Fault detection for non-condensing boilers using simulated building automation system sensor data. (October 2020)

• Record Type: Journal Article
• Authors: Shohet, Rony; Kandil, Mohamed S.; Wang, Yidan; McArthur, J.J.
• Is Part Of: Advanced engineering informatics. Volume 46(2020)
• Publication Date: 2020-10
• Subjects: Fault detection -- Machine learning -- Boiler emulator; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2020.101176
• Languages: English
• ISSNs: 1474-0346

Abstract

Highlights: The development of a non-condensing boiler emulator is presented. Both normal and faulty operation (3 fault types) are simulated for 14 boilers. Datasets were used to train fault detection and diagnosis algorithms and test accuracy. SVM was the most effective machine learning algorithm (>90% accuracy) FDD models exhibit poor ability to generalize across boiler sizes and manufacturers. Abstract: Building performance has been shown to degrade significantly after commissioning, resulting in increased energy consumption and associated greenhouse gas emissions. Fault Detection and Diagnosis (FDD) protocols using existing sensor networks and IoT devices have the potential to minimize this waste by continually identifying system degradation and re-tuning control strategies to adapt to real building performance. Due to its significant contribution to greenhouse gas emissions, the performance of gas boiler systems for building heating is critical. A review of boiler performance studies has been used to develop a set of common faults and degraded performance conditions, which have been integrated into a MATLAB/Simscape emulator. This resulted in a labeled dataset with approximately 10, 000 simulations of steady-state performance for each of 14 non-condensing boilers. The collected data is used for training and testing fault classification using K-nearest neighbour, Decision tree, Random Forest, and Support Vector Machines. The results show that the Decision Tree, Random Forest, and Support Vector Machines method provide high prediction accuracy, consistently exceeding 95%, and generalization across multiple boilers is not possible due to low classification accuracy.