Unmanned ship fan tower footing inspection system and unmanned ship

Abstract

The embodiment of the invention discloses an unmanned ship fan tower footing inspection system and an unmanned ship. The system comprises a control platform and an unmanned ship body, wherein the unmanned ship body is provided with a multi-mode sensing module, a data processing module, a communication module and a control module; the multi-mode sensing module is used for detecting the structural state data and the environmental data of the fan tower footing in the detection range; the data processing module is connected with the multi-mode sensing module, receives the detected structure state data and performs fusion analysis on the structure state data to obtain health state data; the communication module is connected with the data processing module and the control platform and transmits the health state data back to the control platform. The control module is connected with the communication module and the multi-mode sensing module and controls the unmanned ship body to advance according to the inspection instruction and the environment data sent by the control platform. On the basis, in the autonomous advancing process of the unmanned ship, the health state of the fan tower footing is detected from multiple aspects through a multi-mode sensing module.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of unmanned boat inspection, and in particular, to an unmanned boat fan tower base inspection system and an unmanned boat. Background Art

[0002] With the development of technology, the offshore wind power generation technology has also been continuously developed. Due to the erosion effect of the seawater environment, it is necessary to inspect the fan tower base to ensure the safety and reliability of the fan tower base and ensure the normal operation of the fan.

[0003] Currently, the inspection of the fan tower base mainly relies on manual divers or remotely operated underwater vehicles (ROVs). However, these methods have problems such as high operation costs, low inspection efficiency, large influence by sea conditions, and high safety risks. Manual inspection requires divers to operate in complex sea conditions, which is costly and dangerous. Although ROVs can replace some operations, they still rely on manual operation and it is difficult to achieve long-term autonomous inspection. Summary of the Invention

[0004] The embodiments of the present application provide an unmanned boat fan tower base inspection system and an unmanned boat to achieve long-term autonomous inspection.

[0005] In a first aspect, the embodiments of the present application provide an unmanned boat fan tower base inspection system, including:

[0006] A control platform and an unmanned boat hull, on which a multi-modal perception module, a data processing module, a communication module, and a control module are arranged;

[0007] The multi-modal perception module is used to detect the structural state data and environmental data of the fan tower base within the detection range during the progress of the unmanned boat hull;

[0008] The data processing module is connected to the multi-modal perception module, and is used to receive the detected structural state data of the fan tower base and perform fusion analysis on the structural state data to obtain the health state data of the fan tower base;

[0009] The communication module is respectively connected to the data processing module and the control platform, and is used to transmit the health state data of the fan tower base back to the control platform;

[0010] The control module is respectively connected to the communication module and the multi-modal perception module, and is used to control the progress of the unmanned boat hull according to the inspection instructions sent by the control platform and the environmental data.

[0011] In a second aspect, the embodiments of the present application provide an unmanned boat, which includes the unmanned boat hull provided in any embodiment of the present application.

[0012] The technical solution of the embodiment of the present application, the system includes: a control platform and an unmanned boat hull, and a multi-modal perception module, a data processing module, a communication module and a control module are arranged on the unmanned boat hull; the multi-modal perception module is used to detect the structural state data and environmental data of the wind turbine tower foundation within the detection range during the progress of the unmanned boat hull; the data processing module is connected to the multi-modal perception module, and is used to receive the detected structural state data of the wind turbine tower foundation, and perform fusion analysis on the structural state data to obtain the health state data of the wind turbine tower foundation; the communication module is respectively connected to the data processing module and the control platform, and is used to transmit the health state data of the wind turbine tower foundation back to the control platform; the control module is respectively connected to the communication module and the multi-modal perception module, and is used to control the progress of the unmanned boat hull according to the inspection instruction sent by the control platform and the environmental data. Based on this, during the autonomous inspection process of the unmanned boat, the multi-modal perception module carried by it is used to detect the health state of the wind turbine tower foundation from multiple aspects, realizing autonomous, complete and accurate inspection. Description of the Drawings

[0013] Figure 1 It is a schematic structural diagram of the unmanned boat wind turbine tower foundation inspection system provided by Embodiment 1 of the present application. Detailed Embodiment

[0014] The present application will be further described in detail below with reference to the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present application, rather than limiting the present application. In addition, it should be noted that only the parts related to the present application rather than all the structures are shown in the drawings for the sake of convenience of description.

