Fan tower drum interior detection system and method based on high-precision three-dimensional modeling

Abstract

The invention discloses a system and a method for detecting the interior of a fan tower based on high-precision three-dimensional modeling, and the system comprises a multi-modal data collection device which is used for collecting multi-modal data; the real-time data processing and SLAM unit is used for performing SLAM processing on the acquired multi-modal data; the multi-scale self-adaptive modeling unit is used for building a three-dimensional model in the tower tube based on the SLAM result; the artificial intelligence analysis unit is used for analyzing and detecting the interior of the fan tower drum on the basis of the three-dimensional model in the tower drum; the technical problems that the accuracy and comprehensiveness of the detection result are difficult to guarantee and the efficient and intelligent management requirement of a modern wind power plant is difficult to meet when a traditional detection method faces a large and complex fan tower drum are solved, the accuracy and comprehensiveness of the detection result are effectively improved, and meanwhile efficient and intelligent management is achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of wind power generation, and relates to a wind turbine tower internal detection system and method based on high-precision three-dimensional modeling. Background Art

[0002] In the wave of global energy structure transformation, wind power generation is gradually becoming an important part of the energy supply system with its clean and renewable characteristics. As the core equipment for converting wind energy into electrical energy, the efficient and stable operation of wind turbines is crucial to promoting the large-scale development and utilization of wind energy. In the entire wind turbine, the tower is a supporting structure, and its internal state is directly related to the overall safety and power generation efficiency of the wind turbine. Therefore, the inspection and maintenance of the internal condition of the tower is particularly important.

[0003] Traditional wind turbine tower internal inspection methods mainly rely on manual operation. This process usually requires maintenance personnel to enter the tower in person and conduct status assessment through visual observation and handheld measuring tools. However, this method has many limitations: first, manual inspection is inefficient and it is difficult to quickly complete a comprehensive inspection of the entire tower interior; second, the tower is tall and the internal environment is complex, which brings high safety risks to maintenance personnel; third, manual inspection is easily affected by subjective factors, and coupled with the limitations of inspection tools, it is often difficult to obtain detailed and accurate three-dimensional data inside the tower, which undoubtedly limits the in-depth analysis and scientific evaluation of the health status of the tower structure.

[0004] With the continuous advancement of wind power technology and the vigorous development of the wind power industry, the design of wind turbine towers has become more complex and the size has gradually increased, which has put forward higher requirements for detection work. Traditional detection methods are not enough when facing large and complex wind turbine towers. Not only are they inefficient, but they are also difficult to ensure the accuracy and comprehensiveness of the detection results, and it is difficult to meet the efficient and intelligent management needs of modern wind farms. Summary of the invention

[0005] The purpose of the present invention is to solve the technical problem that traditional detection methods in the prior art are difficult to ensure the accuracy and comprehensiveness of the detection results when facing large and complex wind turbine towers, and are difficult to meet the efficient and intelligent management needs of modern wind farms, and to provide a wind turbine tower internal detection system and method based on high-precision three-dimensional modeling.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: A first aspect of the present invention provides a wind turbine tower internal detection system based on high-precision three-dimensional modeling, comprising: A multimodal data acquisition device, used for acquiring multimodal data; Real-time data processing and SLAM unit, used to perform SLAM processing on the collected multimodal data; Multi-scale adaptive modeling unit, used to build a 3D model of the tower interior based on SLAM results; The artificial intelligence analysis unit is used to analyze and detect the interior of the wind turbine tower based on the three-dimensional model of the interior of the tower.

[0007] Furthermore, the present invention also includes an autonomous movement detection device for performing functional testing of each module, sensor calibration and communication link inspection.

[0008] Furthermore, it also includes an adaptive path planning module, which is used to automatically generate an optimal detection path according to the internal structural characteristics of the tower and detection requirements.

[0009] Furthermore, it also includes a mixed reality visualization and interaction unit for visualization of the three-dimensional model and analysis data inside the tower and human-computer interaction.

[0010] Furthermore, it also includes a safety monitoring and emergency processing unit, which is used to monitor the working status of the system and process different anomalies.

