Artificial intelligence (AI) has received a lot of attention with many publications in recent years. Interestingly related projects in the industry are mostly still in their early stages. We are convinced that progress will only be possible if the entire machine learning (ML) life cycle is considered. Our study focuses on the practical challenges, uses a recent study as foundation and adopts the life-cycle description, highlights the life-cycle practices in other domains and formulates research directions that can help to improve the utilization of AI and machine learning in the process industry.

No abstract

No abstract

No abstract

Identification of quality issues in batch production is relevant for stable and successful production. The identification of systematic quality issues and the identification of root causes is complex and challenging. Powerful multivariate statistical methods exist to perform batch analysis, yet their application is difficult due to data diversity and complexity in model training. Here, insights from data analysis projects on four batch plants are presented and real world challenges are reviewed. This leads to a semi-automatic process for more efficient batch analysis overcoming the mentioned tedious tasks.