An Improved Method for Optimizing CNC Laser Cutting Paths for Ship Hull Components with Thicknesses up to 24 mm

Abstract

In this paper, the essence and optimization objectives of the hull parts path optimization problem of CNC laser cutting are described, and the shortcomings of the existing optimization methods are pointed out. Based on the optimization problem of the hull parts CNC laser cutting path, a new part-cutting constraint rule based on partial cutting is proposed, which aims to overcome the drawbacks of the traditional algorithms with serial cutting constraint rules. This paper addresses the problem of optimizing the path for CNC laser cutting of hull parts, including an empty path and the order and directions used for the provided cut contours. Based on the discretization of the part contour segments, a novel toolpath model for hull parts called hull parts cutting path optimization problems based on partial cutting rules (HPCPO) is proposed in this paper. To solve the HPCPO problem, a segmented genetic algorithm based on reinforcement learning (RLSGA) is proposed. In RLSGA, the population is viewed as an intelligent agent, and the agent’s state is the population’s diversity coefficient. Three different segmented crossover operators are considered as the agent’s actions, and the agent’s reward is related to the changes in the population’s fitness and diversity coefficients. Two benchmark problems for HPCPO were constructed to evaluate the performance of RLSGA and compared with four other algorithms. The results showed that RLSGA outperformed the other algorithms and effectively solved the HPCPO problem.