Design and Application of Workshop Production Scheduling Strategy Based on Manufacturing Big Data

A multi-objective flexible workshop production scheduling optimization model is established for a series of workshop data in manufacturing enterprises, such as delivery time, processing time, and machine energy consumption, with the goal of minimizing total weighted lead and delay time, minimizing maximum completion time, and minimizing total machine energy consumption. On the basis of the NSGA-II algorithm, a combination of random generation and heuristic generation is used to initialize the population, while introducing dynamic crossover, mutation probability, and an improved elite retention strategy based on dynamic update crowding operator to optimize the NSGA-II algorithm, and solving the scheduling model to obtain the optimal set of scheduling solutions. Compared with the original NSGA-II algorithm, the improved NSGA-II (INSGA-II) algorithm improves population diversity, accelerates convergence speed, avoids falling into local optima, and can obtain better scheduling schemes. Finally, the feasibility and effectiveness of the INSGA-II algorithm were verified through simulation experiments.