[0011] A second aspect of the present invention provides a method for detecting the interior of a wind turbine tower based on high-precision three-dimensional modeling, comprising the following steps: Dynamically adjust the working parameters of each sensor according to the complexity of the environment and detection requirements to collect multi-modal data; Process the collected multimodal data and perform SLAM to obtain point cloud data inside the tower; Based on the point cloud data inside the tower, a three-dimensional model of the interior of the tower is constructed; Based on the three-dimensional model of the interior of the tower, the interior of the wind turbine tower is analyzed and inspected.

[0012] Furthermore, the operating parameters of each sensor are dynamically adjusted according to the environmental complexity and detection requirements to collect multimodal data, specifically: Perform adaptive path planning, build an initial environment model through preset tower structure data and real-time environment, generate a detection path using a global path planning algorithm, and dynamically adjust the detection path during the detection process; Based on the detection path, the working parameters of each sensor are dynamically adjusted according to the environmental complexity and detection requirements to perform multimodal data collection.

[0013] Further, the collected multimodal data is processed and SLAM is performed, specifically: After feature extraction and initial pose estimation of the collected multimodal data, local map construction is performed; The constructed local map is optimized and loop detection is performed on the global map to obtain the point cloud data and posture information inside the tower.

[0014] Further, the three-dimensional model of the interior of the tower is constructed based on the point cloud data inside the tower, specifically: Use octree structure to store and process point cloud data; The model accuracy is dynamically adjusted according to the geometric complexity and semantic information of each octree node, and high-precision reconstruction is used for complex areas.

[0015] Furthermore, the three-dimensional model of the interior of the tower is used to analyze and detect the interior of the wind turbine tower, specifically: The deep learning model is used to perform defect detection, deformation analysis, and stress distribution prediction, and to evaluate the remaining life of key tower components. Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses a wind turbine tower internal detection system based on high-precision 3D modeling. The system is equipped with a multimodal data acquisition device, which can simultaneously acquire multiple types of data including visible light images, infrared thermal imaging, laser scanning, etc., thereby improving the richness and comprehensiveness of the data. The real-time data processing and SLAM unit can quickly process the acquired multimodal data to achieve accurate positioning and map construction inside the wind turbine tower. The multiscale adaptive modeling unit can flexibly build a 3D model of the inside of the wind turbine tower based on the results of SLAM. The unit adopts advanced algorithms and technologies, and can dynamically adjust the model according to the complexity of the inside of the wind turbine tower and the detection requirements. The accuracy and detail of the model not only improves the accuracy of the model, but also effectively controls the amount of data and reduces storage and computing costs. Based on the three-dimensional model of the inside of the tower, the artificial intelligence analysis unit can intelligently identify and analyze abnormal conditions inside the wind turbine tower. By using deep learning and machine learning, the data in the model can be deeply mined and analyzed. It can accurately detect potential problems such as cracks, corrosion, and wear inside the wind turbine tower, and provide predictive maintenance suggestions, which greatly improves the level of intelligent wind turbine management. At the same time, artificial intelligence analysis is also highly efficient and can complete the processing and analysis of large amounts of data in a short time, greatly improving detection efficiency.

[0016] Furthermore, mixed reality visualization and interaction functions provide maintenance personnel with an intuitive and interactive way to present data, facilitating decision-making.

[0017] Furthermore, the autonomous mobile detection device integrates advanced autonomous navigation, motion control and environmental perception technologies, and can autonomously perform tasks such as functional testing of each module, sensor calibration and communication link inspection. The introduction of this device not only improves the automation level of the system, but also significantly reduces the need for manual intervention, making the detection process more efficient and convenient. Through the autonomous mobile detection device, the system can comprehensively and accurately test the functions of each module. The device can simulate actual detection scenarios and test each module one by one to ensure its stability and reliability under different working conditions.

