A Knowledge-Assisted Variable Neighborhood Search for Two-Sided Assembly Line Balancing Considering Preventive Maintenance Scenarios

In a realistic two-sided assembly line, a preventive maintenance (PM) activity may cause a stoppage of the whole line and a waste of capacity in most stations. To promote production continuity, multiple interchangeable task assignment schemes are required, each targeting one of the regular and PM scenarios. Yet previous studies have not solved the resulting two-sided assembly line balancing problem considering PM scenarios (TALBP-PM), and the domain knowledge deserves extraction. Hence, a multiobjective mixed-integer linear programming model is formulated to minimize cycle times and total task adjustment simultaneously, and a knowledge-assisted variable neighborhood search (KVNS) is customized. Specifically, a decoding mechanism with idle time reduction is proposed to achieve schemes with the shortest cycle times. A rule-based initialization relying on the externalization of implicit relations among unique attributes is designed to derive a high-quality initial solution. Supported by the critical station and task knowledge, objective-oriented neighborhood structures are developed to generate neighbor solutions with increasingly better objectives. Besides, a restart operator adaptive to multidomain knowledge is refined to escape from local optima. Computational results show that the knowledge assistance is effective, and KVNS is superior to other state-of-the-art meta-heuristics in achieving well-converged and -distributed Pareto fronts of TALBP-PM.