Fault Detection in Solar Thermal Systems using Probabilistic Reconstructions

As heating is the largest factor of Greenhouse gases in the household sector, it shouldbe the focus of our decarbonisation efforts. Solar Thermal Systems (STS), which provideheat based on solar energy, are a promising technology in this regard. However, STSare prone to faults due to improper installation, maintenance, or operation, often leadingto a substantial reduction in efficiency, damage to the system, or even an increase inenergy cost. As individual monitoring is economically prohibitive for small-scale systems,automated monitoring and fault detection should be used to address this issue.We propose a data-driven neural network approach for fault detection in small-scaleSTS, utilising probabilistic reconstructions from a long short-term memory (LSTM) basedVariational Autoencoder (VAE). Key factors in our approach are generalising from faultlessdata to previously unseen systems and an anomaly score derived from an ensemble ofreconstructions. We apply this to an operational dataset provided by our industry partner,which includes systems with different types of faults.Our results show that our model can detect faults in STS with comparable performanceto the state-of-the-art expert-based system used by our industry partner. Furthermore, ourmodel can detect previously undetected faults, specifically those resulting from unexpectedbehaviour in the control software or behaviours that were entirely unexpected and notconsidered in the expert-based system. Thus, a combination of our model and the expert-based system covers a broader range of faults than either system and is proposed forfurther use in the industry partner’s application. Additionally, other providers without afunctioning expert-based system could build upon our work to get a minimal viable productfor fault detection in STS, purely based on data from existing systems and without theneed to install additional sensors or domain-specific knowledge.