Detection of inappropriate working conditions for the timing belt in internal-combustion engines using vibration signals and data mining

Abstract

Abnormal operating conditions for the timing belt can lead to cracks, fatigue, sudden rupture and damage to engines. In this study, an intelligent system was developed to detect and classify high-load operating conditions and high-temperature operating conditions for timing belts. To achieve this, vibration signals in normal operating conditions, high-load operating conditions and high-temperature operating conditions were collected. Time-domain signals were transformed to the frequency domain and the time–frequency domain using the fast Fourier transform method and the wavelet transform method respectively. In the data-mining stage, 25 statistical features were extracted from different signal domains. The improved distance evaluation method was adopted to select the best features and to reduce the input space for the classifier. Then, the signal features from the time domain, the frequency domain and the time-frequency domain were fed into an artificial neural network to evaluate the accuracy of this designed procedure for detecting inappropriate operating conditions for the timing belt. Based on all these features extracted from the signals in the time, frequency and time–frequency domains, the artificial neural network classifier detected and classified normal operating conditions, high-load operating conditions and high-temperature operating conditions with accuracies of 73.3%, 85% and 89.2% respectively. The classification accuracies using features selected by improved distance evaluation in the signals from the time, frequency and time–frequency domains were found to be 85%, 95.8% and 95% respectively. The results showed that the developed system was capable of detecting and classifying both the normal operating conditions and abnormal operating conditions for the timing belt. The results also suggested that a combination of signal processing and feature selection can significantly enhance the classification accuracy.

Keywords

Fault diagnosis and classification internal-combustion engine timing belt artificial neural networks signal processing data mining

Get full access to this article

View all access options for this article.

References

Manin

Michon

Remond

Dufour

From transmission error measurement to pulley–belt slip determination in serpentine belt drives: influence of tensioner and belt characteristics. Mechanism Mach Theory 2009; 44: 813–821.

Thomanek

Steinberg

Krauser

. Ford Zetec-E, I4 engine timing belt drive. SAE paper 1999-01-0641, 1999.

Stojanovic

Tanasijevic

Miloradovic

Tribomechanical systems in timing belt drives. J Balkan Tribol Assoc 2009; 15: 465–473.

Mikalauskas

Volkovas

Analysis of the dynamics of a defective V-belt and diagnostic possibilities. Proc IMechE Part I: J Systems and Control Engineering 2006; 220: 145–153.

Ucar

Ergun

Cengiz

A novel failure diagnosis system design for automotive timing belts. Expl Techq 2014; 38: 48–53.

Ahmed

Method and apparatus for detecting timing belt damage using link-coupled feedback. US Patent 6,523,400, 2003.

Dalgarno

Day

Childs

THX

Moore

RB.

Stiffness loss of synchronous belts. Composites Part B: Engng 1998; 9: 217–222.

Fedorko

Ivančo

Molnár

Husáková

Simulation of interaction of a pipe conveyor belt with moulding rolls. Procedia Engng 2012; 48: 129–134.

Blander

Wenzel

Piska

VG.

Method of detecting timing apparatus malfunction in an engine. US Patent 5,463,898, 1995.

10.

Mack

JE.

Belt flaw detector. US Patent 5,994,712, 1999.

11.

Childs

Dalgarno

Day

Moore

Automotive timing belt life laws and a user design guide. Proc IMechE Part D: J Automobile Engineering 1998; 212(5): 409–419.

12.

Nassiri

New approach in characterizing accessory drive belts for finite element applications. Master’s Thesis, Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, 2011.

13.

Basso

Detection of reduced tooth stiffness in synchronous belts by means of pulley vibration monitoring. Proc IMechE Part D: J Automobile Engineering 2006; 220(7): 947–957.

14.

Dalgarno

Day

Childs

Synchronous belt materials and belt life correlation. Proc IMechE Part D: J Automobile Engineering 1994; 208(1): 37–48.

15.

Callegari

Cannella

Ferri

Multi-body modelling of timing belt dynamics. Proc IMechE Part K: J Multi-body Dynamics 2003; 217: 63–75.

16.

Fawcett

Improvements in belt tension setting procedures on internal combustion engines. Proc IMechE Part D: J Automobile Engineering 1999; 213(2): 119–126.

17.

