General Fault Monitoring and Diagnosis Expert System Based on Fault Tree and Multi-Sensor Information

Abstract:

Due to the limited generality of traditional fault diagnosis expert system and its low accuracy of extracting failure symptoms, a general fault monitoring and diagnosis expert system has been built. For different devices, users can build fault trees in an interactive way and then the fault trees will be saved as expert knowledge. A variety of sensors are fixed to monitor the real-time condition of the device and intelligent algorithms such as wavelet transform and neural network are used to assist the extraction of failure symptoms. On the basis of integration of multi-sensor failure symptoms, the fault diagnosis is realized through forward and backward reasoning. The simulation diagnosis experiments of NC device have shown the effectiveness of the proposed method.

• Periodical: Applied Mechanics and Materials (Volumes 121-126)
• Pages: 4481-4485
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.121-126.4481
• Online since: October 2011
• Authors: Ai Yu Zhang, Xiao Guang Zhao, Lei Zhang
• Keywords: Backward Reasoning, Expert System, Fault Diagnosis, Fault Tree, Forward Reasoning, Neural Network (NN), Wavelet Transform (WT)

References

[1] Zalis K. Application of expert system in diagnostics of high voltage insulating system[J]. Proceedings of the 2004 IEEE International Conference, Volume 2, Page(s): 691-694, July (2004).

DOI: 10.1109/icsd.2004.1350525

[2] SHI Jiangping, TONG Weiguang, WANG Daling. Design of the Transformer Fault Diagnosis Expert System Based on Fuzzy Reasoning[J]. Computer Science-Technology and Applications, 2009. IFCSTA '09. International Forum on, Page(s): 110 – 114, Dec. (2009).

DOI: 10.1109/ifcsta.2009.34

[3] ZHANG Hanqiu, Yong Yan. A Wavelet-Based Approach to Abrupt Fault Detection and Diagnosis of Sensors[J]. Instrumentation and Measurement, IEEE Transactions on, Page(s): 1389-1396, (2001).

DOI: 10.1109/19.963215

[4] Lada, E. K, Jye-Chyi Lu , Wilson, J.R. A Wavelet-Based Procedure for Process Fault Detection[J]. Semiconductor Manufacturing, IEEE Transactions on, Page(s): 79-90, Feb. (2002).

DOI: 10.1109/66.983447

[5] Singh, G.K., Al Kazzaz, S.A.S. Development of an Intelligent Diagnostic System for Induction Machine Health Monitoring[J]. Systems Journal, IEEE, Page(s): 273-288, June (2008).

DOI: 10.1109/jsyst.2008.924129

[6] Perera, N., Rajapakse, A.D. Recognition of Fault Transients Using a Probabilistic Neural-Network Classifier[J]. Power Delivery, IEEE Transactions on, Page(s): 410-419, (2011).

DOI: 10.1109/tpwrd.2010.2060214

[7] Aminian, M., Aminian, F. A Modular Fault-Diagnostic System for Analog Electronic Circuits Using Neural Networks with Wavelet Transform as a Preprocessor[J]. Instrumentation and Measurement, IEEE Transactions on, Page(s): 1546 -1554, Oct. (2007).

DOI: 10.1109/tim.2007.904549

[8] WU Jian. The CNC Machine Faults Diagnosis Expert System Base on CLIPS[D]. Guangxi: Guangxi University, (2008).

[9] YIN Chaoqing, YIN Hao. Artificial Intelligence and Expert System[M]. Beijing: China WaterPower Press, (2002).

[10] FU Qinyi, FU Jianyi, WANG Fenglin. A Kind of Wavelet Packet Algorithm without Frequency Band Derangement[J]. Journal of Vibration Engineering, 1999, 12: 423-428.

[11] Mallat S. A Theory for Multiresolution Signal Decomposition: The Wavelet Representation[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, Page(s): 674-693, July (1989).

DOI: 10.1109/34.192463

[12] GUI Zhonghua, HAN Fengqin. Neural Network Based on Wavelet Packet-Characteristic Entropy For Fault Diagnosis of Draft Tube[J]. Proceedings of the CSEE. 2005, 25(4): 99-102.