Abstract
It is significant to identify the running-states of diesel engines for ensuring its running stability, fuel economy and emission behavior. Vibration diagnosis is an on-line prognostics and diagnosis technique by picking-up the frequency characters of the vibration signal on the diesel engine. In the paper, combining with the wavelet noise reduction and character extraction with varying scales, the Hidden Semi-Markov model (HSMM) is built by the example of the inlet valve abrasion to recognize the running-states effectively. According to experiment and simulation researches, it indicates that the identification veracity is 96.9% in the 160 test samples after training the HSMM with 120 training samples. This state recognition method is satisfied for the engineering demand, and it can be applied to vibration analysis for other complex machineries.
Publisher
Trans Tech Publications, Ltd.
Reference8 articles.
1. Huang Qiang, Song Shihua, Ding Zhihua, etc. Analysis of fault grades of diesel engines using vibration signals [J]. Journal of Huazhong University of Science and Technology, No. 6(2007), pp.105-107, In Chinese.
2. D. Watzenig, M.S. Sommer and G. Steiner. Engine state monitoring and fault diagnosis of large marine diesel engines. e&i Elektrotechnik und Informationstechnik, Vol. 126(2009), pp.173-179.
3. ZhiGang Han, XiaoYan Liu, ShuXia Jiang. Fault Diagnosis of Electronic Ignition System of Automobile Engine Based on Wavelet Transform. Advances in Mechanical and Electronic Engineering. No. 176(2012), pp.51-55.
4. Ridha Ziani, Rabah Zegadi, Ahmed Felkaoui, Mohammed Djouada. Bearing Fault Diagnosis Using Neural Network and Genetic Algorithms with the Trace Criterion. Condition Monitoring of Machinery in Non-Stationary Operations. (2012), pp.89-96.
5. Zhang Xiao, Huang Qiang. Recovery of 3D Human Posture based on Monocular Vision Technology. Proceedings of 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems, November, (2009), pp.5-8.