An adaptive genetic algorithm based on Q-learning for energy-efficient e-waste disassembly line balancing and rebalancing considering task failures

Abstract

The efficient disassembly and recycling of e-waste not only provides economic benefits but also contributes to reducing energy consumption. However, the disassembly process is often influenced by uncertainties, such as damage or deformation of components, which may result in potential task failures. These failures can disrupt the balance of the disassembly line, affecting the efficiency of subsequent tasks. Therefore, it is crucial to develop a decision-making model and optimization method to address disassembly failures. This study presents a predictive disassembly line balancing model with objectives focused on the number of workstations, the smoothness index, and energy consumption. The optimization objective of adjusting the disassembly sequence is introduced, and a rebalancing model is developed to reallocate the remaining tasks in response to various failures. The sequence combination that minimizes comprehensive energy consumption is selected as the optimal disassembly strategy. Considering the complexity and dynamic disturbance of the problem, an adaptive multi-objective genetic algorithm based on Q-learning is proposed. To improve the quality of the disassembly solutions, six evolutionary actions and four population performance states are designed. During the algorithm’s iteration, the search strategy is dynamically adjusted through Q-learning. The effectiveness of the proposed algorithm is verified by solving several classic disassembly cases and comparing the results with those from six advanced algorithms. Finally, in an actual refrigerator disassembly case, 11 disassembly schemes are generated, accounting for task failures. The results indicate that, compared to traditional disassembly methods, the rebalancing approach not only optimizes the station loads but also increases revenue by 11.98 %, demonstrating the effectiveness of the proposed model and method in handling task failures on disassembly lines.