Knowledge-Assisted Dual-Stage Evolutionary Optimization of Large-Scale Crude Oil Scheduling

TL;DR

This work tackles the difficulty of short-term, large-scale crude oil scheduling (LSCOSPs) in marine-access refineries, where thousands of binary variables and nonlinear constraints hinder conventional MINLP methods. It introduces DSEA/HR, a knowledge-assisted dual-stage evolutionary framework that combines a global search via competitive swarm optimization (CSO) with a local refinement stage using CoDE, guided by two heuristic rules derived from crude blending knowledge. The key contributions are (i) problem-specific heuristic rules for population initialization, (ii) a repair-based local refinement to fix infeasibility in the continuous space, and (iii) extensive experiments showing DSEA/HR outperforms state-of-the-art MINLP solvers and metaheuristics on real-world LSCOSP cases while maintaining reasonable computation times. The approach demonstrates significant practical impact by providing a scalable, effective tool for refinery scheduling that aligns with operational realities and can adapt to large, complex instances. Future work suggests automatic extraction of problem knowledge and strategies to improve solution feasibility rates across more challenging scenarios.

Abstract

With the scaling up of crude oil scheduling in modern refineries, large-scale crude oil scheduling problems (LSCOSPs) emerge with thousands of binary variables and non-linear constraints, which are challenging to be optimized by traditional optimization methods. To solve LSCOSPs, we take the practical crude oil scheduling from a marine-access refinery as an example and start with modeling LSCOSPs from crude unloading, transportation, crude distillation unit processing, and inventory management of intermediate products. On the basis of the proposed model, a dual-stage evolutionary algorithm driven by heuristic rules (denoted by DSEA/HR) is developed, where the dual-stage search mechanism consists of global search and local refinement. In the global search stage, we devise several heuristic rules based on the empirical operating knowledge to generate a well-performing initial population and accelerate convergence in the mixed variables space. In the local refinement stage, a repair strategy is proposed to move the infeasible solutions towards feasible regions by further optimizing the local continuous variables. During the whole evolutionary process, the proposed dual-stage framework plays a crucial role in balancing exploration and exploitation. Experimental results have shown that DSEA/HR outperforms the state-of-the-art and widely-used mathematical programming methods and metaheuristic algorithms on LSCOSP instances within a reasonable time.

Figures (8)

• Figure 1: Crude oil scheduling structure of marine-access refineries.
• Figure 2: An illustration of an feasible schedule. (a) Gantt chart of a feasible solution. (b) Flow rate and sulfur content of feed to the CDU. (c) Outputs of two types of residue in the CDU.
• Figure 3: Representation of encoding for each period.
• Figure 4: The flowchart of DSEA/HR for solving LSCOSPs.
• Figure 5: Box plots for the objective values by DSEA/HR, DSEA/HR-V1, and DSEA/HR-V2 in Cases 1-3. (a) Case 1. (b) Case 2. (c) Case 3.

Theorems & Definitions (1)

• Remark 1