control unit and the shore base station;

[0009] An energy management module, installed on the unmanned ship, for supplying power to the unmanned ship, the central control unit, the wireless communication module, the autonomous navigation module and the various sensors;

[0010] An autonomous navigation module, installed on the unmanned ship, is used to use a variety of navigation equipment to achieve autonomous navigation and obstacle avoidance of the unmanned ship;

[0011] Wherein, the central control unit comprises:

[0012] An image processing module, used to analyze the visible light image data acquired by the camera, detect and locate blade defects including cracks on the blade surface or falling fragments;

[0013] A hot spot analysis module, used to analyze the temperature distribution data obtained by the infrared thermal imager to identify abnormally high temperature areas inside the fan;

[0014] A structural assessment module, used to analyze the three-dimensional point cloud data acquired by the laser radar to assess the integrity and deformation of the structure including the tower and blades of the wind turbine;

[0015] A defect diagnosis module, used to analyze the defect and damage data obtained by the ultrasonic flaw detector to determine the health status of the wind turbine foundation and underwater structure;

[0016] The environmental monitoring module is used to analyze the environmental perception data obtained by the meteorological sensor and evaluate the impact of environmental factors on the operation of the wind turbine.

[0017] In some possible implementations, the central control unit further includes:

[0018] A data fusion module, used for comprehensively analyzing the analysis results of the image processing module, the hot spot analysis module, the structure assessment module, the defect diagnosis module and the environmental monitoring module, and generating a comprehensive health assessment report of the wind turbine;

[0019] The maintenance decision module is used to generate maintenance suggestions for the wind turbine according to the comprehensive health assessment report of the wind turbine and the preset maintenance strategy, wherein the maintenance suggestions include maintenance priority, maintenance method and maintenance time.

[0020] In some possible implementations, the autonomous navigation module adopts an intelligent decision-making algorithm based on reinforcement learning to obtain the environmental perception data and inspection task requirements from the meteorological sensor and autonomously plan the optimal inspection route.

[0021] In some possible implementations,

[0022] The image processing module is specifically used to adopt a deep learning algorithm based on a convolutional neural network to establish a defect detection model by training multiple wind turbine blade image data; extract features including any multiple of texture, edge, and color in the visible light image data based on the defect detection model, and realize the recognition and positioning of blade defects through multi-level feature fusion and classification;

[0023] The hot spot analysis module is specifically used to identify the high temperature area in the temperature distribution map by using an image segmentation algorithm based on a heat map, and calculate the parameters of the high temperature area including the area, average temperature and maximum temperature;

[0024] The structural assessment module is specifically used to align and compare the three-dimensional point cloud data of the wind turbine collected at different times, and quantitatively analyze the deformation degree of the structure by using an algorithm based on three-dimensional reconstruction and deformation analysis;

[0025] The defect diagnosis module is specifically used to identify the defect echo signal in the ultrasonic image data by using an algorithm based on acoustic wave image analysis algorithm and pattern recognition, and judge the type, location and severity of the defect according to the characteristics of the defect echo signal including any one of intensity, frequency and attenuation; wherein the ultrasonic image data refers to the defect and damage data obtained by the ultrasonic flaw detector;

[0026] The environmental monitoring module is specifically used to extract the meteorological characteristic pattern of the wind farm from the environmental perception data by adopting an algorithm based on time series analysis and data mining, and to analyze the correlation between the meteorological characteristic pattern and the performance of the wind turbine.

[0027] In some possible implementations, the data fusion module is specifically used to use a multi-source data fusion algorithm based on a Bayesian network to associate and fuse the analysis results of the image processing module, the hot spot analysis module, the structure assessment module, the defect diagnosis module and the environmental monitoring module, to obtain the health status scores of each component of the wind turbine and the whole machine, and to generate a comprehensive health assessment report;

[0028] The maintenance decision module is specifically used to adopt an intelligent decision-making algorithm based on case reasoning and a rule engine, and to establish a maintenance decision rule library by learning and summarizing historical maintenance cases; when a comprehensive health assessment report of the wind turbine is generated, similar historical cases are automatically matched, and maintenance recommendations for the wind turbine are generated according to preset decision rules.

[0029] In some possible implementations, the maintenance decision module is specifically used to:

[0030] Extract and represent the features of historical maintenance cases and establish a case feature library. The features of each case include the model, operating time, health status, failure mode, maintenance measures and maintenance effect of the wind turbine.

[0031] After the comprehensive health assessment report of the current wind turbine is generated, the feature vector of the wind turbine is extracted, and similarity calculation is performed with the historical cases in the case feature library; wherein the similarity calculation adopts a K nearest neighbor algorithm or a similarity weighted algorithm;

[0032] According to the distance or correlation between the feature vectors, find the K historical cases that are most similar to the current wind turbine status.

[0033] In some possible implementations, the multiple navigation devices include a global positioning system, a radar, and a sonar; the unmanned ship is a catamaran with a deck platform connected between the two hulls; and the central control unit is an industrial computer or an embedded computer.

[0034] In a second aspect, the present invention provides an operation method of the intelligent marine wind power inspection system as described above, which comprises the following steps:

[0035] Use the autonomous navigation module on the unmanned ship and adopt a variety of navigation equipment to achieve autonomous navigation and obstacle avoidance of the unmanned ship;

[0036] Using a variety of sensors on the unmanned ship to detect offshore wind turbines and collect detection data;

[0037] Transmitting the detection data to a central control unit on the unmanned vessel;

[0038] In the central control unit, based on the received detection data and the preset algorithm, the data is processed and an inspection report and maintenance recommendations are generated;

[0039] Using the wireless communication module on the unmanned vessel, the generated inspection report and maintenance suggestions are transmitted to a shore base station;

[0040] The energy management module on the unmanned ship is used to power the unmanned ship, the central control unit, the wireless communication module, the autonomous navigation module and various sensors.

[0041] The above technical solution has the following beneficial effects:

[0042] By equipping the unmanned ship with an autonomous navigation module, the unmanned ship can use a variety of navigation equipment to automatically navigate and avoid obstacles, greatly reducing dependence on manual operation and improving the safety and efficiency of inspection operations.

[0043] The central control unit in the present invention can receive and process detection data from various sensors in real time, which are specially used to detect the key components and operating conditions of wind turbines. The system can also automatically generate detailed inspection reports and maintenance suggestions based on preset algorithms, providing a scientific basis for the operation and maintenance of wind farms.

[0044] In the present invention, through the wireless communication module, the real-time transmission of data and control instructions can be achieved between the unmanned ship, the central control unit and the shore base station, ensuring the real-time and accuracy of information exchange.

