Fault detection using transient machine signals

This paper describes the development and testing of a strategy for vibration-based online detection of faults in a particular class of machinery. This machinery is defined by two basic characteristics that preclude it from the application of standard online condition monitoring systems. The first characteristic is the absence of historical fault data. The second characteristic is that the machine is in a constant state of transient operation. An example of such a machine is the swing machinery of an electromechanical excavator. The monitoring strategy presented here employs an anomaly detection scheme together with various methods of signal processing and feature extraction. Experiments are carried out using a laboratory apparatus to show the how various configurations of the system are able to detect different types of faults. The results indicate that this approach is effective and merits further investigation.

[1]  Lionel Tarassenko,et al.  Choosing an appropriate model for novelty detection , 1997 .

[2]  Stephen Jose Hanson,et al.  A Neural Network Autoassociator for Induction Motor Failure Prediction , 1995, NIPS.

[3]  Asoke Nandi.  Vibration based fault detection - features classifiers and novelty detection , 2002 .

[4]  Jin Chen,et al.  Decision tree and PCA-based fault diagnosis of rotating machinery , 2007 .

[5]  Gerhard Widmer,et al.  NOVELTY DETECTION FOR SPECTRAL SIMILARITY OF SONGS , 2005 .

[6]  Bo-Suk Yang,et al.  Condition classification of small reciprocating compressor for refrigeration using artificial neural networks and support vector machines , 2005 .

[7]  Kristin P. Bennett,et al.  Support vector machines: hype or hallelujah? , 2000, SKDD.

[8]  Sameer Singh,et al.  Novelty detection: a review - part 1: statistical approaches , 2003, Signal Process..

[9]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[10]  S. Qian.  Introduction to Time-Frequency and Wavelet Transforms , 2001 .

[11]  Bernhard Schölkopf,et al.  Support Vector Method for Novelty Detection , 1999, NIPS.

[12]  David M. J. Tax,et al.  One-class classification , 2001 .

[13]  Charles R. Farrar,et al.  Novelty detection under changing environmental conditions , 2001, SPIE Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring.

[14]  Paul C. Moster.  Gear fault detection and classification using learning machines , 2004 .

[15]  Robert P. W. Duin,et al.  Novelty Detection Using Self-Organizing Maps , 1997, ICONIP.

[16]  David G. Stork,et al.  Pattern Classification , 1973 .

[17]  Nathalie Japkowicz,et al.  A Novelty Detection Approach to Classification , 1995, IJCAI.

[18]  Sungzoon Cho,et al.  Characteristics of auto-associative MLP as a novelty detector , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[19]  Asoke K. Nandi,et al.  Modified self-organising map for automated novelty detection applied to vibration signal monitoring , 2006 .

[20]  Min-Chun Pan,et al.  Improvement on Gabor order tracking and objective comparison with Vold–Kalman filtering order tracking , 2007 .