A robust MILP and gene expression programming based on heuristic rules for mixed-model multi-manned assembly line balancing

Current dynamic markets require manufacturing industries to organize a robust plan to cope with uncertain demand planning. This work addresses the mixed-model multi-manned assembly line balancing under uncertain demand and aims to optimize the assembly line configuration by a robust mixed-integer linear programming (MILP) model and a robust solution generation mechanism embedded with dispatching rules. The proposed model relaxes the cycle time constraint and designs robust sequencing constraints and objective functions to ensure the line configuration can meet all the demand plans. Furthermore, two solution generation mechanisms, including a task-operator-sequence and an operator-task-sequence, are designed. To quickly find a suitable line configuration, a gene expression programming (GEP) approach with multi-attribute representation is proposed to obtain efficient dispatching rules which are ultimately embedded into the solution generation mechanisms. Experimental results show that solving the proposed MILP model mathematically is effective when tackling small and medium-scale instances. However, for large instances, the dispatching rules generated by the GEP have significant superiority over traditional heuristic rules and those rules mined by a genetic programming algorithm. (C) 2021 Published by Elsevier B.V.