Early detection of faults in HVAC systems using an XGBoost model with a dynamic threshold

Abstract Growing demand for energy efficient buildings requires robust models to ensure efficient performance over the evolving life cycle of the building. Energy management systems can prevent energy wastage in buildings without sacrificing occupant’s comfort. However, their full capabilities have not been completely realized, partly due to their inability to quickly detect faults in HVAC systems. An accurate model and an appropriate threshold are the key factors in fault detection. The traditional method of setting a fixed threshold often leads to missed opportunities to detect faults, delayed detection of faults or false alarms. To improve the effectiveness of fault detection algorithms, we have first developed a data-driven model using extreme gradient boosting (XGBoost). We have then applied the proposed dynamic threshold method to determine occurrences of faults in real time. This method adjusts the threshold value dynamically according to the real-time moving average and moving standard deviation of the predictions. The results demonstrate the usefulness of our proposed method to detect faults early in the course. An average increase of 8.82% and 117.65%, in the F1 score, is achieved with the proposed method in comparison to the traditional fixed threshold method and an existing dynamic residual method.

[1]  James E. Braun,et al.  Development of Fault Models for Hybrid Fault Detection and Diagnostics Algorithm , 2015 .

[2]  David A. Cieslak,et al.  Hellinger distance decision trees are robust and skew-insensitive , 2011, Data Mining and Knowledge Discovery.

[3]  Michael Wetter,et al.  Robust on-line fault detection diagnosis for HVAC components based on nonlinear state estimation techniques , 2014 .

[4]  Tianqi Chen,et al.  Higgs Boson Discovery with Boosted Trees , 2014, HEPML@NIPS.

[5]  T. Agami Reddy,et al.  Automated fault detection and diagnosis for hvac&r systems: Functional description and lessons learnt , 2008 .

[6]  Sylvain Robert,et al.  State of the art in building modelling and energy performances prediction: A review , 2013 .

[7]  John E. Seem,et al.  Using intelligent data analysis to detect abnormal energy consumption in buildings , 2007 .

[8]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[9]  Michael Wetter,et al.  A framework for simulation-based real-time whole building performance assessment , 2012 .

[10]  Woohyun Kim,et al.  A review of fault detection and diagnostics methods for building systems , 2018 .

[11]  Trevor Hastie,et al.  An Introduction to Statistical Learning , 2013, Springer Texts in Statistics.

[12]  Joaquín Navarro-Esbrí,et al.  A vapour compression chiller fault detection technique based on adaptative algorithms. Application to on-line refrigerant leakage detection , 2006 .

[13]  Shengwei Wang,et al.  Sensor-fault detection, diagnosis and estimation for centrifugal chiller systems using principal-component analysis method , 2005 .

[14]  José Manuel Benítez,et al.  On the use of cross-validation for time series predictor evaluation , 2012, Inf. Sci..

[15]  Stephen R. Marsland,et al.  Machine Learning - An Algorithmic Perspective , 2009, Chapman and Hall / CRC machine learning and pattern recognition series.

[16]  Alessandro Beghi,et al.  Data-driven Fault Detection and Diagnosis for HVAC water chillers , 2016 .

[17]  Francisco Martínez-Álvarez,et al.  A Survey on Data Mining Techniques Applied to Electricity-Related Time Series Forecasting , 2015 .

[18]  Joseph Robertson,et al.  Hybrid Model-Based and Data-Driven Fault Detection and Diagnostics for Commercial Buildings: Preprint , 2016 .

[19]  Frédéric Magoulès,et al.  Development of an RDP neural network for building energy consumption fault detection and diagnosis , 2013 .

[20]  Alois Knoll,et al.  Gradient boosting machines, a tutorial , 2013, Front. Neurorobot..

[21]  Hazem Elzarka,et al.  Advanced machine learning techniques for building performance simulation: a comparative analysis , 2018, Journal of Building Performance Simulation.

[22]  Jian-Qiao Sun,et al.  Cross-level fault detection and diagnosis of building HVAC systems , 2011 .

[23]  Xiufeng Pang,et al.  MODELING AND SIMULATION OF HVAC FAULTS IN ENERGYPLUS , 2011 .

[24]  Zeyu Wang,et al.  A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models , 2017 .

[25]  Frédéric Magoulès,et al.  Feature Selection for Predicting Building Energy Consumption Based on Statistical Learning Method , 2012 .