In collaboration with an industrial partner, Alfa Laval AB, this thesis discusses a novel approach for identifying operational modes, specifically a cleaning mode, in separator machines without the benefit of labelled data and with very limited operating knowledge. Understanding the operational modes is crucial for comprehending the machine’s behaviour and ensuring its optimal performance.

Alfa Laval AB relies on a threshold-based fault detection system. The cleaning mode triggers vibrations that confuse the machine’s fault detection system, resulting in false alarms. The primary challenge revolves around the limited understanding of this infrequent cleaning mode, occurring periodically for 1-2 hours at intermittent intervals. To tackle this, we approach the problem as a data mining task. Matrix Profile (MP), a powerful tool in time series data analysis excels at identifying motifs and discords but struggles to distinguish between frequent and non-frequent motifs.

To address the drawback, we introduced an innovative approach capable of detecting frequent motifs and non-frequent motifs from the matrix profile output. The fundamental concept involves extracting the top-K motif matches using the Matrix Profile (MP) and systematically monitoring the evolution of structural similarity through pairwise similarity matrix calculation, progressing from pairs of two motifs to a group of K motifs.

This approach helps us to identify infrequent motifs that contain the most similar patterns which will be a good fit to address our challenge of identifying the cleaning mode.