受测试成本、安全性、可靠性等因素的制约，需要依托以模型船为载体的物理实验平台实现从虚拟仿真测试到全尺寸实船测试之间的过渡。本文基于“航行脑”系统体系架构设计思想，采用船-岸-云分布式监控与数据采集架构，研发由能源管理、感知、决策、执行、通信等模块组成的船舶智能航行功能物理试验平台，打造“求新”系列缩尺比自航船模。开展回转试验、Z形试验、单船自主循迹、船舶编队等测试，验证了系统的有效性，并提出未来改进方向。
In the research of ship test and verification technology, restricted by factors such as test cost, safety, and reliability, it is necessary to rely on the physical experiment platform with the scale model ship as the carrier to realize the transition test link between virtual simulation test and full-scale real ship test. Based on the design idea of the navigation brain system, a physical experiment platform with the scale model ship is developed, which consists of five modules of power supply, perception, decision-making, execution, and communication, and three monitoring and data acquisition systems of the ship, shore, and cloud. The Qiuxin series of scaled model ships are constructed. The effectiveness of the system is verified by turning tests, zigzag tests, path-following control tests, and formation control tests. Finally, the test performance and future improvement direction of the test platform are summarized and prospected.
2024,46(3): 169-173 收稿日期：2022-08-10
DOI：10.3404/j.issn.1672-7649.2024.03.031
分类号：U692.5+1
基金项目：南方海洋科学与工程广东省实验室（珠海）资助项目（SML2021SP101）；国家自然科学基金资助项目（52272425，62003250）
作者简介：韩成浩(1996-),男,硕士研究生,研究方向为智能船舶运动控制
参考文献：
[1] 孙峰, 蔡玉良, 马吉林. 船舶智能避碰策略测试方法与指标研究[J]. 交通信息与安全, 2019, 37(5): 84–93
[2] 刘佳仑, 杨帆, 马枫, 等. 智能船舶航行功能测试验证的方法体系[J]. 中国舰船研究, 2021, 16(1): 45–50
[3] MU D, WANG G, FAN Y, et al. Path following for podded propulsion unmanned surface vehicle: Theory, simulation and experiment[J]. IEEJ Transactions on Electrical and Electronic Engineering, 2018.
[4] 文元桥, 杨吉, 李通, 等. 一种面向科研试验的无人艇[J]. 船舶工程, 2019, 41(1): 11–16+39
[5] GU N, PENG Z, WANG D, et al. Anti-disturbance coordinated path following control of robotic autonomous surface vehicles: theory and experiment[J]. IEEE/ASME Transactions on Mechatronics, 2019, 24(5): 2386–2396
[6] NAAEM W, IRWIN G W, YANG A. COLREGs-based collision avoidance strategies for unmanned surface vehicles[J]. Mechatronics, 2012, 22(6): 669–678
[7] 刘彬. 多无人艇协同编队控制理论及实验研究[D]. 武汉: 华中科技大学, 2019.
[8] THYRI E H, BREIVIK M, LEKKAS A M. A Path-velocity decomposition approach to collision avoidance for autonomous passenger ferries in confined waters[J]. IFAC-Papers online, 2020, 53(2): 14628–14635
[9] SHEN H, HASHIMOTO H, MATSUDA A, et al. Automatic collision avoidance of multiple ships based on deep Q-learning[J]. Applied Ocean Research, 2019(86): 268–288
[10] HINOSTROZA M A, XU H, SOARES C G. Motion planning, guidance, and control system for autonomous surface vessel[J], Offshore Mechanics and Arctic Engineering, 2018.
[11] WANG Y, CHAI S, NGUYEN H D. Experimental and numerical study of autopilot using Extended Kalman Filter trained neural networks for surface vessels[J]. International Journal of Naval Architecture and Ocean Engineering, 2020(12): 314–324
[12] 严新平, 吴超, 马枫. 面向智能航行的货船“航行脑”概念设计[J]. 中国航海, 2017, 40(4): 95-98+136.
[13] WANG L, LI S, LIU J, et al, Data-driven model identification and predictive control for path-following of underactuated ships with unknown dynamics [J], International Journal of Naval Architecture and Ocean Engineering, 2022.
