Automated Clustering and the Path Toward Visual Analytics for Enhanced Process Optimization in the Pulp and Paper Industry

Abstract With higher energy prices as well as the desired shift toward sustainability, improving the efficiency of their operation is becoming a major challenge of the pulp and paper industry. To achieve this, producers are prioritizing energy savings, optimized machine washing cycles as well as timely fault detection across their plants. Compressors are one of the key parts of paper production lines. This paper therefore presents an approach to address the aforementioned goals, focusing on compressors and their interaction with other critical components in the plant. To accommodate industry requirements for confidentiality, we explore methods that rely on minimal system knowledge, allowing clients to protect proprietary information. This study explores three approaches to re-adapt human-labeled machine operations and implement automatic labeling using clustering techniques. All methods, including an auto-encoder, achieved strong performance with F1 scores above 0.92 and an adjusted rand index (ARI) score above 0.94. The auto-encoder compressed data by a factor of eight, retaining accuracy while enabling robust clustering and capturing nonlinear relationships. The results shown by the tests indicate that it is possible to integrate automated analysis with visual analytics, laying the foundation for future advancements in interactive data exploration and in some circumstances safe automated labeling. This integration aims to enhance anomaly detection, predictive maintenance, and process optimization in industrial systems.