Base Oil Process Modelling Using Machine Learning

Abstract

The quality of feedstock used in base oil processing depends on the source of the crude oil. Moreover, the refinery is fed with various blends of crude oil to meet the demand of the refining products. These circumstances have caused changes of quality of the feedstock for the base oil production. Often the feedstock properties deviate from the original properties measured during the process design phase. To recalculate and remodel using first principal approaches requires significant costs due to the detailed material characterizations and several pilot-plant runs requirements. To perform all material characterization and pilot plant runs every time the refinery receives a different blend of crude oil will simply multiply the costs. Due to economic reasons, only selected lab characterizations are performed, and the base oil processing plant is operated reactively based on the feedback of the lab analysis of the base oil product. However, this reactive method leads to loss in production for several hours because of the residence time as well as time required to perform the lab analysis. Hence in this paper, an alternative method is studied to minimize the production loss by reacting proactively utilizing machine learning algorithms. Support Vector Regression (SVR), Decision Tree Regression (DTR), Random Forest Regression (RFR) and Extreme Gradient Boosting (XGBoost) models are developed and studied using historical data of the plant to predict the base oil product kinematic viscosity and viscosity index based on the feedstock qualities and the process operating conditions. The XGBoost model shows the most optimal and consistent performance during validation and a 6.5 months plant testing period. Subsequent deployment at our plant facility and product recovery analysis have shown that the prediction model has facilitated in reducing the production recovery period during product transition by 40%.

Machine Learning-Based Modeling and Optimization Analysis for an Integrated Industrial Base Oil Production Complex

“…The hyperparameters (i.e., number of estimator, maximum depth, learning rate, and regularization lambda) are tuned using grid search cross validation by scikit-learn Tables – record the set of hyperparameters evaluated and the corresponding cross-validation scores for each of the model types, respectively . The rank for each hyperparameter tuning is sorted in descending order based on their mean test score (coefficient of determination, R 2 ) values.…”

“…22 Tables 1−8 record the set of hyperparameters evaluated and the corresponding cross-validation scores for each of the model types, respectively. 26 The rank for each hyperparameter tuning is sorted in descending order based on their mean test score (coefficient of determination, R 2 ) values.…”

Investigative Analysis of Automatic Mode Detection for a Lubricant Base Oil Production Plant Using PCA and Machine-Learning Models

“…Finally, the product is distilled under vacuum conditions to remove the lighter materials. Figure 1 shows a simplified flow diagram of the industrial base oil processing plant taken from ref ( 10 ).…”

“… Simplified process flow diagram of the base oil processing plant from ref ( 10 ). Copyright [2021] [M. A. M. Fadzil et al].…”

Oil and Gas Production Forecasting Using Decision Trees, Random Forst, and XGBoost

“…This article will review several recent studies that use ML in the Oil and Gas industry. [18] In this research, an alternative strategy is proposed for reducing Oil production losses by employing ML supervised regression models "XGBoost, RFR, DTR, and SVR", which are constructed and examined to make predictions regarding the plant's operating circumstances. The highest effectiveness and consistency throughout the validation process have been demonstrated by the XGBoost model.…”