[0045] The energy management module in the present invention includes solar panels and energy storage devices, which can provide continuous and stable green energy for the unmanned ship and various equipment thereon, reduce dependence on fossil energy, reduce operation and maintenance costs, and reduce environmental impact. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. It is obvious that the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 It is a functional block diagram of an intelligent marine wind power inspection system according to an embodiment of the present invention;

[0048] Figure 2 It is a specific functional block diagram of the intelligent marine wind power inspection system according to an embodiment of the present invention;

[0049] Figure 3 It is another specific functional block diagram of the intelligent marine wind power inspection system according to an embodiment of the present invention;

[0050] Figure 4 It is a flow chart of an operation method of an intelligent marine wind power inspection system according to an embodiment of the present invention;

[0051] Figure 5 It is a functional block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] like Figure 1 As shown, an embodiment of the present invention provides an intelligent marine wind power inspection system, which includes:

[0054] Autonomous unmanned boats equipped with a variety of sensors for detecting offshore wind turbines;

[0055] The central control unit is installed on the unmanned ship and is used to receive and process the detection data from various sensors, and generate inspection reports and maintenance suggestions based on the detection data of various sensors and preset algorithms;

[0056] A wireless communication module, installed on the unmanned ship, is used to transmit data and control instructions between the unmanned ship, the central control unit and the shore base station;

[0057] Energy management module, installed on the unmanned ship, used to power the unmanned ship, central control unit, wireless communication module, autonomous navigation module and various sensors;

[0058] The autonomous navigation module is installed on the unmanned ship and is used to adopt a variety of navigation equipment to realize the autonomous navigation and obstacle avoidance of the unmanned ship.

[0059] In some embodiments, the plurality of navigation devices include GPS (Global Positioning System), radar and sonar. The energy management module may include solar panels and energy storage devices.

[0060] In some embodiments, the multiple sensors include: a camera for acquiring visible light image data of the external structure of the fan; an infrared thermal imager for acquiring temperature distribution data inside the fan; a lidar for acquiring three-dimensional point cloud data of the fan structure; an ultrasonic flaw detector for acquiring defect and damage data of the fan foundation and underwater structure; and a meteorological sensor for acquiring environmental perception data including wind speed, wind direction, temperature and humidity.

[0061] Specifically, in the intelligent marine wind power inspection system provided in the embodiment of the present invention, the autonomous unmanned ship is the core platform of the entire system, which is equipped with a variety of sensors for wind turbine detection, a central control unit for data processing and analysis, a wireless communication module, an energy management module, and an autonomous navigation module and other key components, which work together to realize intelligent inspection of offshore wind farms.

[0062] The design of an unmanned ship needs to comprehensively consider factors such as navigation stability, endurance, and load capacity. In a specific embodiment, the unmanned ship adopts a catamaran design, and a deck platform for carrying various equipment is connected between the two hulls. The catamaran design can provide better stability and load capacity, and is suitable for performing tasks at sea for a long time. The power system of the unmanned ship can adopt electric propulsion, and the energy storage device in the energy management module provides electrical energy. Installing solar panels on the deck can continuously replenish electrical energy during navigation and extend the endurance time.

[0063] The various sensors carried on the unmanned boat are the key to wind turbine inspection. Among them, the high-definition camera is used to obtain visible light images of the external structure of the wind turbine. By analyzing the texture, color and other features in the image, defects such as cracks and falling debris on the blade surface can be detected. For example, when cracks appear on the surface of the blade, a linear texture that is significantly different from the surrounding area will appear on the image; when debris falls off the surface of the blade, irregular color patches will appear on the image. By training appropriate image recognition algorithms, the central control unit can automatically detect and locate these defects.

[0064] Infrared thermal imagers can obtain temperature distribution data inside the fan. The fan includes key components such as generators, gearboxes, and converters, which generate a lot of heat during long-term operation. By analyzing the temperature distribution inside the fan, some abnormal conditions can be discovered in time, such as excessively high generator winding temperature, local overheating caused by poor lubrication of the gearbox, etc. For example, the surface temperature of a normally working gearbox is usually between 60-70°C. If the infrared thermal imager finds that the temperature of a certain area is significantly higher than that of other areas, and the temperature exceeds 80°C, it indicates that there is a problem with the lubrication of that area and it needs to be repaired as soon as possible to avoid further damage.

[0065] LiDAR can obtain three-dimensional point cloud data of wind turbine structures. By analyzing the point cloud data, the integrity and deformation of wind turbine towers, blades and other structures can be comprehensively evaluated. For example, by comparing the three-dimensional models of wind turbines obtained at different times, structural problems such as the bending deformation of the tower and the twisting deformation of the blades can be quantitatively analyzed. In a specific embodiment, the LiDAR carried on the unmanned ship can scan 360 degrees around the wind turbine to obtain high-density point cloud data. Through point cloud splicing and three-dimensional reconstruction algorithms, a detailed three-dimensional model of the wind turbine is generated, and compared and analyzed with the design model to quantitatively evaluate the degree of deformation of the structure.

[0066] Ultrasonic flaw detectors are mainly used to detect defects and damage in wind turbine foundations and underwater structures. The wind turbine foundation is cast with high-strength concrete and equipped with a steel cage inside. During the long-term operation of the wind turbine, problems such as concrete cracking and steel corrosion may occur inside the foundation, resulting in a decrease in foundation strength and affecting the safety of the wind turbine. By arranging ultrasonic probes on the surface of the foundation, it is possible to obtain an acoustic wave image inside the foundation and analyze information such as the density of the concrete, the location and size of internal defects. For example, when cracks appear inside the concrete, the ultrasonic wave will produce an obvious reflection signal; when the steel is corroded, the propagation speed of the sound wave will change. By analyzing the characteristics of these acoustic wave signals, health problems of the foundation can be discovered in a timely manner.

[0067] Meteorological sensors can obtain environmental parameters of wind farms, such as wind speed, wind direction, temperature, humidity, etc. By analyzing these environmental data, the meteorological characteristics of wind farms can be mastered and the impact of environmental factors on wind turbine operation can be evaluated. For example, when the wind speed is too high or the wind direction changes suddenly, the wind turbine blades will bear a large load, and long-term operation may aggravate the fatigue damage of the blades. By real-time monitoring of wind speed and direction, combined with the operation data of the wind turbine, the control strategy of the wind turbine can be optimized to improve the power generation efficiency while ensuring safety. In addition, environmental parameter data can also be used to optimize the inspection route of unmanned ships. For example, in windy weather, unmanned ships can adjust their routes appropriately to avoid areas with large winds and waves to ensure their own navigation safety.

[0068] A central control unit is also installed on the unmanned ship for comprehensive processing and analysis of data collected by various sensors. The central control unit can use a high-performance industrial computer or embedded computer, equipped with a high-speed processor, a large-capacity storage device and a variety of interfaces, which can realize real-time processing and storage of data. For example, in a specific embodiment, the central control unit uses an Intel Core i7 processor, equipped with 16GB of memory and a 1TB solid-state hard drive, which can meet the operating requirements of various algorithms.

