Artificial Intelligence in Process Engineering

Abstract

In recent years, the field of Artificial Intelligence (AI) is experiencing a boom, caused by recent breakthroughs in computing power, AI techniques, and software architectures. Among the many fields being impacted by this paradigm shift, process engineering has experienced the benefits caused by AI. However, the published methods and applications in process engineering are diverse, and there is still much unexploited potential. Herein, the goal of providing a systematic overview of the current state of AI and its applications in process engineering is discussed. Current applications are described and classified according to a broader systematic. Current techniques, types of AI as well as pre‐ and postprocessing will be examined similarly and assigned to the previously discussed applications. Given the importance of mechanistic models in process engineering as opposed to the pure black box nature of most of AI, reverse engineering strategies as well as hybrid modeling will be highlighted. Furthermore, a holistic strategy will be formulated for the application of the current state of AI in process engineering.

Viscosity Model for Nanoparticulate Suspensions Based on Surface Interactions

“…For details on these so-called fuzzy genes, see Appendix A . A short presentation of this strategy was given in the review of Thon et al [ 30 ] and set in the context of other methods of artificial intelligence for model development.…”

“…In agreement with the dependency found in the numerical study [18], these effects were represented heuristically by regarding the shear rate based on a power law expression. Hence, the parameter B 2 was introduced as an exponent to Equation (30).…”

Industrial data science – a review of machine learning applications for chemical and process industries

“…39,40 Pragmatically, several models with their tuning parameters can be fitted (known as autoML). 41,42 What is still relevant is: what question to ask the data, how to avoid over-fitting, and the use of Explainable AI 43 (data-driven techniques to interpret what more complex ML models are able to capture, see Fig. 10 as an example).…”

Chemical engineering at crossroads

“…Thon et al [ 39 ] presented a comprehensive review of AI in process industry and provided a perspective that ‘AI will take an integral role in most—if not all—fields including process and chemical engineering'. Pan et al [ 40 ] advocated for integrating simulation, ML, and statistics in data‐centric engineering to create digital twins of chemical engineering systems.…”