A grey wolf optimization algorithm for solving partial destructive disassembly line balancing problem consider feasibility evaluation and noise pollution

Abstract

Partial destructive disassembly (PDD) is a crucial tool for enhancing efficiency and reducing disassembly costs when recycling complex end-of-life (EOL) products. Evaluating the feasibility of PDD is crucial for determining its implementation. However, the existing partial destructive disassembly line balancing (PDDLB) problem prioritizes profitability and randomly selects components for destructive, disregarding the feasibility of PDD and the noise pollution resulting from destructive operations. To address this concern, this paper introduces the integration of feasibility evaluation and noise considerations into the PDDLB problem for the first time. Subsequently, a mathematical model is established for the PDDLB problem, aiming to minimize disassembly costs, achieve smoothness balance, minimize the number of stations, and mitigate the adverse effects of noise. Then, an improved grey wolf optimization algorithm (IGWOA) considering feasibility evaluation and noise limitations is developed. It non-linearizes the convergence factor to enhance accuracy in the search for optimality, introduces a Lévy flight operation to further expand the search solution space, and incorporates an interference factor to prevent local optimality. In addition, the superiority of the proposed algorithm in solving different cases is verified by comparing five algorithms for the 25-task example and seven algorithms for the 52-task example in the latest literature. Finally, the proposed method is applied to a real engine case. The obtained results are compared with several classical Swarm Intelligence methods. The comparison results show that IGWOA has advantages due to other group intelligence methods in solving small, medium, and large-scale example. Moreover, the disassembly cost is comparatively low.