[0069] Based on the analysis and processing of multiple sensor data, the central control unit can generate inspection reports and maintenance recommendations for the wind turbine. Inspection reports usually include an overall health assessment of the wind turbine, the test results of each component, detailed descriptions of defects and anomalies, etc., which are used to comprehensively evaluate the technical status of the wind turbine. For example, during an inspection, the camera found a 30-centimeter-long crack on the trailing edge of blade No. 2 of a wind turbine, the infrared thermal imager found that the local temperature of the gearbox reached 85°C, and the ultrasonic flaw detector found a through crack in the middle of the foundation. After comprehensively analyzing these data, the central control unit evaluated the health status of the wind turbine as "serious warning", and described each defect in detail in the inspection report, prompting the operation and maintenance personnel to deal with it as soon as possible.

[0070] While generating the inspection report, the central control unit can also give corresponding maintenance suggestions, including recommended maintenance measures, priorities, time windows, etc. For example, in response to the above-mentioned wind turbine problem, the maintenance suggestions given by the central control unit may include: repair or replace blade No. 2, which is recommended to be completed within 1 week; check the lubrication system of the gearbox and replace the lubricating oil if necessary, which is recommended to be completed within 2 weeks; grouting repairs to foundation cracks, which is recommended to be completed within 1 month. These maintenance suggestions can help the operation and maintenance team formulate a detailed work plan and carry out wind turbine maintenance work in an orderly manner.

[0071] The wireless communication module on the unmanned boat is used for data exchange and remote control with the shore base station. During the inspection process, the unmanned boat transmits the collected data to the shore base station in real time through the wireless communication module and receives control instructions from the shore base station. For example, when the unmanned boat finds that a certain wind turbine has a serious fault, it will immediately send an alarm message to the shore base station. The shore base station can remotely control the unmanned boat to focus on monitoring the wind turbine and adjust subsequent inspection tasks.

[0072] The energy management module is the key to ensure that the unmanned ship can perform its mission for a long time. In one embodiment, the energy management module includes a large-area solar panel and a large-capacity lithium battery pack. The solar panel is used to generate electricity during the day and store the excess electricity in the lithium battery pack. At night or on rainy days, the unmanned ship is powered by the lithium battery pack. By reasonably designing the area of ​​the solar panel and the capacity of the lithium battery pack, the unmanned ship can be operated autonomously for a long time, reducing the need for manual maintenance.

[0073] The autonomous navigation module is the key to achieving autonomous navigation and obstacle avoidance for unmanned ships. The autonomous navigation module integrates satellite positioning systems such as GPS and Beidou, and combines obstacle detection equipment such as radar and sonar to achieve accurate positioning and obstacle avoidance of unmanned ships at sea. For example, in a specific embodiment, the unmanned ship is equipped with a differential GPS receiver, which can achieve centimeter-level positioning accuracy; it is also equipped with multi-beam sonar and lidar, which can achieve all-round detection of surface and underwater obstacles. The autonomous navigation module can independently plan a safe and efficient route by comprehensively analyzing these sensor data, combined with electronic nautical charts and route planning algorithms, and dynamically adjust the route to avoid collisions based on the obstacle information detected during navigation.

[0074] In summary, the intelligent marine wind power inspection system provided by the embodiment of the present invention can realize all-round, efficient and intelligent inspection of offshore wind farms by integrating multiple sensors, data processing, wireless communication, energy management, autonomous navigation and other functional modules on unmanned ships, timely discover wind turbine failures, provide reliable maintenance suggestions, reduce wind turbine downtime, and improve the overall operational efficiency of wind farms. Compared with the traditional manual inspection method, the embodiment of the present invention has the advantages of high inspection efficiency, low labor cost, diverse detection methods, intelligent data analysis, etc., and represents the development direction of offshore wind power operation and maintenance technology.

[0075] like Figure 2 As shown, in some embodiments, the central control unit includes:

[0076] An image processing module is used to analyze the visible light image data acquired by the camera to detect and locate blade defects including cracks on the blade surface or falling debris;

[0077] Hot spot analysis module, used to analyze the temperature distribution data obtained by the infrared thermal imager and identify abnormally high temperature areas inside the fan;

[0078] The structural assessment module is used to analyze the three-dimensional point cloud data obtained by the lidar to evaluate the integrity and deformation of the structure including the tower and blades of the wind turbine;

[0079] Defect diagnosis module, which is used to analyze the defect and damage data obtained by the ultrasonic flaw detector to determine the health status of the wind turbine foundation and underwater structure;

[0080] The environmental monitoring module is used to analyze the environmental perception data obtained by meteorological sensors and evaluate the impact of environmental factors on wind turbine operation.

[0081] In some embodiments of the present invention, the central control unit is one of the core components of the intelligent offshore wind power inspection system, and its main function is to comprehensively analyze and process the data collected by various sensors, evaluate the health status of the wind turbine, and generate inspection reports and maintenance recommendations. In order to achieve these functions, the central control unit adopts a modular design, including an image processing module, a hot spot analysis module, a structure assessment module, a defect diagnosis module, and an environmental monitoring module. The modules cooperate with each other to jointly complete the tasks of data analysis and wind turbine health assessment.

[0082] The image processing module is mainly used to analyze the visible light image data acquired by the camera, detect and locate defects on the surface of the wind turbine blades, such as cracks, falling debris, etc. In a specific embodiment, the image processing module adopts a deep learning algorithm based on a convolutional neural network (CNN), and establishes a high-precision defect detection model by training a large amount of wind turbine blade image data. The defect detection model can automatically extract features such as texture, edge, color, etc. in the image, and accurately identify and locate blade defects through multi-level feature fusion and classification. For example, when an unmanned ship inspects a wind turbine, the camera will take multiple high-definition images of the blades. The image processing module will automatically analyze these images, mark suspicious defect areas, and provide detailed information such as the type, location, and size of the defect for reference by maintenance personnel.

[0083] The hotspot analysis module is mainly used to analyze the temperature distribution data obtained by the infrared thermal imager and identify abnormally high temperature areas inside the fan. During the operation of the fan, key components such as the generator, gearbox, and converter will generate a lot of heat. If the heat dissipation is poor or the lubrication fails, local high temperature will occur. Long-term operation may cause component damage, affecting the power generation efficiency and safety of the fan. The hotspot analysis module uses an image segmentation algorithm based on thermal maps, which can automatically identify high-temperature areas in the temperature distribution map and calculate its area, average temperature, maximum temperature and other parameters. For example, during an inspection, the infrared thermal imager found that the local temperature of a fan gearbox reached 90°C, which was significantly higher than other areas. The hotspot analysis module will automatically mark the high-temperature area and judge that its area accounts for more than 20%, and the average temperature is 15°C higher than the normal value, indicating that the gearbox may have problems such as poor lubrication or gear wear, and needs to be repaired as soon as possible.