[0018] Furthermore, the adaptive path planning module can automatically generate the optimal detection path according to the structural characteristics and detection requirements inside the tower. Through the adaptive path planning module, the system can automatically generate the optimal detection path, avoiding the problems of repeated detection and missing areas. This not only improves the detection efficiency, but also ensures the comprehensiveness and accuracy of the detection results. At the same time, since the path planning process is automatically completed by the system, it avoids the errors and uncertainties that may be caused by manual planning, further improving the reliability of the detection results.

[0019] Furthermore, the mixed reality visualization and interaction unit uses mixed reality (MR) technology to present the three-dimensional model and analysis data inside the tower in an intuitive and vivid way. Technicians can directly view and interact with the structure and detection data inside the tower in a virtual environment by wearing mixed reality devices such as HoloLens. This visualization method not only improves the readability of the data, but also enables technicians to have a deeper understanding of the detection results and internal structural characteristics. The mixed reality visualization and interaction unit provides a wealth of human-computer interaction functions, such as gesture recognition, voice control, virtual annotation, etc. Technicians can use these functions to perform operations such as annotation, measurement, and navigation in a virtual environment, greatly improving the efficiency and accuracy of detection and analysis. At the same time, these interactive functions also enable technicians to control the detection process more flexibly and adjust the detection path and parameters according to actual needs.

[0020] Furthermore, the safety monitoring and emergency handling unit can monitor various parameters and states of the system in real time. Once an abnormal situation is found, such as equipment failure, data transmission interruption, detection path deviation, etc., the unit can immediately issue a warning signal and automatically or manually start the emergency handling process. This real-time monitoring and processing mechanism not only improves the response speed of the system, but also reduces the impact of abnormal situations on the detection process, ensuring the accuracy and reliability of the detection results. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 It is an overall block diagram of a wind turbine tower internal detection system based on high-precision three-dimensional modeling according to an embodiment of the present invention; Figure 2 This is a flow chart of a method for detecting the interior of a wind turbine tower based on high-precision three-dimensional modeling according to an embodiment of the present invention; Figure 3 A schematic diagram of multi-scale adaptive modeling according to an embodiment of the present invention; Figure 4 Schematic diagram of artificial intelligence analysis results according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention described and marked in the drawings here can be arranged and designed in various different configurations.

[0024] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. 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.

[0025] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0026] In the description of the embodiments of the present invention, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, it is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0027] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0028] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0029] The present invention is further described in detail below in conjunction with the accompanying drawings: Embodiment 1: See also Figure 1 The present invention provides a wind turbine tower internal detection system based on high-precision three-dimensional modeling, including an autonomous mobile detection device, a multimodal data acquisition device, a real-time data processing and SLAM unit, a multi-scale adaptive modeling unit, an artificial intelligence analysis unit, a mixed reality visualization and interaction unit, and a safety monitoring and emergency processing unit.

[0030] The autonomous mobile detection device takes into account the internal environment of the wind turbine tower and adopts a modular design, including a scanning module, a power module, a sensor module and a communication module. Among them, the power system ensures that the autonomous mobile detection device can move stably on vertical and inclined surfaces; it not only ensures the reliability of the autonomous mobile detection device in complex environments, but also can carry various sensors.

[0031] The multimodal data acquisition device integrates a variety of sensors, including high-precision laser scanners, panoramic cameras, thermal imaging cameras, and ultrasonic thickness measuring devices. Among them, the laser scanner provides high-precision, high-speed scanning technology, the panoramic camera provides a full range of fields of view, the thermal imaging camera can capture a wide range of temperature changes, and the ultrasonic thickness measuring device provides accurate thickness data. This multi-sensor fusion design ensures the comprehensiveness and accuracy of data collection.

[0032] The real-time data processing and SLAM (Simultaneous Localization and Mapping) unit uses an edge computing architecture. The unit includes a front-end processor on the device side and a back-end optimization processor on the cloud server side. The front-end processor is mainly responsible for feature extraction, initial pose estimation, and local map construction. The back-end optimization processor performs pose graph optimization, loop detection, and global map updates. This distributed processing method effectively balances real-time and accuracy requirements.

