Browse > Article

The Fault Detection of an Air-Conditioning System by Using a Residual Input RBF Neural Network  

Han, Do-Young (Department of Mechanical and Automotive engineering, Kookmin University)
Ryoo, Byoung-Jin (Graduate School of Mechanical Engineering, Kookmin University)
Publication Information
Korean Journal of Air-Conditioning and Refrigeration Engineering / v.17, no.8, 2005 , pp. 780-788 More about this Journal
Abstract
Two different types of algorithms were developed and applied to detect the partial faults of a multi-type air conditioning system. Partial faults include the compressor valve leakage, the refrigerant pipe partial blockage, the condenser fouling, and the evaporator fouling. The first algorithm was developed by using mathematical models and parity relations, and the second algorithm was developed by using mathematical models and a RBF neural network. Test results showed that the second algorithm was better than the first algorithm in detecting various partial faults of the system. Therefore, the algorithm developed by using mathematical models and a RBF neural network may be used for the detection of partial faults of an air-conditioning system.
Keywords
Mathematical models; Parity relations; RBF(Radial Basis Function) Neural network; Compressor valve leakage; Refrigerant pipe partial blockage; Condenser fouling; Evaporator fouling;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Breuker, M. S. and Braun, J. E, 1998, Evaluating the performance of a fault detection and diagnostic system for vapor compression equipment, ASHRAE HVAC&R Research, Vol. 4, No.4, pp.401-425   DOI   ScienceOn
2 Frank, D. and Pletta, J. B., 1992, Neural network sensor fusion for security application, Intelligent Engineering Systems through Artificial Neural Networks, Vol. 2, pp.745-750
3 Han, D. and Ryoo, B., 2003, Partial fault diagnosis of the air-conditioning system by using curve fitting model and neural network algorithm, Proceedings of the SAREK, pp.577-582
4 Han, D. and Ryoo, B., 2004, Fault detection and diagnosis of the air-conditioning system by using a fuzzy algorithm and a RBF neural network, Proceedings of the SAREK, pp. 795-800
5 Riemer, P. L., Mitchell, J. W. and Beckman, W. A., 2002, The use of series analysis in fault detection and diagnosis methodologies, ASHRAE Transactions. 2002, V.108, Pt. 2
6 McIntosh, I. B. D., Mitchell, J. W. and Beckman, W. A., 2000, Fault detection and diagnosis in chillers, ASHRAE Transactions 2000, V.106, Pt. 2
7 Peitsman, H. C. and Bakker, V. E., 1996, Application of black-box models to HVAC systems for fault detection, ASHRAE Transactions, pp. 628-640
8 Han, D. and Joo, M., 2002, Fault detection & diagnosis of an air handling unit based on rule bases, Korean Journal of the Air Conditioning and Refrigeration Engineering, Vol. 14, No.7, pp.552-559
9 Han, D. and Kim, J., 2004, An experimental study on the rule based fault detection and diagnosis system for a constant air volume air handling unit, Korean Journal of the Air-Conditioning and Refrigeration Engineering, Vol. 16, No.9, pp.872-880
10 Han, D. and Hwang, J, 2003, The partial fault detection of an air-conditioning system by the neural network algorithm using normalized input data, Korean Journal of the Air-Conditioning and Refrigeration Engineering, Vol. 15, No.3, pp.159-165
11 Han, D. and Lee, H., 2002, Partial fault detection of air-conditioning system by neural network algorithm using data preprocessing method, Korean Journal of the SAREK Vol. 14, No.7, pp.560-566
12 Ch'ng, C. G. and Yak, A. S., 1998, Neural networks for process diagnosis, ICARCY, pp. 494-498
13 Peitsman, H. C. and Soethout, L. L., 1997, ARX models and real-time model-based diagnosis, ASHHAE Transactions, pp.657-671
14 Breuker, M. S. and Braun, J E., 1998, Common faults and their impacts for rooftop air conditioners, HVAC&R Research, Vol. 4, No. 3, pp.303-318   DOI   ScienceOn