[0084] The structural assessment module is mainly used to analyze the three-dimensional point cloud data obtained by the LiDAR to assess the integrity and deformation of wind turbine towers, blades and other structures. Wind turbines operate in harsh marine environments for a long time, and their structures will inevitably undergo certain deformation or damage, such as tower bending and blade twisting. The structural assessment module uses an algorithm based on three-dimensional reconstruction and deformation analysis, which can align and compare the point cloud data of wind turbines collected at different times, and quantify the degree of deformation of the structure. For example, by comparing the three-dimensional model when the wind turbine was built and the current one, the structural assessment module found that the top of a wind turbine tower had shifted by 0.5 meters relative to the initial position, and there was obvious bending deformation at a height of 20 meters, with the maximum deformation reaching 0.3 meters, indicating that the tower structure of the wind turbine may have safety hazards and requires further inspection and reinforcement.

[0085] In the embodiment of the present invention, the structural assessment module is a key module that uses the three-dimensional point cloud data of the wind turbine acquired by the laser radar to perform a detailed analysis and assessment of the integrity and deformation of the wind turbine tower, blades and other structures. Its core algorithm is based on three-dimensional reconstruction and deformation analysis, and its principle and implementation are described in detail below.

[0086] 1. 3D reconstruction:

[0087] By emitting laser beams to the wind turbine structure and receiving reflected echoes, LiDAR can obtain a large amount of three-dimensional coordinate point data on the wind turbine surface, namely point cloud data. However, due to the limited scanning angle and ranging accuracy of LiDAR, the point cloud data obtained from a single scan is usually incomplete and difficult to be used directly for structural analysis. Therefore, it is necessary to splice and fuse the point cloud data obtained from multiple and multi-angle scans to reconstruct a complete three-dimensional model of the wind turbine structure.

[0088] The structural assessment module uses a 3D reconstruction method based on the ICP (Iterative Closest Point) algorithm. The basic steps are as follows:

[0089] a. Pre-process the point cloud data obtained from different scans to remove noise points and outliers to improve data quality;

[0090] b. Select a point cloud data as a reference and align the other point cloud data with it through rigid body transformation (translation and rotation) so that the coordinate points of the same structure in different point clouds overlap as much as possible;

[0091] c. Iteratively optimize the transformation matrix to minimize the distance error between the aligned point clouds until it converges to the best matching position;

[0092] d. All aligned point cloud data are fused together to generate a complete 3D model of the wind turbine structure.

[0093] Through 3D reconstruction, scattered and incomplete point cloud data can be integrated into a high-precision and high-detail 3D model of the wind turbine, providing a basis for subsequent structural deformation analysis.

[0094] 2. Deformation analysis:

[0095] During long-term operation, the fan structure will be affected by factors such as wind load, deadweight, and temperature, causing certain deformation. Timely and accurate monitoring and evaluation of these deformations are crucial to ensure the safe operation of the fan and extend its service life.

[0096] The structural assessment module uses a deformation analysis method based on 3D model comparison. The basic principle is to make a detailed comparison between the 3D models of the wind turbine at different times (for example, when the wind turbine was built and now), and to quantify the degree of structural deformation by calculating the spatial deviation between the two models.

[0097] The specific implementation steps are as follows:

[0098] a. Using the above 3D reconstruction method, reconstruct the complete 3D models of the fan at different times;

[0099] b. Accurately align the 3D models at different times to make their positions and directions consistent in the spatial coordinate system;

[0100] c. Mesh the two registered models to generate a structured mesh model for point-by-point comparison;

[0101] d. Calculate the spatial distance and normal vector angle between corresponding points on two grid models to obtain the deviation field distribution reflecting the structural deformation;

[0102] e. Evaluate the type, degree and scope of structural deformation based on the characteristics of the deviation field distribution, such as the size, direction, gradient, etc. of the deviation.

[0103] For example, by comparing the three-dimensional models of the wind turbine at the beginning of its construction and after five years of operation, the structural assessment module found that the top of the tower was offset by 20 cm to the windward side, and the offset showed a trend of gradually increasing from bottom to top, indicating that the tower may have permanent bending deformation caused by wind load, which needs to be paid attention to. For another example, by comparing the three-dimensional models of wind turbine blades at different pitch angles, the structural assessment module found that the leading edge of a blade had a 5 cm concave deformation at 50% of the chord length, and obvious stress concentration appeared around this point, indicating that the blade may have local structural damage and needs further inspection and repair.

[0104] Through 3D reconstruction and deformation analysis, the structural assessment module can quantitatively analyze and evaluate the structural integrity and deformation of the wind turbine, detect abnormal changes in the structure in a timely manner, and warn of potential safety hazards. Compared with traditional visual inspection and local measurement, this method can provide more comprehensive, detailed, and intuitive structural assessment results, greatly improving the efficiency and reliability of wind turbine structural health monitoring.

[0105] In addition, by deploying LiDAR on wind turbines for a long time and collecting 3D point cloud data regularly, the structural assessment module can also realize continuous tracking and trend prediction of wind turbine structural deformation. By analyzing the evolution of structural deformation in the time dimension, the deterioration trend of the structure can be discovered early, the maintenance plan and strategy of the wind turbine can be optimized, the service life of the wind turbine can be maximized, and the operation and maintenance cost of the wind farm can be reduced.

[0106] In summary, the 3D reconstruction and deformation analysis algorithms in the structural assessment module fully utilize the high-precision, large-range, and non-contact measurement advantages of lidar, providing a new technical means and solution for structural health monitoring of offshore wind farms.

[0107] The defect diagnosis module is mainly used to analyze the defect and damage data obtained by the ultrasonic flaw detector to determine the health status of the wind turbine foundation and underwater structure. The wind turbine foundation is the key to ensure the stable operation of the wind turbine, but it is in an environment of seawater immersion and wind and wave scouring for a long time, which is prone to problems such as concrete cracking and steel corrosion, affecting the strength and stability of the foundation. The defect diagnosis module uses an algorithm based on acoustic image analysis and pattern recognition, which can automatically identify the defect echo signal in the ultrasonic image data, and judge the type, location and severity of the defect based on the intensity, frequency, attenuation and other characteristics of the defect echo signal. For example, during an inspection, the ultrasonic flaw detector detected multiple strong reflection signals in the underwater part of a wind turbine foundation. The defect diagnosis module analyzed and found that these signals showed typical crack echo characteristics, and the echo energy was high and the frequency was low. It was preliminarily judged that there may be multiple through cracks inside the foundation, which need further verification and repair.

