Evolutionary Optimisation for Robotic Disassembly Sequence Planning and Line Balancing

The performance of an evolutionary algorithm in solving disassembly sequence planning or disassembly line balancing greatly depends on six parts: the evolutionary operator; encoding scheme; solution selection and update strategy; population initialisation; solution maintenance; and terminal condition. This chapter introduces classical single-objective evolutionary algorithms (SOEAs) with typical evolutionary operators, and multi-objective evolutionary algorithms (MOEAs) with typical solution selection and update strategies. The chapter also elaborates on common encoding schemes. Typical settings on algorithm initialisation, solution maintenance and terminal conditions are introduced to help engineers to design efficient evolutionary algorithms for robotic disassembly optimisation problems.