Fault Detection and Diagnosis with Modelica Language using Deep Belief Network

Dongkyu Lee
Green City R&D Team, R&D Division, Hyundai Engineering and Construction Company, South Korea

Byoungdoo Lee
Green City R&D Team, R&D Division, Hyundai Engineering and Construction Company, South Korea

Jin Woo Shin
Department of Electrical Engineering, KAIST, South Korea

Ladda ner artikelhttp://dx.doi.org/10.3384/ecp15118615

Ingår i: Proceedings of the 11th International Modelica Conference, Versailles, France, September 21-23, 2015

Linköping Electronic Conference Proceedings 118:66, s. 615-623

Visa mer +

Publicerad: 2015-09-18

ISBN: 978-91-7685-955-1

ISSN: 1650-3686 (tryckt), 1650-3740 (online)


The air handling unit (AHU) is the main component of heating, ventilation and air-conditioning (HVAC) systems, and irregular faults in AHUs are major sources of energy consumption. For energy efficient operation of HVAC, this paper aims to detect and diagnose three abnormal states in the AHU with the popular deep learning model, called Deep Belief Network (DBN), where we train it using various data generated by Modelica.


Fault detectin and diagnosis; Air-handling unit; Deep Belief Network


Massieh Najafi, David M, Auslander, Peter L. Bartlett, Philip Haves, Michael D, Shon, Modeling and measurement constraints in fault detection and diagnostics for HVAC systems, 2010

Zhimin Du, Singiao Jin, Yunyu Yang, Wavelet neural network based fault diagnosis in air handling unit, 2008

J.M.House, H.Vaezi-Nejad, J.M.Whitcomb. An expert rules set for fault detection in air handling units, ASHRAE Trans. 107, 858-871, 2001

J.Schein, S.T. Bushby, N.S. Castro, J.M. House, A rulebased fault detectioin method for air handling units, Energy Build. 38, 1485-1492, 2006

T.I.Salsbury, R.CDimond, Fault detection in HVAC systems using model-based feed forward control, Energy Build. 33, 403-415, 2001

B.Yu, A.H.C. van Passen, S. Riahy, General modeling for model-based FDD on building HVAC systems, Simulat, Pract,,Theory 9(6-8), 387-397, 2002

ASHRAE. Sequences of Operation for Common HVAC Systems. ASHRAE, Atlanta, GA, 2006.

Deru M., K. Field, D. Studer, K. Benne, B. Griffith, P. Torcellini, M. Halverson, D. Winiarski, B. Liu, M. Rosenberg, J. Huang, M. Yazdanian, and D. Crawley. DOE commercial building research benchmarks for commercial buildings. Technical report, U.S. Department of Energy, Energy Efficiency and Renewable Energy, Office of Building Technologies. 2009.

Modelica Buildings Library developed by LBNL. Modelica library for building energy and control systems. http://simulationresearch.lbl.gov/modelica

Top of Alabama Regional Council of Governments. TARCOG: Mathematical models for calculation of thermal performance of glazing systems with our without shading devices, Technical Report, Carli, Inc. 2006.

Masmoudi,Y, Turkay, M, Chabchoub, H, A binarization strategy for modelling mixed data in multigroup classification, Acvanced Logistics and Transport, 345-353, 2013

Yuebin Yu, Denchai Woradechjumroen, and Daihong Yu (2014): A Review of Fault Detection and Diagnosis Methodologies on Air-handling Units.
Energy and Buildings, 82:550–562, 2014.

Zhengwei Li, Adaptable, scalable, probabilistic fault detection and diagnostic methods for the HVAC secondary system. Dissertation. Georgia Institute of Technology. 2012.

Zhimin Du, Bo Fan, Xingqiao Jin, and Jinlei Chi (2014): Fault Detection and Diagnosis for Buildings and HVAC Systems Using Combined Neural Networks and Subtractive Clustering Analysis. Building and Environment, 73:1–11, 2014.

Geoffrey E. Hinton, Simon Osindero, Yee-Whye The, A fast learning algorithm for deep belief nets, Neural Computation, 1527-1554, 2006

Citeringar i Crossref