[0108] The environmental monitoring module is mainly used to analyze the environmental parameter data obtained by meteorological sensors and evaluate the impact of environmental factors on the operation of wind turbines. The environmental conditions of offshore wind farms are complex and changeable. Parameters such as wind speed, wind direction, temperature, and humidity will affect the power generation efficiency and operation safety of wind turbines. The environmental monitoring module uses an algorithm based on time series analysis and data mining, which can extract the meteorological characteristic patterns of wind farms from long-term environmental perception data and analyze the correlation between these meteorological characteristic patterns and wind turbine performance. For example, by analyzing the meteorological data of a wind farm in the past three years, the environmental monitoring module found that the wind farm has high temperatures in summer, with an average temperature of 8°C higher than other seasons. At the same time, the failure rate of wind turbines has also increased significantly, mainly concentrated in components such as converters and gearboxes, suggesting that high temperature may be one of the main causes of failure of these components. In response to this problem, the environmental monitoring module recommends that the operation and maintenance team strengthen the inspection and maintenance of converters and gearboxes in summer, optimize the control strategy of wind turbines, and appropriately reduce the operating power of wind turbines during high temperatures to reduce the thermal stress of components.

[0109] The central control unit can comprehensively analyze and evaluate the health status of wind turbines through the collaborative work of multiple functional modules such as image processing, hot spot analysis, structural assessment, defect diagnosis, and environmental monitoring, providing important decision-making support for the intelligent operation and maintenance of wind farms. This modular design makes the system highly flexible and scalable, and each module can be optimized and upgraded according to actual needs and technological development, continuously improving the system's analysis and diagnostic capabilities. At the same time, by adopting advanced artificial intelligence algorithms, such as deep learning, image recognition, and data mining, the central control unit can quickly extract valuable information from massive multi-source heterogeneous data, achieve early warning and accurate diagnosis of wind turbine failures, reduce unplanned downtime of wind turbines, and improve the overall operating efficiency and economic benefits of wind farms.

[0110] In the embodiment of the present invention, the defect and damage data obtained by the ultrasonic flaw detector is the ultrasonic image data. The ultrasonic flaw detector transmits ultrasonic waves to the object to be tested, receives the reflected echo signal, converts the echo signal into an electrical signal, and then undergoes a series of signal processing to finally form ultrasonic image data reflecting the internal structure of the object to be tested. Therefore, the object analyzed by the defect diagnosis module is the ultrasonic image data, which contains the defect and damage information of the wind turbine foundation and underwater structure.

[0111] The algorithm based on acoustic wave image analysis algorithm and pattern recognition refers to a comprehensive analysis algorithm, which includes two main parts: acoustic wave image analysis algorithm and pattern recognition algorithm. The acoustic wave image analysis algorithm is mainly used to perform preprocessing and feature extraction on ultrasonic images, and convert image data into feature vectors or feature matrices that are easy to analyze and identify. The pattern recognition algorithm is mainly used to classify, identify, and locate the extracted features to determine the type, location, and severity of the defect. The two algorithms work together to complete the task of defect diagnosis.

[0112] The following further describes a specific implementation method of the defect diagnosis module for determining the defect type, location and severity based on the characteristics of the defect echo signal.

[0113] When ultrasonic waves propagate in the wind turbine foundation or underwater structure, if they encounter defects such as cracks and cavities, part of the ultrasonic waves will be reflected back to form defect echo signals. Defects of different types, sizes, and locations have different characteristics of reflected echo signals. The defect diagnosis module can infer the properties of the defect by analyzing the intensity, frequency, attenuation and other characteristics of the echo signal.

[0114] Different types of defects, such as cracks, voids, inclusions, etc., have significantly different frequency characteristics of reflected echo signals. The echo signals of crack defects usually contain higher frequency components, while the echo signals of void defects are mainly low-frequency components. The defect diagnosis module performs spectrum analysis on the echo signal, calculates the energy distribution of different frequency bands, and then matches it with the preset defect spectrum template to determine the type of defect.

[0115] The arrival time of the defect echo signal is related to the location of the defect. The propagation time of the sound wave from the emission to the reception of the defect echo is proportional to the speed of sound and the distance of the defect. By measuring the arrival time of the echo signal and considering the difference in the speed of sound in different media such as concrete and steel, the defect diagnosis module can calculate the distance and direction of the defect relative to the probe, and then determine its spatial position in the wind turbine foundation or underwater structure.

[0116] The strength and attenuation characteristics of the defect echo signal can reflect the size and severity of the defect. Generally speaking, the larger the defect size, the higher the intensity of its reflected echo; the farther the defect is from the probe, the more obvious the attenuation of the echo signal. The defect diagnosis module can quantitatively evaluate the size and severity of the defect by analyzing the peak amplitude, dynamic range, attenuation slope and other indicators of the echo signal, combined with the type and location information of the defect. For example, for crack defects, the higher the peak amplitude of the echo signal, the greater the width and depth of the crack may be, and the more serious the impact on the structure.

[0117] In specific implementation, the defect diagnosis module will establish corresponding diagnostic rules and evaluation models for different defect types. These rules and models are usually based on a large amount of experimental data and engineering experience, and are optimized and updated using machine learning methods. For example, for concrete cracks, the defect diagnosis module can use a classification model based on a support vector machine, input the frequency spectrum characteristics of the echo signal, and determine whether the crack exists; then use a regression model based on a neural network, input the amplitude and attenuation characteristics of the echo signal, and predict the width and depth of the crack; finally, based on the location, size, number and other information of the crack, combined with the mechanical properties of the concrete material such as fracture toughness and fatigue life, comprehensively judge the degree of damage of the crack to the wind turbine foundation.

[0118] Through the above analysis method, the defect diagnosis module can accurately identify and locate the defects and damage of the wind turbine foundation and underwater structure from the ultrasonic image data, and quantitatively evaluate their severity, providing a reliable basis for subsequent maintenance decisions.

[0119] like Figure 3 As shown, in some embodiments, the central control unit further includes:

[0120] Data fusion module, used to comprehensively analyze the analysis results of image processing module, hot spot analysis module, structure assessment module, defect diagnosis module and environmental monitoring module, and generate a comprehensive health assessment report of the wind turbine;

[0121] The maintenance decision module is used to generate maintenance recommendations for the wind turbine based on the comprehensive health assessment report of the wind turbine and the preset maintenance strategy. The maintenance recommendations include maintenance priority, maintenance method and maintenance time.

[0122] In some embodiments, the autonomous navigation module adopts an intelligent decision-making algorithm based on reinforcement learning to autonomously plan the optimal inspection route based on environmental perception data and inspection task requirements obtained by meteorological sensors.

[0123] Specifically, in some embodiments of the present invention, in order to further improve the automation level and practicality of the intelligent offshore wind power inspection system, the central control unit is also equipped with a data fusion module and a maintenance decision module. At the same time, the autonomous navigation module also adopts advanced artificial intelligence algorithms to achieve more intelligent and efficient inspection route planning.

