Study of Intelligent Fault Diagnosis Method for Turbo-Generator Unit Based on Support Vector Machine and Knowledge

Abstract:

For the low efficiency and poor accuracy of turbo-generator Unit s fault diagnosis, this paper divided the common 18 kinds of vibration fault into four categories, and took advantage of support vector machine to distinguish the fault cluster for early fault diagnosis according to the characteristics of vibration signal spectrum. For different fault cluster, different fault pattern recognition model was established. With the use of certain symptom group and weighted fuzzy logic, this article engaged in knowledge reasoning to obtain the specific fault recognition mode. Besides, the searching methods of fault cause, fault influence and troubleshooting measures in the knowledge base were proposed, which made the diagnosis process more meticulous and comprehensive. Case analysis shows that it is feasible to use this method to develop a system for intelligent fault diagnosis of turbo-generator unit, which is valuable for further study in more depth.

• Periodical: Applied Mechanics and Materials (Volumes 543-547)
• Pages: 1057-1063
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.543-547.1057
• Online since: March 2014
• Authors: Xiao Wen Deng*, Yu Jiong Gu, Li Ping Fang, Zhao Xu Ren, Ya Peng Han
• Keywords: Fault Diagnosis, Knowledge Reasoning, Support Vector Machine (SVM), Turbo-Generator Unit, Weighted Fuzzy Logic

References

[1] Donghua Zhou, Yanyan Hu. Fault diagnosis of dynamic systems [J]. Journal of automation, 2009(6), pp.748-758. In Chinese.

[2] Gabbar H A. Design of Intelligent Fault Diagnostic System (FDS) [J]. Process Safety and Environmental Protection, 2007, 85(6) , pp.566-578.

DOI: 10.1205/psep06053

[3] Weixin Shi, Jingbo Shi. Vibration of steam turbine generator unit and accident [M] Beijing: China Electric Power Press, 2008. In Chinese.

[4] Zhongguang Fu. Steam turbine operation and accident treatment [M] Beijing: China Electric Power Press, 2007. In Chinese.

[5] Luping Li, Xuxiang Lu. Vibration of steam turbine generator unit and treatment [M] Beijing: China Electric Power Press, 2007. In Chinese.

[6] Naiyang Deng, Yingjie Tian. Support vector machine: theory, algorithm and development [M] Beijing: Science Press, 2009. In Chinese.

[7] Xuegong Zhang. Introduction of statistical learning theory and support vector machine [J]. Journal of automation, 2000, 26(1) , pp.32-42. In Chinese.

[8] Peng Bai etc. The support vector machine theory and engineering application [M] Xi'an: Xi'an Electronic and Science University Press, 2008. In Chinese.

[9] Wenji Peng, Xingqi Luo, Research on vibration fault diagnosis of hydroelectric unit based on wavelet packet and support vector machine [J]. Chinese Journal of Mechanical Engineering, 2006(24) , pp.164-168. In Chinese.

[10] Elangovan M, Sugumaran V, Ramachandran K I, et al. Effect of SVM kernel functions on classification of vibration signals of a single point cutting tool. Expert System with Applications [J]. 2011, 38(12) , pp.15202-15207.

DOI: 10.1016/j.eswa.2011.05.081

[11] Chang C C, Lin C J, LIBSVM: A library for support vector machines. ACM Trans. Intell. Syst. Technol [J]. 2011, 2(3) , pp.1-27.

DOI: 10.1145/1961189.1961199

[12] Rongzhen Zhao, Chao Li, Youyun Zhang. The development problems of diagnosis knowledge acquisition of fault diagnosis for intelligent mechanical [J]. The vibration and shock, 2007(9) , pp.71-74. In Chinese.