[0033] The multi-scale adaptive modeling unit builds a 3D model of the interior of the tower based on the collected data. It uses a multi-resolution data structure and can dynamically adjust the model accuracy, so that the wind turbine tower internal detection system based on high-precision 3D modeling can effectively control the amount of data while ensuring high-precision reconstruction of key structures. The use of advanced surface reconstruction algorithms and smoothing technology ensures the accuracy and detail retention of the model.

[0034] The artificial intelligence analysis unit provides intelligent support for the evaluation of the internal state of the tower, and is used to perform defect detection, deformation analysis and stress distribution prediction on the modeling data. The unit includes a defect detection model, a deformation analysis module and a stress distribution prediction module. These modules are based on deep learning technology and can automatically identify potential problems and provide decision support for preventive maintenance.

[0035] The mixed reality visualization and interaction unit is used to present modeling results and analysis data, greatly improving the intuitiveness and efficiency of inspection and maintenance work. The unit supports a variety of mixed reality devices, and through gesture control, voice commands and multi-person collaboration mode, maintenance personnel can more intuitively understand the internal conditions of the tower.

[0036] The system also includes a data management and transmission unit and an adaptive path planning module. The data management and transmission unit is used for data compression, transmission and storage, solving the problem of large-scale three-dimensional data processing. The unit adopts intelligent compression strategy, high-speed network transmission and distributed storage architecture to ensure efficient data transmission and management.

[0037] The adaptive path planning module can automatically generate the optimal inspection path according to the internal structural characteristics of the tower and the inspection requirements, ensuring the comprehensiveness and efficiency of the inspection.

[0038] The safety monitoring and emergency handling unit is used to monitor the working status of the system and handle abnormal situations. It is an important part of ensuring the reliable operation of the system. The unit monitors the working status of each part of the system in real time and activates the emergency plan when an abnormal situation occurs to ensure the safety of the detection process.

[0039] The various units of this system communicate and exchange data through standardized interfaces. This modular design not only improves the maintainability and scalability of the system, but also facilitates future upgrades and optimizations.

[0040] Through the collaborative work of the above-mentioned units, the wind turbine tower internal detection system based on high-precision three-dimensional modeling of the present invention can efficiently and accurately complete the detection and modeling tasks inside the tower, and provide comprehensive and reliable data support for the maintenance and management of the wind turbine.

[0041] Embodiment 2: The present invention proposes a method for detecting the interior of a wind turbine tower based on high-precision three-dimensional modeling. Figure 2 As shown, the method includes the following steps: system initialization and self-checking, adaptive path planning, multimodal data acquisition, real-time data processing and SLAM (Simultaneous Localization and Mapping), multi-scale adaptive modeling, artificial intelligence-driven data analysis, mixed reality visualization and interaction, data management and transmission, and security monitoring and emergency response: S1. System initialization and self-test: The operator first transports the autonomous mobile detection device to the bottom of the wind turbine tower. After the system is started, it automatically performs a comprehensive self-test procedure, including but not limited to functional testing of each module, sensor calibration, communication link inspection, etc. The self-test results will be fed back to the operator in real time to ensure that the system is in the best working condition.

[0042] S2. Adaptive path planning: After the system self-check is completed, the adaptive path planning module starts working. This module first builds an initial environmental model through preset tower structure data and real-time environmental perception. Subsequently, an improved global path planning algorithm (such as a variant of the A* algorithm) is used to generate the initial path. During the detection process, the system dynamically adjusts the path based on the real-time collected data, uses local path planning algorithms (such as the dynamic window method) to avoid obstacles, and ensures 100% coverage while minimizing detection time.

[0043] S3. Multimodal data collection: During the inspection process, the system adopts an adaptive data acquisition strategy. This strategy dynamically adjusts the working parameters of each sensor according to the complexity of the environment and the inspection requirements. For example, a higher laser scanning density is used in high curvature areas (such as around welds and bolts), while the scanning density is appropriately reduced in flat areas. The sampling frequency of the panoramic camera and thermal imaging camera will also be adjusted as needed. Ultrasonic thickness measurement focuses on sampling at key structural locations. At the same time, the system evaluates data quality in real time and automatically performs additional collection when necessary.

