Work

Is it returning too hot? Time series segmentation and feature clustering of end-user substation faults in district heating systems

Year: 2024

Type: article

Abstract: This study explores the challenges and advancements in collecting ground-truth data to enhance fault diagnosis models for district heating systems. Initiated by the need to address limitations in previous data collections, this research leverages an enriched dataset from Aalborg utility to identify faults in household substations. Despite some inaccurate fault categorizations, obscured fault patterns, and truncated measurements, the analysis of 50 detailed cases out of 127 fault reports reveals that while return temperature reliably indicates faults, energy usage patterns do not. Employing self-organizing maps combined with k-means clustering, the research categorizes fault symptoms and patterns, demonstrating the utility of high-dimensional data clustering in fault diagnosis. Additionally, an algorithm using time series decomposition is suggested to autonomously identify both extreme and subtle anomalies, enhancing fault detection capabilities. The paper concludes that these methodologies significantly augment the precision and dependability of fault diagnostics in heating systems, paving the way for more efficient operational management.

Source: Applied Energy

DOI: 10.1016/j.apenergy.2024.125122