[0124] The main function of the data fusion module is to comprehensively analyze the output results of each functional module in the central control unit and generate a comprehensive health assessment report for the fan. In practical applications, a single data analysis is often difficult to fully reflect the health status of the fan. For example, only a few surface cracks found through blade image analysis cannot fully determine whether the fan has safety hazards. It is also necessary to combine other information such as the structural deformation and internal temperature of the blade for a comprehensive assessment. The data fusion module uses a multi-source data fusion algorithm based on a Bayesian network, which can associate and fuse the analysis results of modules such as image processing, hot spot analysis, structural assessment, defect diagnosis, and environmental monitoring to obtain the health status scores of each component and the entire fan, and generate a comprehensive health assessment report. For example, during an inspection, the image processing module found that there were multiple cracks on the surface of blade No. 2 of a certain wind turbine, the structural assessment module found that the distortion of the blade exceeded 0.5 degrees, the hot spot analysis module found that the temperature of the connection flange at the root of the blade reached 80°C, and the environmental monitoring module found that the wind speed on that day reached 25m / s. After comprehensive analysis, the data fusion module concluded that the health score of the blade was 65 points (out of 100 points), which was a high-risk state and needed to be listed as a key monitoring object, and it was recommended to arrange maintenance as soon as possible. Through data fusion, the system can more comprehensively and accurately evaluate the true health status of the wind turbine, avoiding one-sided or misjudgment.

[0125] The main function of the maintenance decision module is to automatically generate maintenance recommendations for the wind turbine, including maintenance priority, maintenance method, and maintenance time, based on the comprehensive health assessment report of the wind turbine and combined with the preset maintenance strategy. In traditional wind farm operation and maintenance, maintenance decisions are usually made based on manual experience, which is difficult to be objective, consistent, and optimized. The use of intelligent algorithms can make maintenance plans more scientific and efficient. The maintenance decision module uses an intelligent decision-making algorithm based on case reasoning and rule engines. By learning and summarizing a large number of historical maintenance cases, a set of optimized maintenance decision rule libraries has been established. When a comprehensive health assessment report for a wind turbine is generated, the maintenance decision module will automatically match similar historical cases and generate maintenance recommendations for the wind turbine based on the preset decision rules. For example, when the health score of a wind turbine is lower than 70 points, the maintenance decision module will mark it as a high priority and recommend that it be scheduled for on-site maintenance within 1 week; when the gearbox temperature of a wind turbine exceeds 90°C for 5 consecutive days, the maintenance decision module will recommend replacing the gearbox lubricant and performing an endoscopic inspection; when serious cracks appear on the foundation of a wind turbine, the maintenance decision module will recommend grouting reinforcement and increasing the monitoring frequency. Through intelligent maintenance decisions, the system can guide the operation and maintenance team to carry out their work in a timely and accurate manner, improving the operational reliability and economy of wind farms.

[0126] Specifically, in an embodiment of the present invention, the maintenance decision module adopts an intelligent decision-making algorithm based on case reasoning and rule engine, which uses the empirical knowledge of historical maintenance cases and combines preset decision rules to provide intelligent support for the maintenance decision of the current wind turbine.

[0127] Specifically, the basis and execution process of automatically matching similar historical cases include:

[0128] The maintenance decision module will extract and represent the features of historical maintenance cases and establish a case feature library. The features of each case include the model, operating time, health status, failure mode, maintenance measures, maintenance effect and other aspects of the fan. After the comprehensive health assessment report of the current fan is generated, the maintenance decision module will extract the feature vector of the fan and calculate the similarity with the historical cases in the case feature library. The similarity calculation uses K-nearest neighbor algorithm, similarity weighting and other algorithms to find the K historical cases that are most similar to the current fan status based on the distance or correlation between the feature vectors. The maintenance measures and effects of these similar cases can provide valuable references for the maintenance decisions of the current fan.

[0129] Specifically, the logical relationship between the maintenance decision rule base and the preset decision rules is as follows:

[0130] Preset decision rules refer to some general maintenance decision principles and strategies summarized based on prior knowledge such as expert experience, industry standards, equipment manuals, etc. For example, "when a wind turbine blade has serious cracks, it needs to be replaced within 1 week." These rules are expressed in the form of IF-THEN and can be directly applied to maintenance decisions.

[0131] The maintenance decision rule base is a more comprehensive and detailed decision rule system formed by optimizing and improving the rules based on the preset decision rules and combining the actual results of historical maintenance cases. For example, through the analysis of a large number of cases, it was found that if the cracks in the blades of a certain type of fan are repaired within 3 days when the length exceeds 50 cm, the subsequent failure rate will be greatly reduced. Therefore, the original "replace within 1 week" rule can be refined to "repair within 3 days". The maintenance decision rule base can make maintenance decisions more intelligent and accurate through continuous learning and updating.

[0132] The decision-making algorithm based on case reasoning refers to making decisions on current problems by retrieving and matching similar historical cases and drawing on their successful experiences. Its basic assumption is that similar problems have similar solutions. The advantage of case reasoning is that it can make full use of historical experience and quickly generate feasible decision plans.

[0133] The decision-making algorithm based on the rule engine refers to the logical reasoning of the characteristics of the current problem through the preset IF-THEN rules to draw a decision conclusion. Its basic assumption is that the decision problem can be represented and solved by rule knowledge. The advantage of the rule engine is that the decision-making process is clear and transparent, and it is easy to understand and modify.

[0134] The maintenance decision module combines case reasoning and rule engine to form a hybrid intelligent decision algorithm. When the comprehensive health assessment report of the wind turbine is generated, the maintenance decision module first uses case reasoning to find maintenance measures for similar cases as preliminary solutions; then, through the rule engine, logical reasoning and optimization are performed on the preliminary solutions, and finally maintenance decision recommendations that meet the specific needs of the current wind turbine are generated. This hybrid algorithm can take into account both empiricism and logic, and improve the applicability and explainability of maintenance decisions.

[0135] In summary, the maintenance decision module adopts a hybrid intelligent decision-making algorithm that combines case reasoning and rule engine. By learning historical maintenance experience and combining expert knowledge and equipment characteristics, it can provide more intelligent, efficient and accurate decision support for the operation and maintenance of offshore wind farms, reduce wind turbine downtime and maintenance costs, and improve the overall operating efficiency and economic benefits of wind farms.

[0136] In some embodiments, the autonomous navigation module adopts an intelligent decision-making algorithm based on reinforcement learning, which can autonomously plan the optimal inspection route according to the environmental perception data obtained by meteorological sensors and the inspection task requirements. Traditional inspection route planning usually adopts a fixed mode, such as inspecting in sequence according to the order of wind turbine numbers, which is difficult to adapt to complex and changeable sea conditions and task requirements. By adopting the reinforcement learning algorithm, the system can autonomously learn the best inspection strategy through continuous trial and error and optimization. Specifically, the autonomous navigation module will model the inspection process as a Markov decision process. Each decision will take into account the current environmental status (such as wind speed, wind direction, waves, etc.) and task status (such as the number of inspected wind turbines, remaining power, etc.). Through the iterative update of the value function, the decision-making strategy is continuously optimized, and finally a patrol route that takes into account safety, efficiency, and comprehensiveness is obtained. For example, when the meteorological sensor detects that the wind speed in a certain area is high and the waves are large, the autonomous navigation module will automatically avoid the area and give priority to inspecting wind turbines with relatively stable wind conditions; when a wind turbine is found to be faulty, the autonomous navigation module will appropriately extend the inspection time near the wind turbine to obtain more status information; when the remaining power is insufficient, the autonomous navigation module will return home in time or go to the nearest charging station to replenish energy. Through intelligent inspection route planning, the unmanned ship can complete the inspection task efficiently and flexibly while ensuring its own safety.