[0044] S4. Real-time data processing and SLAM (Simultaneous Localization and Mapping): The collected multimodal data is first processed on the autonomous mobile detection device. This includes data preprocessing (such as denoising, downsampling), feature extraction, initial pose estimation and local map construction. The processed data is transmitted to the cloud server via a high-speed network for further optimization. Cloud processing includes global map optimization, loop detection, multi-sensor data fusion, etc. The system uses an improved graph optimization algorithm to improve the accuracy and robustness of SLAM.

[0045] S5. Multi-scale adaptive modeling: Based on the SLAM (Simultaneous Localization and Mapping) results, the system begins to build a 3D model of the tower interior. Figure 3 As shown in the figure, multi-resolution data structures (such as improved octrees) are used to store and process point cloud data. The system dynamically adjusts the model accuracy based on geometric complexity and semantic information, effectively controlling the amount of data while ensuring high-precision reconstruction of key structures. For complex areas, the system uses advanced surface reconstruction algorithms (such as improved Poisson reconstruction) and adaptive mesh subdivision technology to ensure the accuracy and detail retention of the model. At the same time, the system also performs texture mapping, fuses visible light and thermal imaging data, and provides richer surface information.

[0046] S6. AI-driven data analysis: Based on the construction of the 3D model, the system uses a series of artificial intelligence algorithms to conduct in-depth analysis, such as Figure 4 As shown, including: a) Defect detection: Use improved deep learning models (such as variants of PointNet++) to segment and classify point cloud data to identify potential defects such as cracks, corrosion, and deformation.

[0047] b) Deformation analysis: By comparing the current model with historical data, a high-precision deformation thermal map is generated. The system also uses a time series analysis algorithm to predict possible future deformation trends.

[0048] c) Stress distribution prediction: Combining finite element analysis and machine learning methods, the stress distribution of the tower structure is predicted based on the geometric model, material parameters and environmental data.

[0049] d) Life assessment: Taking into account the test results, historical data and environmental factors, the remaining life of key tower components is assessed.

[0050] S7. Mixed reality visualization and interaction: The system imports modeling and analysis results into mixed reality applications. Maintenance personnel can interact with 3D models through mixed reality devices (such as head-mounted displays). Functions include but are not limited to: a) Virtual Tour: A 1:1 scale virtual environment of the tower interior, supporting free navigation and zooming.

[0051] b) Multi-layer data visualization: can switch to display multiple layers of information such as geometric model, thermal imaging data, stress distribution, etc.

[0052] c) Real-time annotation: supports adding marks and annotations to the model and sharing it with other team members in real time.

[0053] d) Intelligent query: Quickly locate a specific area or retrieve relevant data through voice or gesture commands.

[0054] S8. Data Management and Transfer: The system adopts a hierarchical data management strategy: a) Edge storage: Short-term data caching on autonomous mobile detection devices to support offline working mode.

[0055] b) Cloud storage: Use a distributed file system to store raw data and use spatiotemporal indexing to optimize retrieval efficiency.

[0056] c) Intelligent compression: Differentiated compression strategies are adopted according to the importance of data to optimize storage space while ensuring key information.

[0057] d) Incremental update: Only the changed data is transmitted and stored, reducing network load and storage requirements.

[0058] S9. Safety monitoring and emergency response: During the entire detection process, the system continuously performs security monitoring: a) Real-time status monitoring: monitor key parameters such as position, posture, and power of the autonomous mobile detection device.

[0059] b) Environmental perception: Detect changes in the surrounding environment, such as abnormal temperature, gas concentration, etc.

[0060] c) Fault diagnosis: Use machine learning algorithms to analyze system operation data in real time and predict possible faults.

[0061] d) Emergency plan: According to different abnormal situations, the system can automatically start the corresponding emergency handling process, such as safe recovery, emergency braking, etc.

