Multi-mechanism-based modified bi-objective Harris Hawks optimization for sustainable robotic disassembly line balancing problems

Abstract

Due to the increasingly severe resource scarcity and environmental pollution, appropriate recovery of end-of-life (EOL) products has gained significant importance in recent years. The disassembly lines are one of the vital steps during the entire recovery process. However, considering the disadvantages of manual disassembly lines such as high labor cost, low efficiency, and harm to workers’ health, the transition to robotic disassembly lines is underway. Therefore, in this paper, a sustainable robotic disassembly line balancing problem (RDLBP) is proposed to improve the disassembly efficiency (cycle time) and environmental friendliness (total energy consumption) simultaneously. To narrow the gap between theory and practice, uncertain processing time, sequence-based tool changeover, and robots with different efficiencies and energy consumption rates are considered, which requires adding the steps of resequencing the tasks and allocating the most suitable robots within each workstation on the basis of assigning the tasks to workstations as evenly as possible. To solve this problem, the epsilon constraint algorithm is used to obtain the exact solutions for small scale cases and verify the validity of the proposed model. Simultaneously, due to the NP-hard nature, a modified bi-objective Harris Hawks optimization (MBOHHO) algorithm is developed to solve the line balancing problem for the first time, which combines opposition-based learning, differential evolution, and Gaussian mutation mechanisms, and modifies the renewal strategy of two vital parameters based on bioenergy consumption pattern, contributing to improve the diversity and help jump out of local optimum. Finally, computational experiments are performed to evaluate the performance of the MBOHHO algorithm by comparing it with four other outstanding optimization algorithms, and the results reveal its effectiveness and superiority in various metrics.