A Data-Driven Robust Scheduling Method Integrating Particle Swarm Optimization Algorithm with Kernel-Based Estimation

The assembly job shop scheduling problem (AJSSP) widely exists in the production process of many complex products. Robust methods aim to optimize given criteria for improving robustness schedule by organizing processes under uncertainty. In this work, uncertainty setup time and processing is considered, a framework robust AJSSP using data-driven methodologies proposed. consists obtaining distribution information uncertain parameters based on historical data particle swarm optimization (PSO) algorithm schedule. Firstly, kernel density estimation method used estimate probability function parameters. To control schedule, concept confidence level introduced when determining range Secondly, an interval constructed theory customized discrete PSO are with constraints. Several computational experiments illustrate proposed method, these were proven effective performance