[0137] The following describes the workflow of the intelligent marine wind power inspection system of the present invention in conjunction with a specific application scenario. Assume that a set of this system is deployed in an offshore wind farm, in which the unmanned boat is equipped with high-definition cameras, infrared thermal imagers, laser radars, ultrasonic flaw detectors, meteorological sensors and other equipment. In the early morning of a certain day, the autonomous navigation module plans an inspection route covering all 20 wind turbines in the field according to the weather forecast and inspection tasks of the day, and controls the unmanned boat to automatically navigate along the route. During the inspection process, various sensors continuously collect the status data of the wind turbines and transmit it back to the shore-based control center in real time through the wireless communication module. When the unmanned boat inspected wind turbine No. 7, the image processing module found that a crack about 2 meters long appeared on the trailing edge of its No. 2 blade, the hot spot analysis module found that the maximum temperature of the root flange of the blade reached 95°C, and the structural assessment module found that the maximum distortion of the blade reached 1.5 degrees. After comprehensive analysis, the data fusion module judged that the health score of the blade was 45 points, which was a serious fault state, and the maintenance decision module recommended immediate shutdown for maintenance. After receiving the alarm, the shore-based control center immediately notified the on-site operation and maintenance team to go to wind turbine No. 7 for review and repair. At the same time, the autonomous navigation module also received instructions to adjust the inspection route and focus on monitoring wind turbine No. 7 until the fault was eliminated.

[0138] The intelligent marine wind power inspection system of the present invention utilizes a variety of advanced sensors, communications, artificial intelligence and other technologies to achieve comprehensive perception, intelligent analysis, accurate diagnosis and optimized decision-making of wind turbine status, greatly improving the operation and maintenance efficiency and level of offshore wind farms. The modular design of the system gives it good adaptability and scalability. It can flexibly combine and optimize various functional modules according to different application requirements and technological developments, and continuously improve the performance and intelligence of the system. With the continuous development and integration of new technologies such as artificial intelligence, big data, cloud computing, and the Internet of Things, the intelligent marine wind power inspection system will surely be more widely used in the future, providing strong support for the intelligent and digital transformation of the offshore wind power industry.

[0139] like Figure 4 As shown, an embodiment of the present invention also provides an operation method of an intelligent marine wind power inspection system, which includes the following steps:

[0140] S1: Use the autonomous navigation module on the unmanned ship and adopt a variety of navigation equipment to achieve autonomous navigation and obstacle avoidance of the unmanned ship;

[0141] S2: Use multiple sensors on the unmanned ship to detect offshore wind turbines and collect detection data;

[0142] S3: Transmitting the detection data to a central control unit on the unmanned vessel;

[0143] S4: In the central control unit, according to the received detection data and the preset algorithm, the data is processed and an inspection report and maintenance suggestions are generated;

[0144] S5: using the wireless communication module on the unmanned vessel to transmit the generated inspection report and maintenance suggestions to the shore base station;

[0145] S6: The energy management module on the unmanned ship is used to supply power to the unmanned ship, the central control unit, the wireless communication module, the autonomous navigation module and various sensors.

[0146] In some embodiments, the method specifically comprises:

[0147] The autonomous navigation module formulates inspection plans, determines inspection routes and schedules based on environmental perception data obtained by meteorological sensors and inspection task requirements;

[0148] The autonomous navigation module controls the unmanned boat to autonomously navigate to the designated wind farm site according to the inspection plan, and activates multiple sensors to carry out coordinated inspection;

[0149] The wireless communication module transmits the detection data acquired by various sensors to the central control unit in real time;

[0150] The image processing module, hot spot analysis module, structure assessment module, defect diagnosis module and environmental monitoring module of the central control unit analyze the corresponding detection data respectively;

[0151] The data fusion module of the central control unit comprehensively analyzes the analysis results of each module and generates a comprehensive health assessment report of the fan;

[0152] The maintenance decision module of the central control unit generates maintenance recommendations for the fan based on the comprehensive health assessment report of the fan;

[0153] The wireless communication module sends the generated comprehensive health assessment report and maintenance recommendations of the wind turbine to the shore base station;

[0154] The central control unit adjusts and optimizes the inspection tasks of the unmanned boat according to the control instructions issued by the shore base station.

[0155] In some embodiments, during the inspection process, the unmanned ship shares navigation information with other marine vessels through the AIS system (Automatic Identification System), and adopts an intelligent collision avoidance algorithm based on game theory to ensure navigation safety.

[0156] In some embodiments, the central control unit uses an intelligent diagnosis algorithm based on a knowledge graph to comprehensively analyze historical inspection data and fan operation data to predict the health status and remaining life of the fan.

[0157] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0158] An embodiment of the present application further provides a processor, which is used to run a program, wherein the operating method of the above-mentioned intelligent marine wind power inspection system is executed when the program is running.

[0159] An embodiment of the present application also provides a machine-readable storage medium on which a program is stored, and when the program is executed by a processor, an operating method of the above-mentioned intelligent marine wind power inspection system is implemented.

[0160] An embodiment of the present application also provides a computer program product, including a computer program, which implements the operating method of the above-mentioned intelligent offshore wind power inspection system when executed by a processor.

