Machine Learning Based Suggestions of Separation Units for Process Synthesis in Process Simulation

Abstract

As part of Industry 4.0, workflows in the process industry are becoming increasingly digitalized. In this context, artificial intelligence (AI) methods are also finding their way into the process development. In this communication, machine learning (ML) algorithms are used to suggest suitable separation units based on simulated process streams. Simulations that have been performed earlier are used as training data and the information is learned by machine learning models implemented in Python. The trained models show good, reliable results and are connected to a process simulator using a .NET framework. For further optimization, a concept for the implementation of user feedback will be assigned. The results will provide the fundamental basis for future AI‐based recommendation systems.

Towards a Systematic Data Harmonization to Enable AI Application in the Process Industry

“…In basic engineering, process data from simulation results can be used to predict suitable separation units for separating the simulated process streams with the help of ML algorithms. First research results show that this is possible for binary as well as multi‐substance systems and can provide the basis for future automated process development 6.…”

AI in Process Industries – Current Status and Future Prospects

“…Thus, the ML model serves as a basis for computer-supported process development [22]. Besides the specific application of AI to engineering data, the focus was also on using harmonized data as a basis to ensure the reusability of the models and to address a broad range of users from different fields [23,44,49]. Standardized P&IDs in DEXPI format are used as the data basis, which are available as graph-structured data.…”

Digitale Zwillinge in der Bioprozesstechnik – Chancen und Möglichkeiten

“…Diese Prozesse ko ¨nnen anschließend in die reale Welt u ¨bertragen werden. [23,54] Um die Bioprozessentwicklung zu strukturieren, sollten wie in der Verfahrenstechnik und im Anlagenbau Prozessmodule identifiziert werden [62][63][64]. So ist eine typische Reduzierung der Prozesskette eines biotechnologischen Kultivierungsprozesses, wie er auch in der Industrie angewendet werden kann, in Abb.…”