Self-evolution of a flexible job shop in the knowledgeable manufacturing environment

In this paper, we introduced a new concept `self-evolution´ to improve production performance of manufacturing systems through adjusting system paramerters. Taking a flexible job shop with dynamic jobs arrival as an example, the self-evolution problem is studied. The principle of self-evolution is applied to the flexible job shop. A mathematical model of the static decision problem at each decision moment is established according to the bi-level programming theory. A bi-level genetic algorithm (bi-level GA) is proposed to solve the model. Simulation results demonstrate the effectiveness and feasiblity of the model and algorithm. Through a comparative research, self-evolution operations can improve the performance of the system.