Influence of Class Imbalance on the Quality of Hydrocracking Unit Failure Prediction Models
Abstract
The paper is devoted to the study of the influence of class imbalance on the quality of hydrocracking unit failure prediction models. The use of machine learning methods finds an increasing response in various industries due to the increase in computing power and the reduction in the cost of creating advanced process control systems. The oil and gas industry are highly profitable and large in terms of its industrial capacity; thousands of pieces of technical equipment within one enterprise are involved in the production of petroleum products and their processing. Therefore, improving the operational reliability of oil refining process equipment is an urgent scientific task. In this paper, we consider a method for modeling a hydrocracking unit for the production of diesel fuels and creating models for predicting plant equipment failures. Particular attention is paid to the influence of class imbalance in data when solving the classification problem. The built-in weighting methods for classes of machine learning models are compared, as well as upsampling and downsampling methods.
Copyright information
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
About this article
Publication Date
27 February 2023
Article Doi
eBook ISBN
978-1-80296-960-3
Publisher
European Publisher
Volume
1
Print ISBN (optional)
-
Edition Number
1st Edition
Pages
1-403
Subjects
Hybrid methods, modeling and optimization, complex systems, mathematical models, data mining, computational intelligence
Cite this article as:
Nekrasov, I., Bukhtoyarov, V., & Eremeeva, S. (2023). Influence of Class Imbalance on the Quality of Hydrocracking Unit Failure Prediction Models. In P. Stanimorovic, A. A. Stupina, E. Semenkin, & I. V. Kovalev (Eds.), Hybrid Methods of Modeling and Optimization in Complex Systems, vol 1. European Proceedings of Computers and Technology (pp. 178-185). European Publisher. https://doi.org/10.15405/epct.23021.22