Disassembly Sequence Planning (DSP) is a challenging NP-hard combinatorial optimization problem. As a new and promising population-based evolutional algorithm, the teaching-learning-based Optimization (TLBO) algorithm...
详细信息
Disassembly Sequence Planning (DSP) is a challenging NP-hard combinatorial optimization problem. As a new and promising population-based evolutional algorithm, the teaching-learning-based Optimization (TLBO) algorithm has been successfully applied to various research problems. However, TLBO is not capable or effective in DSP optimization problems with discrete solution spaces and complex disassembly precedence constraints. This paper presents a simplified teaching-learning-based Optimization (STLBO) algorithm for solving DSP problems effectively. The STLBO algorithm inherits the main idea of the teaching-leaming-based evolutionary mechanism from the TLBO algorithm, while the realization method for the evolutionary mechanism and the adaptation methods for the algorithm parameters are different. Three new operators are developed and incorporated in the STLBO algorithm to ensure its applicability to DSP problems with complex disassembly precedence constraints: i.e., a Feasible Solution Generator (FSG) used to generate a feasible disassembly sequence, a teaching Phase Operator (TPO) and a learning Phase Operator (LPO) used to learn and evolve the solutions towards better ones by applying the method of precedence preservation crossover operation. Numerical experiments with case studies on waste product disassembly planning have been carried out to demonstrate the effectiveness of the designed operators and the results exhibited that the developed algorithm performs better than other relevant algorithms under a set of public benchmarks. (C) 2014 Elsevier Ltd. All rights reserved.
暂无评论