Energy Efficiency Optimization Method for Discrete Manufacturing Systems Based on Fusion Case Reasoning and Hybrid Group Intelligence

The energy consumption of the discrete manufacturing system is directly related to the operating state of the equipment. The energy consumption change is different in the three different operating states of the equipment. In the dynamic scheduling process of discrete machining task, the processing order of work pieces and the processes' choice of equipment depend on the scheduling strategy, which results in the dynamic uncertainty of equipment operation status and energy consumption. To address this problem, we propose an energy optimization method combined with case-based reasoning and hybrid group intelligence to solve the optimal scheduling scheme for the devices. We propose this method based on the energy consumption models of three different operating state and aims to minimize the energy consumption of the whole process of task processing. In the framework of particle swarm optimization algorithm, the method is combined with cross and mutation operator in the genetic algorithm. We introduce a case-based reasoning method into the supplementary individual generation process after population screening to improve the convergence ability and real-time operation of the algorithm. Finally, the simulation results are compared and analyzed to verify the effectiveness of the method.