Application of the cascade correlation algorithms (CCA) to bearing fault classification problems

Abstract The impact of machine breakdowns and failures on factory productivity and product quality is an important concern for manufacturing industries. For this reason, predictive maintenance techniques are being investigated extensively as a method of decreasing machine downtime and enhancing production reliability. With increasing attention on neural network technologies, there is an interest in the application of such networks to manufacturing operations, including predictive maintenance challenges. This paper focuses on applying the cascade correlation algorithm (CCA) in predicting specific bearing faults. In the experimental procedure, a set of vibration signals are collected and used in training the CCA. Each vibration signal contains unique information about the particular machine condition that is occurring. From the results of the experiments provided in the paper, the CCA is shown to be a viable network structure for identifying several different bearing conditions utilizing a minimum network structure without a compromise in accuracy.

[1]  Sergios Theodoridis,et al.  Fast adaptive least squares algorithms for power spectral estimation , 1987, IEEE Trans. Acoust. Speech Signal Process..

[2]  Sergios Theodoridis,et al.  Efficient Symmetric Algorithms for the Modified Covariance Method for Autoregressive Spectral Analysis , 1993, IEEE Trans. Signal Process..

[3]  Venkat Venkatasubramanian,et al.  A neural network methodology for process fault diagnosis , 1989 .

[4]  Mark Serridge.  Ten Crucial Concepts Behind Trustworthy Fault Detection in Machine Condition Monitoring , 1990 .

[5]  Gavriel Salvendy,et al.  Neural-networks-aided fault diagnosis in supervisory control of advanced manufacturing systems , 1993 .

[6]  Gerald M. Knapp,et al.  Machine fault classification: a neural network approach , 1992 .

[7]  Scott E. Fahlman,et al.  The Recurrent Cascade-Correlation Architecture , 1990, NIPS.

[8]  J. Nadal,et al.  Learning in feedforward layered networks: the tiling algorithm , 1989 .

[9]  M Angelo,et al.  CHOOSING ACCELEROMETERS FOR MACHINERY HEALTH MONITORING , 1990 .

[10]  Dhananjay S. Phatak,et al.  Connectivity and performance tradeoffs in the cascade correlation learning architecture , 1994, IEEE Trans. Neural Networks.

[11]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[12]  James L. McClelland.  Explorations In Parallel Distributed Processing , 1988 .

[13]  W. M. Carey,et al.  Digital spectral analysis: with applications , 1986 .

[14]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[15]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[16]  Marcus Frean,et al.  The Upstart Algorithm: A Method for Constructing and Training Feedforward Neural Networks , 1990, Neural Computation.