[0015] Embodiment 1

[0016] Figure 1 It is a schematic structural diagram of the unmanned boat wind turbine tower foundation inspection system provided by Embodiment 1 of the present application. As Figure 1 shown, the unmanned boat wind turbine tower foundation inspection system provided in this embodiment can be realized based on the control platform and the unmanned boat. Specifically, the unmanned boat wind turbine tower foundation inspection system can include: a control platform and an unmanned boat hull, and a multi-modal perception module, a data processing module, a communication module and a control module are arranged on the unmanned boat hull.

[0017] Among them, the control platform is usually set on the shore, and is operated, viewed and maintained by the staff. Among the modules arranged on the unmanned boat hull, the multi-modal perception module is connected to the data processing module, the data processing module is respectively connected to the communication module and the control module, and the communication module is communicatively connected to the control platform through a certain communication method.

[0018] Among them, the multi-modal perception module is used to detect the structural state data and environmental data of the wind turbine tower foundation within the detection range during the progress of the unmanned boat hull;

[0019] The data processing module is connected to the multi-modal perception module, and is used to receive the detected structural state data of the wind turbine tower foundation, and perform fusion analysis on the structural state data to obtain the health state data of the wind turbine tower foundation;

[0020] The communication module is respectively connected to the data processing module and the control platform, and is used to transmit the health state data of the wind turbine tower foundation back to the control platform;

[0021] The control module is respectively connected to the communication module and the multi-modal perception module, and is used to control the progress of the unmanned boat hull according to the inspection instructions sent by the control platform and the environmental data.

[0022] In this embodiment, during the autonomous progress inspection of the unmanned boat, the multi-modal perception module carried by it is used to detect the health state of the wind turbine tower foundation from multiple aspects, realizing autonomous, complete and accurate inspection.

[0023] Specifically, the multi-modal perception module includes sensors such as underwater high-definition cameras, structured light imaging, multi-beam sonar, and side-scan sonar. The structural state data includes corrosion data, crack data, settlement data, and biological attachment data of the wind turbine tower foundation.

[0024] For the crack data, the multi-modal perception module is used to obtain the sensing data of multiple sensing devices, and use a preset edge detection algorithm and a morphological processing algorithm to extract the crack data based on the sensing data of the multiple sensing devices.

[0025] Among them, the preset edge detection algorithm and the morphological processing algorithm can be specifically as follows:

[0026]

[0027] L c =max(y i )-min(y i )

[0028] Among them, x i,max and x i,min are the maximum and minimum abscissas of the crack area, and y i is the ordinate of the crack area.

[0029] For the settlement data, the multi-modal perception module is used to determine the settlement data of the tower foundation based on the sensing data of the multiple sensing devices by using a preset point cloud registration algorithm and a Kalman filtering algorithm. Among them, the preset point cloud registration algorithm and the Kalman filtering algorithm can be as follows:

[0030]

[0031] Among them, is the current point cloud, is the historical point cloud, and R, T are the rotation and translation matrices.

[0032] Specifically, the above algorithm can accurately obtain the surface damage and settlement information of the wind turbine tower base, improve the perception ability of the unmanned boat under complex sea conditions, and provide high-quality input data for data processing and decision-making in the subsequent data processing module, ensuring the reliability and accuracy of the inspection task.

[0033] In addition, for the biofouling data, the multi-modal perception module is used to determine the biofouling data of the tower base based on the preset deep learning segmentation network and the biofouling area algorithm, using the sensing data of the multiple sensing devices.

[0034] Among them, the deep learning segmentation network is mainly used for the detection of barnacles and seaweeds. In a specific example, it can be based on the U-Net semantic segmentation network, and its optimized loss function is as follows:

[0035] L = L ce + λL dice ,

[0036] Among them, A and B are the predicted region and the true annotation region respectively, and λ is the loss weight. In addition, the biofouling area calculation formula is as follows:

[0037]

[0038] Among them, p i is the number of pixel points in the predicted segmentation region, and A pixel is the physical area corresponding to a single pixel point.

[0039] The above algorithm can effectively detect and evaluate the biofouling situation on the surface of the tower base, provide accurate area measurement results, and provide cleaning suggestions for the operation and maintenance personnel to reduce the impact of marine biofouling on the stability of the tower base and improve the long-term operation safety of the wind turbine equipment.

[0040] In addition, the data processing module is used to perform fusion analysis on the structural state data using the Bayesian fusion algorithm to obtain the health state data of the tower base. Among them, for any health trend, the Bayesian fusion algorithm is used to determine the intermediate state estimate, and combined with the preset anomaly detection algorithm, the deviation degree of the health trend type is determined based on the intermediate state estimate, and the deviation degree is determined as the health trend of the current type.

