CN-121990113-A - Tension abnormality detection method and device for anchoring system on floating photovoltaic platform

CN121990113ACN 121990113 ACN121990113 ACN 121990113ACN-121990113-A

Abstract

The application provides a tension abnormality detection method and device for an anchoring system on a floating type photovoltaic platform, wherein after tension data of each mooring point and real-time storm direction data of the floating type platform are collected in real time, an initial tension distribution topological graph is constructed based on a platform structure of the floating type platform and arrangement information of each mooring point, tension data of each mooring point is mapped to the initial tension distribution topological graph, the mapped tension distribution topological graph is input into a pre-trained abnormality identification model to identify abnormal nodes with abnormal tension distribution, and a target sea anchor which is invalid is positioned based on the position of the mooring point corresponding to the abnormal node and the real-time storm direction data. The method can accurately identify and position the early tension abnormality of the floating type photovoltaic platform anchoring system in real time, and obviously improves the safety and operation and maintenance efficiency of the platform.

Inventors

ZHANG ZENGHUI
FENG WEIKANG
LIU RUICHAO
Huang Hezha
ZHAN GUILONG
Shi Qiayin
CHENG BIN
LEI YU
CHEN JIANJUN
WEN DONGBIN

Assignees

华能(福建漳州)能源有限责任公司
中国华能集团清洁能源技术研究院有限公司

Dates

Publication Date: 20260508
Application Date: 20260324

Claims (10)

1. A method of detecting tension anomalies in a mooring system on a floating photovoltaic platform, the mooring system comprising a plurality of mooring points symmetrically disposed on the floating platform and corresponding subsea anchors connected to each mooring point by mooring lines, the method comprising: collecting tension data of each mooring point and real-time storm direction data of the floating platform in real time; Constructing an initial tension distribution topological graph based on the platform structure of the floating platform and the arrangement information of each mooring point, and mapping the tension data of each mooring point to the initial tension distribution topological graph; inputting the mapped tension distribution topological graph into a pre-trained abnormal recognition model, and recognizing abnormal nodes with abnormal tension distribution; and positioning a failed target submarine anchor based on the position of the mooring point corresponding to the abnormal node and the real-time wind wave direction data.
2. The method of claim 1, wherein the tension data is measured by a tension sensor mounted on each mooring point; the real-time wind and wave direction data is measured by a anemoscope and a wave direction meter mounted on the floating platform.
3. The method of claim 1, wherein constructing an initial tension profile topology based on the platform structure of the floating platform and the placement information of each mooring point and mapping tension data for each mooring point to the initial tension profile topology comprises: Acquiring the position of each mooring point on the floating platform; Determining each mooring point as a node, and connecting nodes corresponding to the mooring points which are adjacent in space and have a direct mechanical coupling relation through the platform structure based on the positions of the mooring points on the floating platform by edges to construct a static initial tension distribution topological graph; And assigning the tension data acquired in real time on each mooring point as node characteristics of the corresponding node to obtain a tension distribution topological graph reflecting the tension transmission path of the mooring system in the physical space.
4. The method of claim 1, wherein the pre-trained anomaly identification model is constructed by a graph neural network; Inputting the mapped tension distribution topological graph into a pre-trained anomaly identification model to identify anomaly nodes with anomaly tension distribution, wherein the method comprises the following steps of: aggregating tension characteristics of each node and adjacent nodes thereof through at least one layer of graph convolution operation of the graph neural network so as to learn a spatial dependency relationship among nodes in the tension distribution topological graph; based on the learned spatial dependency, outputting the confidence that each node has tension abnormality, and determining the abnormal node based on the confidence that each node has tension abnormality.
5. The method of claim 1, wherein the pre-trained anomaly identification model is constructed by residual analysis; Inputting the mapped tension distribution topological graph into a pre-trained anomaly identification model to identify anomaly nodes with anomaly tension distribution, wherein the method comprises the following steps of: predicting expected tension data of each node in the tension distribution topological graph under the current environmental load according to the real-time wind wave direction data, and generating a reference tension distribution topological graph; Calculating a residual error between a real-time tension distribution topological graph formed by real-time tension data and the reference tension distribution topological graph; And determining the node with the residual value exceeding the preset threshold value as an abnormal node.
6. The method of claim 1, wherein locating the failed target sea-bottom anchor based on the mooring point position and the real-time storm direction data corresponding to the abnormal node comprises: determining a main stress direction of the floating platform and an expected high-tension mooring point area corresponding to the main stress direction according to the real-time wind wave direction data; comparing the position of the abnormal node with the expected high-tension mooring point area; And if the abnormal node is positioned in the expected high-tension mooring point area and the tension data of the abnormal node is abnormally low, determining that the submarine anchor corresponding to the abnormal node is the failed target submarine anchor.
7. The method of claim 1, wherein after collecting the tension data of each mooring point and the real-time storm direction data of the floating platform in real time, the method further comprises: And unifying the tension data and the real-time storm direction data acquired at the same time of each group under the same time stamp.
8. A tension anomaly detection apparatus for a mooring system on a floating photovoltaic platform, the mooring system comprising a plurality of mooring points symmetrically disposed on the floating platform and corresponding sea anchors connected to each mooring point by mooring lines, the apparatus comprising: The acquisition unit is used for acquiring tension data of each mooring point and real-time storm direction data of the floating platform in real time; the construction unit is used for constructing an initial tension distribution topological graph based on the platform structure of the floating platform and the arrangement information of each mooring point; a mapping unit for mapping tension data of each mooring point to the initial tension distribution topological graph; the recognition unit is used for inputting the mapped tension distribution topological graph into a pre-trained abnormal recognition model and recognizing abnormal nodes with abnormal tension distribution; the positioning unit is used for positioning the failed target submarine anchor based on the position of the mooring point corresponding to the abnormal node and the real-time wind wave direction data.
9. An electronic device, characterized in that the electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are in communication with each other through the communication bus; A memory for storing a computer program; A processor for implementing the method of any of claims 1-7 when executing a program stored on a memory.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when executed by a processor, implements the method of any of claims 1-7.

