Particle swarm optimization-based subsea cable electromagnetic detection by autonomous underwater vehicle

• Published in: Neural computing & applications Vol. 37; no. 21; pp. 15995 - 16012
• Main Authors: Zhang, Jialei, Xiang, Xianbo, Zhang, Qin, Tao, Bo
• Format: Journal Article
• Language: English
• Published: London Springer London 01.07.2025; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Autonomous underwater vehicles; Cables; Communication networks; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Control algorithms; Control of Unmanned Marine Systems: Machine Learning and Computational Intelligence Solutions; Data Mining and Knowledge Discovery; Economic value added; Electromagnetism; Guidance; Horizontal orientation; Image Processing and Computer Vision; Localization; Ocean bottom; Ocean floor; Offshore energy sources; Particle swarm optimization; Probability and Statistics in Computer Science; Retrofitting; S.I.: Machine Learning/Computational Intelligence in Unmanned Marine Systems; Sensors; Special Issue on Advances in Navigation; Submarine cables; Topology; Tracking; Wind power; Electromagnetic detection; Subsea cables; Particle swarm optimization; Autonomous underwater vehicle
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-023-09060-4

Subsea cables are widely used for power and information transmission in offshore infrastructure such as global communication networks and offshore wind farms. The precise positioning of subsea cables is an important prerequisite for maintenance and repair. However, the small diameter and burial depth of 3–5 m below the seabed make locating and detecting the subsea cable technically challenging. This paper investigates the localization and intelligent tracking detection of subsea cables based on autonomous underwater vehicle (AUV) and particle swarm optimization (PSO) algorithm. First, an autonomous electromagnetic localization and tracking topology of subsea cable is designed based on AUV architecture and PSO algorithm. The basic principle of locating the horizontal position and depth of a subsea cable based on horizontal survey line measurement is illustrated. Second, the PSO algorithm is retrofitted with electromagnetic localization. Specifically, the subsea cable localization flow diagram, region of interest (ROI) and fitness function are constructed, respectively. Third, an online swath path planning method for subsea cable detection is designed based on the PSO localization results. Finally, the effectiveness of the PSO submarine cable location algorithm and the online planning method for detection paths is verified through multiple controlled simulation tests.