[0041] It should be noted that the health trends refer to the corrosion hotspot spread trend, crack propagation trend, and settlement trend. When determining the intermediate state estimate, the following algorithm can be used:

[0042] p(x k |z k ) = ηp(z k |x k )∫p(x k |x k-1 )p(x k-1 |z 1:k-1 )dx k-1

[0043] where p(x k |z k ) is the state estimate given the measurement data z k , p(z k |x k ) is the measurement probability, p(x k |x k-1 ) is the state transition probability, and η is the normalization coefficient.

[0044] [[ID=4)]]Then, when determining the deviation degree, statistical anomaly detection can be combined:

[0045] D anomaly = ∑P(S t |H) - P(s t |O)

[0046] where P(S t |H) represents the probability of the tower base state under normal conditions, and P(S t |O) represents the probability of the tower base state detected currently.

[0047] The above algorithm can fuse various sensor data, improve the accuracy of tower base damage detection, and identify potential structural problems through anomaly detection methods, thus providing reliable health assessment information for the operation and maintenance of the wind turbine.

[0048] For the communication module, 5G / satellite dual-mode communication and a preset adaptive bandwidth optimization algorithm can be used to connect the hull of the unmanned boat and the control platform. Specifically, the communication module adopts 5G / satellite dual-mode communication technology and combines an adaptive bandwidth optimization algorithm. The optimization formula is as follows:

[0049]

[0050] where r t is the current bandwidth, r t is the real-time channel state, is the historical mean, and α is the learning rate.

[0051] This algorithm can adaptively adjust the data transmission rate according to the changes in the marine communication environment, improve the stability of data backhaul, ensure the real-time nature of remote monitoring, and support information sharing among multiple unmanned boats to improve the efficiency of collaborative inspection.

[0052] For information sharing among unmanned boats, the communication module is also used to communicate with the hulls of other unmanned boats working together, and complete the inspection of the same wind turbine tower base by sharing the inspection path. Among them, the planned paths can be shared. Since the coordinate systems during the path planning of each unmanned boat may not be exactly the same, but the unmanned boats working together usually connect to the same control platform. Therefore, based on the coordinates and orientation of the control platform, the coordinate system can be unified, so as to achieve non-overlapping and error-free of the paths planned by each unmanned boat, realize the inspection of the same wind turbine tower base by multiple unmanned boats, and improve the inspection efficiency.

[0053] For the control module, the control module uses a preset mixed-integer linear programming algorithm and the environmental data for path planning, and controls the movement of the unmanned boat hull according to the path planning.

[0054] Among them, when performing path planning, the mixed-integer linear programming (MILP) + A* algorithm can be used for path planning, and the objective function is as follows:

[0055]

[0056] Constraint conditions:

[0057]

[0058] Among them, C ij is the path cost (energy consumption / time) of the unmanned boat from wind turbine tower base i to tower base j. Local obstacle avoidance uses the dynamic window approach (DWA) to calculate the optimal speed:

[0059]

[0060] Among them, h goal represents the score for driving towards the target point, h obstacle represents the obstacle avoidance score, and h velocity is the speed smoothness score.

[0061] This algorithm can globally optimize the inspection path of the unmanned boat, and combine local obstacle avoidance strategies to achieve efficient and safe task planning, ensure that the unmanned boat stably performs inspection tasks under complex sea conditions, and improve the task completion rate.

[0062] In addition, the hull of the unmanned boat in this embodiment can adopt a design adaptable to wind and waves, be made of high-strength composite materials, have excellent wind and wave resistance and impact resistance, and be able to operate stably under complex sea conditions, ensuring that the unmanned boat can continuously perform tasks for a long time in the harsh environment of the wind farm.

[0063] In this embodiment, through the combination of multiple sensors such as underwater high-definition cameras, structured light imaging, multibeam sonar, and sidescan sonar, the detection accuracy of corrosion, cracks, settlement, and biological attachment is improved, and Bayesian data fusion, point cloud registration, deep learning segmentation, and anomaly detection algorithms are used to optimize data processing. Combining path planning and obstacle avoidance algorithms improves the inspection efficiency. In addition, the system integrates 5G / satellite dual-mode communication, supports remote real-time data transmission back and cooperative operation of unmanned boats, reduces manual intervention, improves the intelligent level of inspection, and ensures the structural safety of the long-term operation of the wind turbine tower foundation. By integrating technologies such as multi-sensor data fusion, intelligent inspection path optimization, and remote data transmission, the unmanned boat can work stably under complex sea conditions and extreme weather conditions, significantly improving the intelligent level of wind turbine tower foundation inspection, reducing operation and maintenance costs, and ensuring the long-term safety and stability of the wind turbine foundation structure, with broad application prospects.

