Unsupervised Learning of Energy States in Automated Storage Systems with Self-Organizing Maps

Energy efficiency in industrial environments is subject to regulatory and economic constraints. Automated intralogistics systems, such as High Rack Storage Systems (HRSS), exhibit complex and dynamic energy patterns. This paper proposes an unsupervised learning approach that uses Self-Organizing Maps (SOMs) to characterize operational energy states from HRSS measurements (power, voltage, and position). After preprocessing, we train an SOM and apply Watershed segmentation to obtain a topological map of states, and we analyze state transitions with a Markov model to study persistence and switching behavior. The approach yields an interpretable taxonomy of energy use and highlights operating conditions associated with different efficiency levels, as well as central states that influence system behavior. While the study focuses on a single demonstrator, the results suggest that SOM can support explainable monitoring and analysis of industrial energy behavior and may help guide proactive energy-management decisions in Industry 4.0 settings.