Fault Diagnosis of Some Equipment Based on BP Neural Network

Abstract:

Neural network has obvious advantages on dealing with the uncertain problems with a huge amount of data. Some equipment’s faults performance of such characteristics that the date is abundant, and failure phenomenon is not explicit and uncertain. Then, it leads to being hard to diagnose the faults through the traditional diagnosis method in a short time. This paper will analysis the data feature and then build a model to deal with the qualitative data attributes in order that the BP network can use it smoothly. Calculation result shows that using this method, fault diagnosis can be simply and quickly. The paper also provides a new kind of composite way to figure out fault positions for the front-line operators based on experts’experience knowledge but not on measurement signals.

• Periodical: Applied Mechanics and Materials (Volumes 644-650)
• Pages: 1193-1196
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.644-650.1193
• Online since: September 2014
• Authors: Qing Li*, Da Lin Sun, Li Zhang, Xue Qian Wang
• Keywords: BP Neural Network (BPNN), Fault Data Qualitative Processing, Fault Diagnosis

References

[1] S.F. Liu, in Theory and Methods for Operations Research and Decision, edited by K.D. Wang, X.Z. Zhou, China, Beijing (2010), in Tsinghua University Press.

[2] D.F. Zhang, in MATLAB Design of BP Network Application, edited by D.F. Zhang, China, Beijing (2008), in China Machine Press.

[3] J. Yang, X.L. Huang, D.S. Zhang, in Intelligent Fault Diagnosis Technology for Equipments, edited by J. Yang, Z.S. Feng, China, Beijing (2004), in National Defence Industry Press.

[4] W. Deng, X.H. Yang, M.H. Zhao: High Voltage Engineering Vol. 35 (2009), p.1624.

[5] J.B. Yang, H.C. Zhang, P. Chen: Computer &. Digital Engineering Vol. 40 (2012), p.65.