Study on ship steering based on hybrid intelligent control

• Published in: Proceedings of the 2002 American Control Conference (IEEE Cat. No.CH37301) Vol. 3; pp. 2118 - 2123 vol.3
• Main Authors: YANG, Guoxun, GUO, Chen, JIA, Xinle
• Format: Conference Proceeding
• Language: English
• Published: Piscataway NJ IEEE 2002
• Subjects: Applied sciences; Computer science; control theory; systems; Control system synthesis; Control theory. Systems; Exact sciences and technology; Fuzzy control; Fuzzy neural networks; Intelligent control; Intelligent robots; Marine vehicles; Navigation; Neural networks; Supervised learning; Uncertainty; Energy analysis; Statistical analysis; Hybrid control; Control system; Reinforcement learning; Ship maneuver; Neural network; Optimization; Fuzzy control; Neurocontrollers; Quality control; Defect; Ship; Learning algorithm; Artificial intelligence; Intelligent control
• ISBN: 0780372980; 9780780372986
• ISSN: 0743-1619; 2378-5861
• DOI: 10.1109/ACC.2002.1023949

Hybrid intelligent technique is used in ship steering control. It can make full use of the advantages of all kinds of intelligent algorithms. This provides an efficient way for the improvement of ship steering control performance. In this paper, genetic algorithm optimization is used in off-line learning period. According to the new definition of fitness function, the optimized result obtained is more suitable to the actual situation. In online learning period, reinforcement learning and neural fuzzy control are integrated. It removes the defect that the conventional hybrid intelligent algorithm learning must be provided with some sample data, and. the ship control quality is effectively improved in the case of appending additional sea state disturbance.