Ship pipe route design based on NSGA-III and multi-population parallel evolution

Abstract

Ship pipe route design (SPRD) aims to generate pipe layouts while considering various objectives and constraints in a confined 3D space, leading to extremely high complexity. To solve the problem of SPRD, traditional methods often adopt weighted summation of sub-objectives, introduce penalty functions to convert it to a single-objective optimization problem. However, these methods tend to yield a single optimal pipe route design pattern, and some existing multi-objective pipe routing algorithms do not have high search performance or sufficient treatment of constraints. Based on the grid-space decomposition model, this paper establishes a multi-objective pipe routing optimization model with several sub-objectives including path length, bends number, path energy, number of air-pockets, and number of violated bending distance, which also considers pipe routing for different diameters and interface direction requirements. A ship pipe route design framework based on the NSGA-III (Non-dominated Sorting Genetic algorithm III) is proposed, and its embedded pathfinding algorithm can explore pipe route using heuristic information and failure retry strategy, which greatly reduces the algorithm complexity compared to the classical algorithms such as A* and LEE and also facilitates parallel implementation. By employing OpenMP technology to achieve parallel evolution of multiple populations, more Pareto optimal solutions can be obtained in approximately the same timeframe as single population evolution. Finally, through comparative experiments using simulated cases, the feasibility and advancement of the proposed method are verified.