Applying Predictive Machine Learning Algorithms to Petroleum Refining Processes as Part of Intelligent Automation

Intelligent automation is a term that can be applied to the more complex field of workflow automation, consisting of robotic workplace automation, robotic process automation, machine learning, and artificial intelligence. Depending on the type of business, companies often use one or more types of automation to improve efficiency or effectiveness. As you move from process-driven automation to more flexible data-driven automation, additional costs arise in the form of training datasets, technical development, infrastructure, and expertise. But the potential benefits in terms of new ideas and financial development can increase significantly. The development of mechanized oil production in recent years has been accompanied by significant achievements in the field of digitalization. Machine learning, as an important element of digitalization, can successfully solve many production problems. The paper describes the application of some machine learning algorithms for solving the problem of classifying and predicting failures of hydrocracking process equipment that occur during oil refining and diesel fuel production. The application of random forest, principal component analysis and hyperparameter tuning methods is considered. The effectiveness of their application is compared.