The importance of electronic product recycling has been well-recognized by the manufacturing community. Traditional linear disassembly lines face challenges, such as workspace limitation. Therefore, it is necessary to propose more efficient disassembly line layouts than traditional ones. Robotic technology is becoming more and more mature, and its application to disassembly lines is well recognized. This work proposes M2UDP and develops its mathematical model for the optimal solutions to the problem. In order to search for its optimal solutions, we leverage a multi-verse optimization algorithm with neural network techniques in encoding and decoding discrete disassembly sequences. Experimental results show that the newly proposed algorithm is superior to three popular algorithms in solving M2UDP. This paper provides decision-makers with more choices in disassembly line design and offers solutions for disassembly line balancing while minimizing the environmental impact of discarded or end-of-life products.

The development of technology accelerates the upgrade of products, which results in a significant number of obsolete products. This research aims to solve the multirobotic multiproduct U-shaped disassembly line balancing problem (M2UDP), in which different products are disassembled on a U-shaped model in a preset cycle time and assigned tasks to robots in each workstation reasonably. A linear mixed-integer model is established to maximize disassembly profit and minimize carbon emissions. An improved multiobjective multiverse optimizer (IMMO) that utilizes the sigmoid activation function in neural networks is proposed to find the optimal plan for the model. The improved algorithm is verified via a set of real-life instances and compared with three classical multiobjective optimization algorithms. The experimental results show that the proposed IMMO performs better than those peers in solving the M2UDP problems.