T-S.

Applying wavelets transform and support vector machine for copper clad laminate defects classification. Comput Ind Engng 2009; 56: 1154–1168.

18.

Andrade

Esat

Badi

MNM

. A new approach to time-domain vibration condition monitoring: gear tooth fatigue crack detection and identification by the Kolmogorov–Smirnov test. J Sound Vibr 2001; 240: 909–919.

19.

C-Y

Bahill

AT.

Preprocessing methods in the computation of the fast Fourier transform. Comput Ind Engng 1991; 21: 653–657.

20.

Zhu

Wong

Hong

GS.

Wavelet analysis of sensor signals for tool condition monitoring: a review and some new results. Int J Mach Tools Mf 2009; 49: 537–553.

21.

Huang

Recognition of concurrent control chart patterns using wavelet transform decomposition and multiclass support vector machines. Comput Ind Engng 2013; 66: 683–695.

22.

Xian

G-M

Zeng

B-Q.

An intelligent fault diagnosis method based on wavelet packer analysis and hybrid support vector machines. Expert Systems Applic 2009; 36: 12 131–12 136.

23.

Peng

Chu

FL.

Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography. Mech Systems Signal Processing 2004; 18: 199–221.

24.

Rafiee

Tse

PW.

Application of mother wavelet functions for automatic gear and bearing fault diagnosis. Expert Systems Applic 2010; 37: 4568–4579.

25.

Banakar

Azeem

MF.

Artificial wavelet neural network and its application in neuro-fuzzy models. Appl Soft Comput 2008; 8: 1463–1485.

26.

Abdullah

Sabar

Ahmad Nazri

Ayob

An exponential Monte-Carlo algorithm for feature selection problems. Comput Ind Engng 2014; 67: 160–167.

27.

Lei

A new approach to intelligent fault diagnosis of rotating machinery. Expert Systems Applic 2008; 35: 1593–1600.

28.

R-X

Ren

G-Q

J-P.

Engine fault diagnosis based on a morphological neural network using a morphological filter as a preprocessor. Proc IMechE Part D: J Automobile Engineering 2013; 227(4): 490–505.

29.

Castellini

Cupido

Paone

Tomasini

. Tracking laser Doppler vibrometer for linear motion: application to a timing belt. In: 4th international conference on vibration measurements by laser techniques: advances and applications, Proceedings of the SPIE, Vol 4072, Ancona, Italy, 21–23 June 2000, paper 194. Bellingham, Washington: SPIE.

30.

Sundararaman

Chen

Chandrashekhara

Temperature dependent fatigue-failure analysis of V-ribbed serpentine belts. Int J Fatigue 2009; 31: 1262–1270.

31.

Ha-Anh

Vu-Khanh

Prediction of mechanical properties of polychloroprene during thermo-oxidative aging. Polymer testing 2005; 24: 775–780.

32.

Childs

THC

Dalgarno

KW.

V-ribbed belt design, wear and traction capacity. Proc IMechE Part D: J Automobile Engineering 1998; 212(4): 333–344.

33.

Jiang

Makis

Optimal Bayesian estimation and control scheme for gear shaft fault detection. Comput Ind Engng 2012; 63: 754–762.

34.

Crouse

Nowak

Baraniuk

RG.

Wavelet-based statistical signal processing using hidden Markov models. IEEE Trans Signal Processing 1998; 46: 886–902.

35.

Cho

Ensemble based on GA wrapper feature selection. Comput Ind Engng 2006; 51: 111–116.

36.

Manimala

Selvi

Ahila

Hybrid soft computing techniques for feature selection and parameter optimization in power quality data mining. Appl Soft Comput 2011; 11: 5485–5497.

37.

Mitoma

Wang

Chen

Fault diagnosis and condition surveillance for plant rotating machinery using partially-linearized neural network. Comput Ind Engng 2008; 55: 783–794.

38.

Wang

Chen

Intelligent diagnosis method for rolling element bearing faults using possibility theory and neural network. Comput Ind Engng 2011; 60: 511–518.

39.

Khazaee

Ahmadi

Omid

Moosavian

Vibration condition monitoring of planetary gears based on decision level data fusion using Dempster–Shafer theory of evidence. J Vibroengng 2012; 14: 838–851.