An online fault detection and diagnosis method of sensors in district heating substations based on long short-term memory network and adaptive threshold selection algorithm

Abstract

District heating system is an essential energy infrastructure. Due to the harsh working environment, sensors in district heating substations are prone to faults, which will mislead the control strategies of substations. We propose an online fault detection and diagnosis (FDD) method for sensors in substations. The proposed method establishes a Sequence-to-Sequence Prediction Model based on Long Short-Term Memory network with Spatial-Temporal Attention (abbreviated as STALSTM-seq2seq model) for each target sensor. The model can learn normal and evolving data patterns from historical time series of sensors and predict current sensor observation. Then, an adaptive threshold selection algorithm is used to autonomously determine current anomaly threshold based on the prediction error vector of the model. If the prediction error exceeds the anomaly threshold, the sensor malfunctions. Otherwise, the sensor operates normally. Through a comprehensive case study, we demonstrate that the adaptive threshold selection algorithm can fully utilize the forecasting ability of the STALSTM-seq2seq model, and thereby ensure the accuracy of sensor FDD. Overall, the online sensor FDD method achieves an average F1 score of 0.8473. The research shows that the proposed method provides an effective and robust solution to timely and accurately identify sensor faults for district heating substations.