This paper investigates the classification of a valve clearance fault in an internal combustion diesel engine using vibration time domain features extracted from signal segments measured at several points on the engine bloc. Signals containing a large number of engine cycles are used to obtain a number of observations of each feature. The set of features is thus considered a set of variables. A stepwise variable selection algorithm based on univariate and multivariate analysis of variance is then used to sort the variables according to their diagnostic ability. The algorithm is also used to construct sets of variables of increasing size used to improve fault classification. Four commonly used supervised classifiers are trained and then tested, giving roughly the same percentage of correct classification. The tested classifiers confirmed that the use of more variables selected by the stepwise variable selection algorithm increases the percentage of correct classification.
AntoniJDanièreJGuilletF (2002) Effective vibration analysis of IC engines using cyclostationarity. Part I: A methodology for condition monitoring. Journal of Sound and Vibration257(5): 815–37.
2.
BogusćPMerkiszJ (2005) Misfire detection of locomotive diesel engine by non-linear analysis. Mechanical Systems and Signal Processing19(4): 881–99.
3.
BoutrosTLiangM (2007) Mechanical fault detection using fuzzy index fusion. International Journal of Machine Tools and Manufacture47(11): 1702–14.
4.
CarlucciAPChiaraFLaforgiaD (2006) Analysis of the relation between injection parameter variation and block vibration of an internal combustion diesel engine. Journal of Sound and Vibration295: 141–64.
5.
ChengdongWYouyunZZhenyuanZ (2008) Fault diagnosis for diesel valve trains based on time–frequency images. Mechanical Systems and Signal Processing22: 1981–93.
6.
ClarenceWS (2005) Vibration and shock handbook. New York: Taylor & Francis.
FanYSZhengGT (2007) Research of high-resolution vibration signal detection technique and application to mechanical fault diagnosis. Mechanical Systems and Signal Processing21: 678–87.
12.
FawcettT (2006) An introduction to ROC analysis. Pattern Recognition Letters27: 861–74.
13.
GengZChenJHullJB (2003) Analysis of engine vibration and design of an applicable diagnosing approach. International Journal of Mechanical Sciences45: 1391–410.
14.
GirtlerJKorczewskiZManczakJ (2010) Conception of diagnosing self-ignition engines fed with biofuels in operation conditions. Journal of Polish CIMAC5(2): 83–97.
15.
GuyonLElisseeffA (2003) An introduction to variable and feature selection. Journal of Machine Learning Research3(1): 1157–82.
HuQHeZZhangZZiY (2007) Fault diagnosis of rotating machinery based on improved wavelet package transform and SVMs ensemble. Mechanical Systems and Signal Processing21: 688–705.
18.
KunchevaLI (2004) Combining pattern classifiers: methods and algorithms. Hoboken, NJ: John Wiley & Sons, Inc.
19.
LeonhardtSAyoubiM (1997) Methods for fault diagnosis. Control Engineering Practice5(5): 683–92.
20.
LiHMaXHuHRenQ (2006) Investigation on reciprocating engine condition classification by using wavelet packet Hilbert spectrum. In: JiaoL. (eds) Lecture Notes in Computer Science, Advances in Natural Computation. Berlin: Springer, 588–97.
21.
LopatinskalaEZhuJMathewJ (1995) Monitoring varying speed machinery vibration – II. Recursive filters and angle domain. Mechanical Systems and Signal Processing9(6): 647–55.
22.
MarpesV (1977) On the frequency content of the surface vibration of a diesel engine. Journal of Sound and Vibration52(3): 365–86.
OthmanMO (1989) Improving the performance of multi-cylinder engine by spectrum analyser feedback. Journal of Sound and Vibration131(l): l–l1.
25.
RaichACCinarA (1995) Multivariate statistical methods for monitoring continuous processes: assessment of discrimination power of disturbance models and diagnosis of multiple disturbances. Chemometrics and Intelligent Laboratory Systems30: 37–48.
26.
RencherAC (2002) Methods of multivariate analysis, 2nd ed.New York: John Wiley & Sons.
27.
RossSM (2004) Introduction to probability and statistics for engineers and scientists, 3rd ed.San Diego, CA: Academic Press.
28.
SamuelPDPinesDJ (2005) A review of vibration-based techniques for helicopter transmission diagnostics. Journal of Sound and Vibration282: 475–508.
29.
ShenLTayFE H (2000) Fault diagnosis based on rough set theory. Computers in Industry43: 61–72.
30.
ShiyuanLFengshouGBallA (2006) Detection of engine valve faults by vibration signals measured on the cylinder head. Proceedings of the Institution of Mechanical Engineers, Part D, Journal of Automobile Engineering220(3): 379–86.
31.
ToivolaJHollménJ (2009) Feature extraction and selection from vibration measurements for structural health monitoring. Advances in intelligent data analysis VIII. Berlin: Springer, 213–24.
32.
WalpoleREMyersRHMyersSLYeK (2007) Probability & statistics for engineers & scientists, 8th ed.Upper Saddle River, NJ: Pearson Education Inc.
33.
WeisbergS (2005) Applied linear regression, 3rd ed.Hoboken, NJ: John Wiley & Sons, Inc.
34.
WidodoAYangBS (2007) Support vector machine in machine condition monitoring and fault diagnosis. Mechanical Systems and Signal Processing21: 2560–74.
35.
WuJDChenJC (2006) Continuous wavelet transform technique for fault signal diagnosis of internal combustion engines. NDT&E International39: 304–11.
36.
WuXChenJWangWZhouY (2001) Multi-index fusion-based fault diagnosis theories and methods. Mechanical Systems and Signal Processing15(5): 995–1006.
37.
YangWX (2006) Establishment of the mathematical model for diagnosing the engine valve faults by genetic programming. Journal of Sound and Vibration293: 213–26.
38.
ZhangLNandiAK (2007) Fault classification using genetic programming. Mechanical Systems and Signal Processing21: 1273–84.
