Interpretability of Causal Discovery in Tracking Deterioration in a Highly Dynamic Process

• Published in: Sensors (Basel, Switzerland) Vol. 24; no. 12; p. 3728
• Main Authors: Choudhary, Asha, Vuković, Matej, Mutlu, Belgin, Haslgrübler, Michael, Kern, Roman
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 08.06.2024; MDPI
• Subjects: Algorithms; causal discovery; causal interpretability; degradation monitoring; Graphs; health monitoring; interpretability; jaccard distance; Methods; Product quality; Subject specialists; Time series; interpretability; jaccard distance; causal discovery; health monitoring; causal interpretability; degradation monitoring

In a dynamic production processes, mechanical degradation poses a significant challenge, impacting product quality and process efficiency. This paper explores a novel approach for monitoring degradation in the context of viscose fiber production, a highly dynamic manufacturing process. Using causal...