[0161] The embodiment of the present application also provides a computer device, which may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05 and a memory (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A06. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor A01, a method for a decision engine is implemented. The display screen A04 of the computer device can be a liquid crystal display or an electronic ink display, and the input device A05 of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0162] Those skilled in the art will understand that the structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0163] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0164] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0165] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0166] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0167] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0168] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0169] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0170] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0171] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. An intelligent offshore wind power inspection system, It is characterized in that include: An autonomous unmanned ship is equipped with a variety of sensors for detecting offshore wind turbines; the multiple sensors include cameras, infrared thermal imagers, laser radars, ultrasonic flaw detectors and meteorological sensors; wherein the camera is used to obtain visible light image data of the external structure of the wind turbine, the infrared thermal imager is used to obtain temperature distribution data inside the wind turbine, the laser radar is used to obtain three-dimensional point cloud data of the wind turbine structure, the ultrasonic flaw detector is used to obtain defect and damage data of the wind turbine foundation and underwater structure, and the meteorological sensor is used to obtain environmental perception data including wind speed, wind direction, temperature and humidity; A central control unit, installed on the unmanned vessel, for receiving and processing detection data from a variety of sensors, and generating inspection reports and maintenance recommendations based on the detection data from the various sensors and a preset algorithm; A wireless communication module, installed on the unmanned ship, for transmitting data and control instructions between the unmanned ship, the central control unit and the shore base station; An energy management module, installed on the unmanned ship, for supplying power to the unmanned ship, the central control unit, the wireless communication module, the autonomous navigation module and the various sensors; An autonomous navigation module, installed on the unmanned ship, is used to use a variety of navigation equipment to achieve autonomous navigation and obstacle avoidance of the unmanned ship; Wherein, the central control unit comprises: An image processing module, used to analyze the visible light image data acquired by the camera, detect and locate blade defects including cracks on the blade surface or falling fragments; A hot spot analysis module, used to analyze the temperature distribution data obtained by the infrared thermal imager to identify abnormally high temperature areas inside the fan; A structural assessment module, used to analyze the three-dimensional point cloud data acquired by the laser radar to assess the integrity and deformation of the structure including the tower and blades of the wind turbine; A defect diagnosis module, used to analyze the defect and damage data obtained by the ultrasonic flaw detector to determine the health status of the wind turbine foundation and underwater structure; The environmental monitoring module is used to analyze the environmental perception data obtained by the meteorological sensor and evaluate the impact of environmental factors on the operation of the wind turbine.

2. According to claim 1, the intelligent marine wind power inspection system, It is characterized in that The central control unit also includes: A data fusion module, used for comprehensively analyzing the analysis results of the image processing module, the hot spot analysis module, the structure assessment module, the defect diagnosis module and the environmental monitoring module, and generating a comprehensive health assessment report of the wind turbine; The maintenance decision module is used to generate maintenance suggestions for the wind turbine according to the comprehensive health assessment report of the wind turbine and the preset maintenance strategy, wherein the maintenance suggestions include maintenance priority, maintenance method and maintenance time.

3. The intelligent marine wind power inspection system according to claim 1, It is characterized in that The autonomous navigation module adopts an intelligent decision-making algorithm based on reinforcement learning, obtains the environmental perception data and inspection task requirements according to the meteorological sensor, and autonomously plans the optimal inspection route.

4. The intelligent marine wind power inspection system according to claim 1, It is characterized in that The image processing module is specifically used to adopt a deep learning algorithm based on a convolutional neural network to establish a defect detection model by training multiple wind turbine blade image data; extract features including any multiple of texture, edge, and color in the visible light image data based on the defect detection model, and realize the recognition and positioning of blade defects through multi-level feature fusion and classification; The hot spot analysis module is specifically used to identify the high temperature area in the temperature distribution map by using an image segmentation algorithm based on a heat map, and calculate the parameters of the high temperature area including the area, average temperature and maximum temperature; The structural assessment module is specifically used to align and compare the three-dimensional point cloud data of the wind turbine collected at different times, and quantitatively analyze the deformation degree of the structure by using an algorithm based on three-dimensional reconstruction and deformation analysis; The defect diagnosis module is specifically used to identify the defect echo signal in the ultrasonic image data by using an algorithm based on acoustic wave image analysis algorithm and pattern recognition, and judge the type, location and severity of the defect according to the characteristics of the defect echo signal including any one of intensity, frequency and attenuation; wherein the ultrasonic image data refers to the defect and damage data obtained by the ultrasonic flaw detector; The environmental monitoring module is specifically used to extract the meteorological characteristic pattern of the wind farm from the environmental perception data by adopting an algorithm based on time series analysis and data mining, and to analyze the correlation between the meteorological characteristic pattern and the performance of the wind turbine.

5. The intelligent marine wind power inspection system according to claim 2, It is characterized in that The data fusion module is specifically used to use a multi-source data fusion algorithm based on a Bayesian network to associate and fuse the analysis results of the image processing module, the hot spot analysis module, the structure assessment module, the defect diagnosis module and the environmental monitoring module, to obtain the health status scores of each component of the wind turbine and the whole machine, and to generate a comprehensive health assessment report; The maintenance decision module is specifically used to adopt an intelligent decision-making algorithm based on case reasoning and a rule engine, and to establish a maintenance decision rule library by learning and summarizing historical maintenance cases; when a comprehensive health assessment report of the wind turbine is generated, similar historical cases are automatically matched, and maintenance recommendations for the wind turbine are generated according to preset decision rules.

6. The intelligent marine wind power inspection system according to claim 5, It is characterized in that The maintenance decision module is specifically used for: Extract and represent the features of historical maintenance cases and establish a case feature library. The features of each case include the model, operating time, health status, failure mode, maintenance measures and maintenance effect of the wind turbine. After the comprehensive health assessment report of the current wind turbine is generated, the feature vector of the wind turbine is extracted, and similarity calculation is performed with the historical cases in the case feature library; wherein the similarity calculation adopts a K nearest neighbor algorithm or a similarity weighted algorithm; According to the distance or correlation between the feature vectors, find the K historical cases that are most similar to the current wind turbine status.

7. The intelligent marine wind power inspection system according to claim 1, It is characterized in that The various navigation equipment include a global positioning system, radar and sonar; a catamaran structure is adopted, and a deck platform is connected between the two hulls.

8. The intelligent marine wind power inspection system according to claim 1, It is characterized in that The central control unit adopts an industrial computer or an embedded computer.

9. The intelligent marine wind power inspection system according to claim 1, It is characterized in that The energy management module includes a solar panel and an energy storage device.

10. An operating method of the intelligent marine wind power inspection system according to any one of claims 1 to 9, It is characterized in that The following steps are involved: Use the autonomous navigation module on the unmanned ship and adopt a variety of navigation equipment to achieve autonomous navigation and obstacle avoidance of the unmanned ship; Using a variety of sensors on the unmanned ship to detect offshore wind turbines and collect detection data; Transmitting the detection data to a central control unit on the unmanned vessel; In the central control unit, based on the received detection data and the preset algorithm, the data is processed and an inspection report and maintenance recommendations are generated; Using the wireless communication module on the unmanned vessel, the generated inspection report and maintenance suggestions are transmitted to a shore base station; The energy management module on the unmanned ship is used to power the unmanned ship, the central control unit, the wireless communication module, the autonomous navigation module and various sensors.

Citation Information

Patent Citations

  • Ultrasound detection method for crack propagation in unmanned ship body

    CN106153722A

  • State monitoring and maintenance support system of unmanned ship

    CN115964883A

  • Ship inspection and evaluation system

    CN118172041A

  • Unmanned ship inspection system suitable for offshore wind plant

    CN217515351U

Cited By

  • Road infrastructure real-time monitoring method and system based on unmanned aerial vehicle Internet of Things

    CN120375242A

  • Robust autonomous navigation and obstacle avoidance method for underwater detection robot

    CN120521616A