A Real-time Prediction System for Molecular-level Information of Heavy Oil Based on Machine Learning

Acquiring accurate molecular-level information about petroleum is crucial for refining and chemical enterprises to implement the“selection of the optimal processing route”strategy.With the development of data prediction systems represented by machine learning,it has become possible for real-time prediction systems of petroleum fraction molecular information to replace analyses such as gas chromatography and mass spectrometry.However,the biggest difficulty lies in acquiring the data required for training the neural network.To address these issues,this work proposes an innovative method that utilizes the Aspen HYSYS and full two-dimensional gas chromatography-time-of-flight mass spectrometry to establish a comprehensive training database.Subsequently,a deep neural network prediction model is developed for heavy distillate oil to predict its composition in terms of molecular structure.After training,the model accurately predicts the molecular composition of catalytically cracked raw oil in a refinery.The validation and test sets exhibit R2 values of 0.99769 and 0.99807,respectively,and the average relative error of molecular composition prediction for raw materials of the catalytic cracking unit is less than 7%.Finally,the SHAP(SHapley Additive ExPlanation)interpretation method is used to disclose the relationship among different variables by performing global and local weight comparisons and correlation analyses.

Exergy analysis of multi-stage crude distillation units

This paper aims effect on crude distillation to investigate the multi-stage units （CDUs） in thermody- namics. In this regard, we proposed three-, four-, five-, and six-stage CDU processes with all variables constrained to be almost the same except for the number of stages. We also analyzed the energy and exergy to assess the energy consumed by each process. Because additional distillation units would share the processing load and thus prevent products with low boiling points from overheating, the heat demand of the CDUs decreases with increasing stages and thus reduces the heat supply. Exergy loss is considered as a key parameter to assess these processes. When the exergy losses in heat exchangers are disregarded, the three- and four-stage CDUs have lower exergy losses than the five- and six-stage CDUs. When the overall exergy losses are considered, the optimum number of stages of CDUs depends on the exergy efficiency of heat integration.