Reinforcement Learning Based Gasoline Blending Optimization: Achieving More Efficient Nonlinear Online Blending of Fuels

TL;DR

This paper presents a deep reinforcement learning approach for gasoline blending optimization that improves economic outcomes, robustness to property fluctuations, and adapts to system changes in real-time.

Contribution

It introduces a novel DRL-based online optimization method for nonlinear gasoline blending, incorporating a practical MDP model and environment simulator for real-world application.

Findings

Outperforms traditional methods in economic efficiency

Demonstrates robustness to property fluctuations and oil switching

Maintains performance through automatic adaptation to system drift

Abstract

The online optimization of gasoline blending benefits refinery economies. However, the nonlinear blending mechanism, the oil property fluctuations, and the blending model mismatch bring difficulties to the optimization. To solve the above issues, this paper proposes a novel online optimization method based on deep reinforcement learning algorithm (DRL). The Markov decision process (MDP) expression are given considering a practical gasoline blending system. Then, the environment simulator of gasoline blending process is established based on the MDP expression and the one-year measurement data of a real-world refinery. The soft actor-critic (SAC) DRL algorithm is applied to improve the DRL agent policy by using the data obtained from the interaction between DRL agent and environment simulator. Compared with a traditional method, the proposed method has better economic performance. Meanwhile, it is more robust under property fluctuations and component oil switching. Furthermore, the proposed method maintains performance by automatically adapting to system drift.