A synchronous data-driven hybrid framework for optimizing hydrotreating units and hydrogen networks under uncertainty

Minimizing hydrogen consumption while maintaining the production quality in the refinery is increasingly important with more usage of heavy crude oil. However, the uncertainty of the impurity content in the input flow has led to the optimal solution losing efficacy. Therefore, a synchronous optimization framework for the hydrogen network and the production system is proposed. In this work, the relationship between the production state and the hydrogen demand is characterized by a hybrid model. Besides, a Wasserstein distributionally robust optimization module is inserted into the optimization of the hydrogen network, considering the uncertain condition of the impurity content in the input flow. The results show that the balance of hydrogen consumption and production quality could be improved. a lower hydrogen demand, reduced energy consumption, and higher product profit could be achieved with a stabler production state.