Research on Key Technologies for Intelligent Detection of Underwater Pipelines with Multi-Tech Integration

DOI: https://doi.org/10.62517/jes.202502213

Author(s)

Huanbin Chen1, Shudong Xie1, Guanghong Xin1,2,*

Affiliation(s)

1Sanya University, New Energy and Intelligent Connected Vehicle College, Sanya, China 2Zhai Mingguo Academic Workstation of Sanya University, Sanya, China *Corresponding Author

Abstract

In response to the challenges such as light attenuation, water flow interference and unstable communication faced by intelligent underwater pipeline detection, as well as the limitations of traditional methods in image quality, motion control and data transmission, this study proposes a multi-technology integration solution, integrating visual enhancement, intelligent control and efficient communication technologies, aiming to break through the bottleneck of the "perception - control - communication" collaborative optimization of underwater robots. Based on multi-scale Retinex and CLAHE algorithms, the image signal-to-noise ratio is improved by 40%; using adaptive sliding mode control, the precision of fixed-depth hovering is ±0.05 m, and the path tracking error is reduced by 75%; optimizing OFDM modulation, a transmission rate of 180 Mbps can be achieved at a depth of 30 m, with a packet loss rate lower than 0.5%. At the same time, through the design of a streamlined structure and a 45° inclined propeller, the flow resistance is reduced by 40%; improving YOLOv5 combined with multi-scale attention mechanism, the detection accuracy in turbid waters reaches 92.3%. This study not only provides theoretical support and engineering paradigms for the inspection of deep-sea infrastructure, but also provides important technical guarantees for the implementation of the "Smart Ocean" strategy, and has significant theoretical significance and application value.

Keywords

Underwater Pipeline Inspection; Intelligent Control; Visual Enhancement; Orthogonal Frequency-Division Multiplexing Communication

References

[1]A. Quattrini Li, C. J. Carver, Q. Shao, X. Zhou, and S. Nelakuditi, "Communication for Underwater Robots: Recent Trends," Current Robotics Reports, vol. 4, no. 2, pp. 13 - 22, 2023, doi: 10.1007/s43154-023-00100-4. [2]L. Sun, Y. Wang, X. Hui, X. Ma, X. Bai, and M. Tan, “Underwater Robots and Key Technologies for Operation Control,” Cyborg Bionic Syst., vol. 5, p. 0089, 2024. DOI: 10.34133/cbsystems.0089 [3]K. Liao, X. Peng, "Underwater image enhancement using multi - task fusion," PLOS ONE, vol. 19, no. 2, p. e0299110, 2024, doi: 10.1371/journal.pone.0299110. [4]C. Yang, S. Liu, H. Su, L. Zhang, Q. Xia, and Y. Chen et al., “Review of underwater adsorptive-operating robots: Design and application,” Ocean Engineering, vol. 294, p. 116794, 2024. [5]S. Raveendran, M. D. Patil, and G. K. Birajdar et al., “Underwater image enhancement: A comprehensive review, recent trends, challenges, and applications,” Artificial Intelligence Review, vol. 54, pp. 5413–5467, 2021. [6]J. Qu, Y. Xu, Z. Li, Z. Yu, B. Mao, Y. Wang, Z. Wang, Q. Fan, X. Qian, M. Zhang, M. Xu, B. Liang, H. Liu, X. Wang, X. Wang, and T. Li, “Recent Advances on Underwater Soft Robots,” Advanced Intelligent Systems, vol. 6, no. 2, 2023, doi: 10.1002/aisy.202300299. [7]G. Chen, W. Chen, Z. Wang, T. Guo, X. Xia, and L. Xu, “Research on the Design and Dynamic Performance of Underwater Detection Robots,” *Wireless Communications and Mobile Computing*, vol. 2022, no. 1, 2022, doi: 10.1155/2022/3715514. [8]C. Yang, S. Liu, H. Su, L. Zhang, Q. Xia, and Y. Chen et al., “Review of underwater adsorptive-operating robots: Design and application,” Ocean Engineering, vol. 294, p. 116794, 2024, doi: 10.1016/j.oceaneng.2024.116794. [9]C. Yang, C. Gu, T. Zhang, and Y. Gao, “Underwater robot sensing technology: A survey,” Fundamental Research, vol. 1, no. 3, pp. 337–345, 2021, doi: 10.1016/j.fmre.2021.03.002. [10]D. B. Jeong and N. Y. Ko, “Sensor Fusion for Underwater Vehicle Navigation Compensating Misalignment Using Lie Theory,” Sensors, vol. 24, no. 5, 2024, doi: 10.3390/s24051653. [11]Y. Qu, M. Yang, J. Zhang, W. Xie, B. Qiang, and J. Chen, “An Outline of Multi - Sensor Fusion Methods for Mobile Agents Indoor Navigation,” Sensors, vol. 21, no. 5, 2021, doi: 10.3390/s21051605. [12]N. Chouaikit, A. A. Ali, M. M. Jawad, I. K. Bal, M. M. Nordin, and B. Otero, “Multi - Sensor Fusion for Underwater Vehicle Localization by Augmenting RBF Neural Networks and Error - State Kalman Filter,” Sensors, vol. 21, no. 4, 2021, doi: 10.3390/s21041149.