Ship Pipe Route Design Using Improved A* Algorithm and Genetic Algorithm

TL;DR: This article proposes automatic approaches for solving ship pipe route design with A* algorithm and genetic algorithm and the feasibility and effectiveness of the proposed algorithms are demonstrated by the experiments on the designed and actual cases.

Abstract: The goal of ship pipe route design (SPRD) is to seek the near-optimal paths that meet various constraints and objectives. Due to the complex construction of routing space, diverse piping constraints, and the large number of pipes, SPRD is one of the most difficult and time-consuming tasks even to a skilled pipe designer. This article proposes automatic approaches for solving SPRD with A* algorithm and genetic algorithm (GA). Firstly, by simplifying the equipment and decomposing the routing space into grids, the mathematical model of SPRD is created. Then, the improved A* algorithm (A*-Router) for single pipe routing is introduced. The evaluation function, auxiliary tables and algorithm framework of A*-Router are presented. To obtain high-quality and diverse layouts, the improved GA (A*-GA-Router) is formulated by A*-Router and the connection-points strategy. Several new genetic operators of A*-GA-Router are designed to improve the routing performance. For multiple pipes routing, the novel algorithm (Multi-Pipes-Router) which calls A*-GA-Router internally is put forward. It arranges pipes according to the specified routing sequence and can produce parallel layout under the function of GA optimization and connection-points strategy. To cope with branch-pipe routing widely existing in engineering, a new pipe router (Branch-Pipe-Router) is put forward using a modified Steiner Tree framework in combination with the proposed single pipe routing algorithms. Compared with the traditional methods based on coevolution, it is more versatile and can effectively balance the layout quality and time efficiency. Finally, the feasibility and effectiveness of the proposed algorithms are demonstrated by the experiments on the designed and actual cases.