Application of Hidden Markov Models in Ball Mill Gearbox for Fault Diagnosis

Abstract:

In this paper, a ball mill gear reducer was regarded as the research object. Based on the HMM pattern recognition theory, DHMM methods that were used in fault diagnosis had been researched. The vibration signal was required a series transformations which are feature extraction, normalization, scalarization and quantization to get the sequence collections. Then the quantified sequence collections were trained to get the DHMM parameter, or the Viterbi Algorithm which was used for the quantified sequence collections to calculate the maximum probability, thereby the DHMM fault models library was established or the type of fault was recognized. Experiments of five kinds of fault model diagnosis were carried out in this article.

• Periodical: Advanced Materials Research (Volume 842)
• Pages: 401-404
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.842.401
• Online since: November 2013
• Authors: Rong Shu Zheng*, Xin Min Dong, Wang Sheng Hao, Yan Li, Rui Xin Wang
• Keywords: DHMM, Fault Diagnosis, HMM, Pattern Recognition, Viterbi Algorithm

References

[1] Guobao Li. Mill edge reducer fault diagnosis system development[In Chinese]. Changsha: Central South University, 2008: 1.

[2] Hui Zhang, Hua-jing Fang, Lisha Xia. Department of Control Science and Engineering, Huazhong University of Science and Technology. Proceedings of IEEE, (2013).

[3] Changjian Feng. HMM dynamic pattern recognition theory, methods, and in rotating machinery fault diagnosis[In Chinese]. Hangzhou: Zhejiang University, (2002).

[4] Jin Chen. Machinery Vibration Monitoring and Fault Diagnosis[In Chinese]. Shanghai: Shanghai Jiaotong University Press, (1999).

[5] Winger L.L. Signal Processing; IEEE Transactions on, 2001, 49(7): p.1501.

[6] Baker J K. IEEE Trans. Assp. 1975, 23(1): p.24.

[7] Rabiner L R. AT&T Bell Tab. Tech,J. 1984, 63(4): p.627.