Evolutionary Algorithms for Optimization Sequence of Cut in the Laser Cutting Path Problem

Abstract

Efficiently cutting smaller two-dimensional parts from a larger surface area is a recurring challenge in many manufacturing environments. This point falls under the cut-and-pack (C&P) problems. This study specifically focused on a specialization of the cut path determination (CPD) known as the laser cutting path planning (LCPP) problem. The LCPP aims to determine a sequence of cutting and sliding movements for the head that minimizes the parts’ separation time. It is important to note that both cutting and glide speeds (moving the head without cutting) can vary depending on the equipment, despite their importance in real-world scenarios. This study investigates an adaptive biased random-key genetic algorithm (ABRKGA) and a heuristic to create improved individuals applied to LCPP. Our focus is on dealing with more meaningful instances that resemble real-world requirements. The experiments in this article used parameter values for typical laser cutting machines to assess the feasibility of the proposed methods compared to an existing strategy. The results demonstrate that solutions based on metaheuristics are competitive and that the inclusion of heuristics in the creation of the initial population benefits the execution of the evolutionary strategy in the treatment of practical problems, achieving better performance in terms of the quality of solutions and computational time.

A review of reinforcement learning based hyper-heuristics

“…With the capability to explore complex search spaces, EAs offer remarkable adaptability and parallelization ease ( Young et al, 2015 ). At present, EAs find extensive application across diverse research domains, including sequence optimization ( Lutz et al, 2023 ; Junior et al, 2023 ), scheduling ( Chen et al, 2023 ; Wang, Li & Gao, 2023 ; Wang et al, 2023 ), object recognition ( Afif et al, 2023 ; Zhang, Li & Qi, 2023 ).…”