Disassembly line balancing with hazardous task failures - Model based solution approaches

In this study, we consider a disassembly line balancing problem that involves a fixed number of workstations and the possibility of failures in hazardous tasks. We assume that each hazardous task may fail with a pre-specified probability and once it fails, the disassembly line stops, and all tasks assigned to subsequent workstations are interrupted. Our problem is to select the set of tasks for processing and assign them to the workstations to maximize the total expected net revenue. We develop a heuristic procedure that uses the linear programming relaxation of the recently reported stochastic mixed-integer program in the literature. To assess the performance of the heuristic procedure, we use two upper bounds that use some properties of the optimal solutions as valid cuts. Our extensive experiments have shown the excellent performance of our heuristic algorithm and upper bounds.