No abstract

Current methods of artificial intelligence may often proof ineffective in the process industry, usually because of insufficient data availability. In this contribution, we investigate how data standards can contribute to fulfill the data availability requirements of machine learning methods. We give an overview of AI use cases relevant in the process industry, name related requirements and discuss known standards in the context of implicit vs. explicit data. We conclude with a roadmap sketching how to bring the results of this contribution into practical application.

Flooding of separation columns is a severe limitation in the operation of distillation and liquid‐liquid extraction columns. To observe operation conditions, machine learning algorithms are implemented to recognize the flooding behavior of separation columns on laboratory scale. Besides this, the investigated columns already provided the modular automation interface Module Type Package (MTP), which is used for data access of necessary sensor data. Hence, artificial intelligence (AI) tools with deep learning offer high potential for the process industry and allow to capture operating states that are otherwise difficult to detect or model. However, the advanced methods are only hesitantly applied in practice due to complex combination of operational sensing, data analysis, and active control of the equipment. This article provides an overview on how AI‐based algorithms can be implemented in existing laboratory plants. Process sensor data as well as image data are used to model the flooding behavior of distillation and extraction columns for stable and robust operational conditions.

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.

No abstract

The increasing digitalization and standardization within the process industry lead to a high availability of digital, machine-readable processes and plant descriptions. In particular, the publication of the DEXPI standard provides a digital representation of plant topologies including a complete description of all specifications. In early planning phases, this can be used as the basis for an automated safety assessment since digital availability significantly simplifies accessibility for smart search algorithms. This paper presents the preHAZOP search algorithm, which was developed to analyze P&IDs in DEXPI format and to detect safety-critical deviations regarding their risk according to a classical HAZOP analysis. The preHAZOP is of particular interest in early process development stages and can be easily integrated into modern, digital engineering workflows.

Auf der ACHEMA 2022 wurden vielfa ¨ltige Lo ¨sungen zur Modularisierung in der Prozessindustrie vorgestellt. In diesem Nachbericht werden insbesondere neue Bereiche der Modularisierung vorgestellt sowie Ergebnisse von Expertenbefragungen hinsichtlich der aktuellen und zuku ¨nftigen Herausforderungen der modularen Produktion beleuchtet. Obwohl in den letzten Jahren umfassende Fortschritte erzielt worden sind, stehen viele Unternehmen vor großen Herausforderungen, die nur in enger Zusammenarbeit von Modul-und Komponentenlieferanten, Anlagenbetreibern und Systemintegratoren sowie Anbietern von Automatisierungslo ¨sungen gemeistert werden ko ¨nnen.

Machine Learning (ML) algorithms can be combined with the modular automation protocol (MTP) and recognize the flooding behavior of laboratory fluids separation columns. Hence, artificial intelligence (AI) tools with deep learning (DL) offer a high potential for the process industry and allow to capture operating states that are otherwise difficult to detect or model. However, the advanced methods are only hesitantly applied in practice. This article provides an overview on how artificial intelligence-based algorithms can be implemented in existing laboratory plants. Process sensor data as well as image data are used to model the flooding behavior of distillation and extraction columns and the system is adapted to the existing modular automation standard of the Module Type Package (MTP).