Combining machine learning and process engineering physics towards enhanced accuracy and explainability of data-driven models. (12th July 2020)

• Record Type: Journal Article
• Authors: Bikmukhametov, Timur; Jäschke, Johannes
• Is Part Of: Computers & chemical engineering. Volume 138(2020)
• Publication Date: 2020-07-12
• Subjects: Machine learning -- Explainable machine learning -- Hybrid modeling -- First principles modeling -- Process engineering -- Virtual flow metering; Chemical engineering -- Data processing -- Periodicals; 660.0285
• DOI: 10.1016/j.compchemeng.2020.106834
• Languages: English
• ISSNs: 0098-1354

Abstract

Highlights: Physics and machine learning combined create accurate modeling solutions. Physics implementation into machine learning algorithms makes them more transparent. Physics-aware machine learning reveals complex patter behavior of process systems. Linear meta-models enable accurate and transparent combinations of physics and data. Abstract: Machine learning models are often considered as black-box solutions which is one of the main reasons why they are still not widely used in operation of process engineering systems. One approach to overcome this problem is to combine machine learning with first principles models of a process engineering system. In this work, we investigate different methods of combining machine learning with first principles and test them on a case study of multiphase flowrate estimation in a petroleum production system. However, the methods can be applied to any process engineering system. The results show that by adding physics-based models to machine learning, it is possible not only to improve the performance of the purely black-box machine learning models, but also to make them more transparent and interpretable. We also propose a step-by-step procedure for selecting a method for combining physics and machine learning depending on the process engineering system conditions.