1results about How to "Improve exploration effect" patented technology

The application provides a distributed blocking flow shop scheduling optimizer driven by a learning mechanism, and proposes a distributed estimation algorithm applying reverse learning and differential evolution to optimize energy-saving distributed blocking flow shop scheduling. The application fully considers the energy consumption in actual production, and designs an initialization method considering total delay time and total energy consumption; in order to improve the quality of the population, a multi-population collaborative operation guided by reinforcement learning and reverse learning is designed, information interaction is realized through the multi-population collaborative mode, and the search speed is accelerated. Based on the specific characteristics of different populations, adjustable parameter variables meeting the exploration and development capacity are designed. In order to optimize the distributed blocking flow shop scheduling problem with the objective function of reducing total delay time and total energy consumption, acceleration and deceleration operations on different paths are proposed. Through comparison on the 2017 test set and examples composed of different numbers of machines, workpieces and machine arrays, the overall performance of the optimizer is better than that of other optimizers.