Description

Tension abnormality detection method and device for anchoring system on floating photovoltaic platform Technical Field The application relates to the technical field of ocean engineering, in particular to a tension abnormality detection method and device for an anchoring system on a floating type photovoltaic platform. Background A floating photovoltaic platform is typically secured to the seabed by a mooring system, which generally consists of mooring points on the platform, mooring lines and seabed anchors. Environmental loads (e.g., wind, waves, currents) are transferred through the platform to the mooring lines, ultimately providing resistance by the subsea anchors. In order to ensure the stability of the platform, the mooring points are often arranged symmetrically. In the prior art, after the installation of the anchoring system is completed, the safety state monitoring means is relatively deficient. Conventional practice relies mainly on periodic manual inspection or simple tension threshold alerting. The method has obvious defects that real-time monitoring cannot be realized by manual inspection, response is delayed, but a simple threshold alarm can be triggered only when tension is seriously out of limit, and an abnormal tension mode which is in a normal threshold range but occurs due to uneven distribution of environmental load cannot be identified, for example, the tension distribution of a certain anchor point is abnormal due to potential anchor failure. Therefore, the prior art is difficult to realize early and accurate positioning and early warning of the hidden faults of the anchoring system. Disclosure of Invention The embodiment of the application aims to provide a tension abnormality detection method and device for an anchoring system on a floating type photovoltaic platform, which are used for accurately identifying and positioning early tension abnormality of the anchoring system of the floating type photovoltaic platform in real time by constructing a tension distribution topological graph and applying a graph neural network or residual analysis, thereby realizing leap from passive alarm to active intelligent diagnosis and remarkably improving the safety and operation and maintenance efficiency of the platform. In a first aspect, a method for detecting tension anomalies in a mooring system on a floating photovoltaic platform, the mooring system comprising a plurality of mooring points symmetrically arranged on the floating platform and corresponding sea anchors connected to each mooring point by mooring lines, the method may comprise: collecting tension data of each mooring point and real-time storm direction data of the floating platform in real time; Constructing an initial tension distribution topological graph based on the platform structure of the floating platform and the arrangement information of each mooring point, and mapping the tension data of each mooring point to the initial tension distribution topological graph; inputting the mapped tension distribution topological graph into a pre-trained abnormal recognition model, and recognizing abnormal nodes with abnormal tension distribution; and positioning a failed target submarine anchor based on the position of the mooring point corresponding to the abnormal node and the real-time wind wave direction data. In one possible implementation, the tension data is measured by tension sensors mounted on each mooring point; the real-time wind and wave direction data is measured by a anemoscope and a wave direction meter mounted on the floating platform. In one possible implementation, constructing an initial tension distribution topology based on the platform structure of the floating platform and the placement information of each mooring point, and mapping tension data of each mooring point to the initial tension distribution topology, comprises: Acquiring the position of each mooring point on the floating platform; Determining each mooring point as a node, and connecting nodes corresponding to the mooring points which are adjacent in space and have a direct mechanical coupling relation through the platform structure based on the positions of the mooring points on the floating platform by edges to construct a static initial tension distribution topological graph; And assigning the tension data acquired in real time on each mooring point as node characteristics of the corresponding node to obtain a tension distribution topological graph reflecting the tension transmission path of the mooring system in the physical space. In one possible implementation, the pre-trained anomaly identification model is built through a graph neural network; Inputting the mapped tension distribution topological graph into a pre-trained anomaly identification model to identify anomaly nodes with anomaly tension distribution, wherein the method comprises the following steps of: aggregating tension characteristics of each node and adjacent nodes thereof throug