Diesel Engine Condition Classification Based on Mechanical Dynamics and Time-Frequency Image Processing
In this research, mechanical structure dynamics for diesel engine working process are investigated in detail for diesel engine vibration signal analysis and pattern recognition. Time domain vibration signal can be looked on as several impulse forces’ responses according to mechanical dynamics analysis. Different part vibration signal can be used for different components’ fault diagnoses. It is very useful to determine the best suitable vibration signal for analysis according to structure dynamics analysis. Hilbert spectrum is used to construct time-frequency distribution because of its performance for nonstationary signal analysis. Time-frequency image technology is investigated in this research for diesel engine fault diagnosis. Euclidean distance is used to distinguish engines’ different working conditions. A single cylinder 1135 direct injection diesel engine with different working conditions classification is as an example to testify the effectiveness of this method. It can be concluded that this new approach can improve the accuracy for diesel engine condition classification.
KeywordsDiesel Engine Fault Diagnosis Empirical Mode Decomposition Vibration Signal Cylinder Head
The support from Chinese National Science Foundation (Grant No. 50805014) for this research is gratefully acknowledged. The first author also wishes to acknowledge to financial aid from State key laboratory of mechanical system and vibration, Shanghai Jiao Tong University (Grant No. VSN-2008-04) and State Key Laboratory of Structural Analysis for Industrial Equipment, Dalian University of Technology (Grant No. GZ0817).
- 1.Logan K, Inozu B, Roy P, Hetet JF, Chesse P, Tauzia X (2002) Real-time marine diesel engine simulation for fault diagnosis. Mar Technol 39(1):21–28Google Scholar
- 4.Li HK, Zhou PL, Ma XJ (2006) Marine diesel engine fault diagnosis by using improved Hilbert spectrum. J Ship Res 4:378–387Google Scholar
- 5.Ma XJ, Yu B, Zhang ZX (2000) A new approach to time-frequency analysis – local wave method. J Vib Eng 25(s):219–224Google Scholar
- 8.Antoni J, Daniere J, et al (2002) Effective vibration analysis of IC engines using cyclostationarity. Part I – a methodology for condition monitoring. J Sound Vib 257(5): 815–837Google Scholar