Fault Diagnosis of HVAC Air-Handling Systems Considering Fault Propagation Impacts Among Components

In a heating, ventilation, and air conditioning system, an air-handling system is a key module. Its components (e.g., air handling unit, air-mixing box, and fans), linked through airflows, condition air to a desired temperature and/or humidity based on comfort or controlled environment requirements. Identifying failure modes and estimating their severities allow maintenance crews to know which faults have occurred, how critical they are, and be guided in the repair process to improve the system availability. The problem of fault detection and diagnosis in air-handling systems is complex because of fault propagation across components, and high false alarm rates caused by uncertainties in system and measurement dynamics. In this paper, to capture fault propagation impacts in an efficient manner, dynamic hidden Markov models are developed to identify failure modes, since they contain state transition matrices depending on other components and do not generate joint states. To filter out false alarms, “coupled statistical process control” techniques are developed by using state transitions matrices representing coupling among components. Experimental results show that the method can effectively diagnose faults with high-diagnosis accuracy.

[1]  Masami Suzuki,et al.  Typical faults of air conditioning systems and fault detection by ARX model and extended Kalman filter , 1996 .

[2]  John E. Seem,et al.  Evaluation of an AHU Fault Detection Scheme Based on Finite State Machine Sequencing Control , 2007 .

[3]  Jonathan A. Wright,et al.  Demonstration of Fault Detection and Diagnosis Methods for Air-Handling Units , 2002 .

[4]  Zhenjun Ma,et al.  A decision tree based data-driven diagnostic strategy for air handling units , 2016 .

[5]  Kenneth A. Loparo,et al.  Tool wear condition monitoring in drilling operations using hidden Markov models (HMMs) , 2001 .

[6]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[7]  Krishna R. Pattipati,et al.  Coupled Factorial Hidden Markov Models (CFHMM) for Diagnosing Multiple and Coupled Faults , 2013, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[8]  Matthew J. Johnson.  Bayesian time series models and scalable inference , 2014 .

[9]  Srinivas Katipamula,et al.  Review Article: Methods for Fault Detection, Diagnostics, and Prognostics for Building Systems—A Review, Part I , 2005 .

[10]  Leslie K. Norford,et al.  Robust model-based fault diagnosis for air handling units , 2015 .

[11]  H. C. Peitsman,et al.  Application of black-box models to HVAC systems for fault detection , 1996 .

[12]  Steven T. Bushby,et al.  A rule-based fault detection method for air handling units , 2006 .

[13]  Bo Fan,et al.  Fault detection and diagnosis for buildings and HVAC systems using combined neural networks and subtractive clustering analysis , 2014 .

[14]  G. M. Kaler.  Expert system predicts service , 1988 .

[15]  Rick Diamond,et al.  Fault detection in HVAC systems using model-based feedforward control , 2001 .

[16]  Peter B. Luh,et al.  Building Energy Doctors: An SPC and Kalman Filter-Based Method for System-Level Fault Detection in HVAC Systems , 2014, IEEE Transactions on Automation Science and Engineering.

[17]  Tobias Rydén,et al.  EM versus Markov chain Monte Carlo for estimation of hidden Markov models: a computational perspective , 2008 .

[18]  Dan Wang,et al.  A Method for the Fault Prediction of Printing Press Based on Statistical Process Control of Registration Accuracy , 2013 .

[19]  Philip Haves,et al.  Condition monitoring in HVAC subsystems using first principles models , 1996 .

[20]  Andrea Bondavalli,et al.  Improving Robustness of Network Fault Diagnosis to Uncertainty in Observations , 2010, 2010 Ninth IEEE International Symposium on Network Computing and Applications.

[21]  Jin Wen,et al.  A model-based fault detection and diagnostic methodology based on PCA method and wavelet transform , 2014 .

[22]  S. Roberts,et al.  Learning interaction dynamics with coupled hidden Markov models , 2000 .

[23]  G. E. Kelly,et al.  Fault diagnosis of an air-handling unit using artificial neural networks , 1996 .

[24]  Krishnan Gowri,et al.  Automated Fault Detection and Diagnostics for Outdoor-Air Ventilation Systems and Economizers: Methodology and Results from Field Testing , 1998 .

[25]  J House,et al.  An Expert Rule Set For Fault Detection In Air-Handling Units | NIST , 2001 .

[26]  Nando de Freitas,et al.  The Unscented Particle Filter , 2000, NIPS.

[27]  Fu Xiao,et al.  AHU sensor fault diagnosis using principal component analysis method , 2004 .

[28]  R. Webb,et al.  Calculation of Fin Efficiency for Wet and Dry Fins , 1996 .

[29]  Michael R. Brambley,et al.  Final Project Report: Self-Correcting Controls for VAV System Faults Filter/Fan/Coil and VAV Box Sections , 2011 .

[30]  Maya R. Gupta,et al.  EM Demystified: An Expectation-Maximization Tutorial , 2010 .

[31]  Dilip Roy,et al.  The Discrete Normal Distribution , 2003 .

[32]  P. Pfeifer,et al.  Chi-Square Goodness-of-Fit Test , 2008, SSRN Electronic Journal.

[33]  Paul Raftery,et al.  Comparative analysis of the AHU InFO fault detection and diagnostic expert tool for AHUs with APAR , 2015 .