[0062] Through the combination of the above steps, the wind turbine tower internal detection method based on high-precision three-dimensional modeling of the present invention can efficiently, safely and accurately complete the tower internal detection task. The method not only provides comprehensive and reliable detection data, but also provides strong support for wind turbine maintenance and management decisions through artificial intelligence analysis and mixed reality technology. In addition, the modular design of the method makes it have good adaptability and scalability, and can be flexibly adjusted and optimized according to different application scenarios.

[0063] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A wind turbine tower internal detection system based on high-precision three-dimensional modeling, characterized in that: include: A multimodal data acquisition device, used for acquiring multimodal data; Real-time data processing and SLAM unit, used to perform SLAM processing on the collected multimodal data; Multi-scale adaptive modeling unit, used to build a 3D model of the tower interior based on SLAM results; The artificial intelligence analysis unit is used to analyze and detect the interior of the wind turbine tower based on the three-dimensional model of the interior of the tower.

2. The wind turbine tower internal detection system based on high-precision three-dimensional modeling according to claim 1 is characterized in that: It also includes an autonomous mobile detection device for performing functional tests of each module, sensor calibration and communication link checks.

3. The wind turbine tower internal detection system based on high-precision three-dimensional modeling according to claim 2 is characterized in that: It also includes an adaptive path planning module, which is used to automatically generate an optimal detection path according to the internal structural characteristics of the tower and detection requirements.

4. The wind turbine tower internal detection system based on high-precision three-dimensional modeling according to claim 1 is characterized in that: It also includes a mixed reality visualization and interaction unit for visualization of the three-dimensional model and analysis data inside the tower and for human-computer interaction.

5. The wind turbine tower internal detection system based on high-precision three-dimensional modeling according to claim 1 is characterized in that: It also includes a safety monitoring and emergency processing unit, which is used to monitor the working status of the system and process different anomalies.

6. A method for detecting the interior of a wind turbine tower based on high-precision three-dimensional modeling, based on the wind turbine tower interior detection system based on high-precision three-dimensional modeling according to claim 1, characterized in that: The following steps are involved: Dynamically adjust the working parameters of each sensor according to the complexity of the environment and detection requirements to collect multi-modal data; Process the collected multimodal data and perform SLAM to obtain point cloud data inside the tower; Based on the point cloud data inside the tower, a three-dimensional model of the interior of the tower is constructed; Based on the three-dimensional model of the interior of the tower, the interior of the wind turbine tower is analyzed and inspected.

7. The method for detecting the interior of a wind turbine tower based on high-precision three-dimensional modeling according to claim 6, characterized in that: The working parameters of each sensor are dynamically adjusted according to the environmental complexity and detection requirements to collect multimodal data, specifically: Perform adaptive path planning, build an initial environment model through preset tower structure data and real-time environment, generate a detection path using a global path planning algorithm, and dynamically adjust the detection path during the detection process; Based on the detection path, the working parameters of each sensor are dynamically adjusted according to the environmental complexity and detection requirements to perform multimodal data collection.

8. The method for detecting the interior of a wind turbine tower based on high-precision three-dimensional modeling according to claim 6, characterized in that: The processing and SLAM of the collected multimodal data are specifically as follows: After feature extraction and initial pose estimation of the collected multimodal data, local map construction is performed; The constructed local map is optimized and loop detection is performed on the global map to obtain the point cloud data and posture information inside the tower.

9. The method for detecting the interior of a wind turbine tower based on high-precision three-dimensional modeling according to claim 6, characterized in that: The three-dimensional model of the interior of the tower is constructed based on the point cloud data inside the tower, specifically: Use octree structure to store and process point cloud data; The model accuracy is dynamically adjusted according to the geometric complexity and semantic information of each octree node, and high-precision reconstruction is used for complex areas.

10. The method for detecting the interior of a wind turbine tower based on high-precision three-dimensional modeling according to claim 6, characterized in that: The analysis and detection of the interior of the wind turbine tower is performed based on the three-dimensional model of the interior of the tower, specifically: Use deep learning models to perform defect detection, deformation analysis, and stress distribution prediction, as well as remaining life assessment of key tower components.

Images