[0064] Embodiment Two

[0065] This embodiment provides an unmanned boat, and the unmanned boat includes the hull of the unmanned boat provided in Embodiment One.

[0066] Among them, a multi-modal sensing module, a data processing module, a communication module, and a control module are arranged on the hull of the unmanned boat.

[0067] Among them, the control platform is usually set on the shore and is operated, viewed, and maintained by staff. Among the modules arranged on the hull of the unmanned boat, the multi-modal sensing module is connected to the data processing module, the data processing module is respectively connected to the communication module and the control module, and the communication module is communicatively connected to the control platform through a certain communication method.

[0068] Among them, the multi-modal sensing module is used to detect the structural state data and environmental data of the wind turbine tower foundation within the detection range during the progress of the hull of the unmanned boat;

[0069] The data processing module is connected to the multi-modal sensing module and is used to receive the detected structural state data of the wind turbine tower foundation and perform fusion analysis on the structural state data to obtain the health state data of the wind turbine tower foundation;

[0070] The communication module is respectively connected to the data processing module and the control platform and is used to transmit the health state data of the wind turbine tower foundation back to the control platform;

[0071] The control module is respectively connected to the communication module and the multi-modal perception module, and is used to control the movement of the unmanned boat hull according to the inspection instructions sent by the control platform and the environmental data.

[0072] In this embodiment, during the autonomous inspection process of the unmanned boat, the multi-modal perception module carried by it is used to detect the health status of the wind turbine tower base from multiple aspects, realizing an autonomous, complete and accurate inspection.

[0073] Note that the above is only a preferred embodiment of the present application and the technical principles applied. Those skilled in the art will understand that the present application is not limited to the specific embodiments here, and various obvious changes, re-adjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments only. Without departing from the concept of the present application, more other equivalent embodiments can be included, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. An inspection system for the wind turbine tower base of an unmanned boat, characterized in that, The system includes: a control platform and an unmanned boat hull, wherein the unmanned boat hull is provided with a multimodal perception module, a data processing module, a communication module and a control module; The multimodal perception module is used to detect the structural status data and environmental data of the wind turbine tower base within the detection range during the movement of the unmanned boat hull; The data processing module is connected to the multimodal perception module, and is used to receive the detected structural status data of the wind turbine tower base, and perform fusion analysis on the structural status data to obtain the health status data of the wind turbine tower base; The communication module is connected to the data processing module and the control platform respectively, and is used to transmit the health status data of the wind turbine tower base back to the control platform; The control module is connected to the communication module and the multimodal perception module respectively, and is used to control the movement of the unmanned boat according to the inspection instructions sent by the control platform and the environmental data.

2. The system according to claim 1, wherein The structural status data includes crack data of the wind turbine tower base; The multimodal perception module is used to obtain sensing data from multiple sensing devices, and to extract crack data based on the sensing data from the multiple sensing devices using a preset edge detection algorithm and a morphological processing algorithm.

3. The system according to claim 2, wherein The structural state data includes settlement data; The multimodal perception module is used to determine the settlement data of the tower foundation based on the sensing data of the multiple sensing devices using a preset point cloud registration algorithm and a Kalman filter algorithm.

4. The system according to claim 2, wherein The structural state data includes biological attachment data; The multimodal perception module is used to determine the biological attachment data of the tower base based on the sensing data of the multiple sensing devices using a preset deep learning segmentation network and a biological attachment area algorithm.

5. The system according to claim 1, wherein The data processing module is used to perform fusion analysis on the structural status data using a Bayesian fusion algorithm to obtain health status data of the tower foundation.

6. The system according to claim 5, wherein The health status data includes multiple types of health trends; For any health trend, the Bayesian fusion algorithm is used to determine an intermediate state estimate, and combined with a preset anomaly detection algorithm, the deviation of the health trend type is determined based on the intermediate state estimate, and the deviation is determined as the current type of health trend.

7. The system according to claim 1, characterized in that, The communication module utilizes 5G / satellite dual-mode communication and a preset adaptive bandwidth optimization algorithm to connect the unmanned boat hull and the control platform.

8. The system according to claim 7, characterized in that The communication module is also used to communicate with other unmanned boats working together to complete the inspection of the same wind turbine tower base through a shared inspection path.

9. The system according to claim 1, characterized in that, The control module performs path planning using a preset mixed integer linear programming algorithm and the environmental data, and controls the movement of the unmanned boat according to the path planning.

10. An unmanned boat, characterized in that, The unmanned boat comprises the unmanned boat hull according to any one of claims 1 to 9.

Images