Knowledge-assisted hybrid optimization strategy of large-scale crude oil scheduling integrated production planning

As modern refinery crude oil scheduling scales up, traditional manual operations and independent optimization methods struggle with complexity and dynamics. This study proposes an empirically assisted integrated planning and scheduling optimization model.The integrated model is solved using a hybrid optimization algorithm combining mathematical programming and particle swarm optimization (MP/PSO). Long-term planning aims to minimize operational and transportation costs while maximizing refinery profits; short-term scheduling, based on initial long-term plans, aims to minimize unit switchovers. In the short-term scheduling phase, heuristic rules based on empirical operational knowledge generate a high-performing initial population to accelerate convergence. This strategy is crucial for enhancing refinery emergency response capabilities, ensuring stable operations, and improving economic benefits. Experimental results show that within a reasonable time frame, MP/PSO performs better than PSO and manual scheduling in large-scale crude oil scheduling scenarios.