Abstract
To improve the performance of particle swarm optimization (PSO), PSO is further improved by being combined with the sine cosine algorithm (SCA), which maintains a balance in exploration and exploitation. Furthermore, to speed up searching for the optimal path with grounding avoidance, a quasi-reflection-based sine cosine particle swarm optimization (SC-PSO) is designed. Its convergence is then proven. In the early stage, it can roam around the whole space and enhance the global search ability. In the later stage of the optimization process, the convergence ability of global optimization is strengthened. The quasi-reflection operation is introduced into the algorithm to improve the diversity of solutions. A new fitness function is developed to transform the path planning into an optimization problem, combined with the optimization standards and constraints of path length, grounding threat, collision avoidance with water targets and path smoothness, so as to realize the safe and efficient operation of ships. For grounding avoidance, the distance of the closest point of pass (DCPP), the distance of close-quarters situation of ground (DCQG), the time of close-quarters situation of ground (TCQG) and the distance from the ship to the shallows (DIS) are considered. To verify the shallow and collision avoidance of the actual ship operation, the terrain fluctuation data with the highest resolution built from global and regional data sets is used. EETOPO1 is a 1 arc-minute global relief model of Earth's surface that integrates land topography and ocean bathymetry. 3D seabed terrain and 3D collision avoidance are used for grounding avoidance in ship track planning. The results show that, compared with SCA and PSO, the new algorithm has the fastest convergence speed and the highest calculation accuracy.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have