TY - JOUR
T1 - Evolving an artificial neural network classifier for condition monitoring of rotating mechanical systems
AU - Saxena, Abhinav
AU - Saad, Ashraf
PY - 2007/1
Y1 - 2007/1
N2 - We present the results of our investigation into the use of genetic algorithms (GAs) for identifying near optimal design parameters of diagnostic systems that are based on artificial neural networks (ANNs) for condition monitoring of mechanical systems. ANNs have been widely used for health diagnosis of mechanical bearing using features extracted from vibration and acoustic emission signals. However, different sensors and the corresponding features exhibit varied response to different faults. Moreover, a number of different features can be used as inputs to a classifier ANN. Identification of the most useful features is important for an efficient classification as opposed to using all features from all channels, leading to very high computational cost and is, consequently, not desirable. Furthermore, determining the ANN structure is a fundamental design issue and can be critical for the classification performance. We show that a GA can be used to select a smaller subset of features that together form a genetically fit family for successful fault identification and classification tasks. At the same time, an appropriate structure of the ANN, in terms of the number of nodes in the hidden layer, can be determined, resulting in improved performance.
AB - We present the results of our investigation into the use of genetic algorithms (GAs) for identifying near optimal design parameters of diagnostic systems that are based on artificial neural networks (ANNs) for condition monitoring of mechanical systems. ANNs have been widely used for health diagnosis of mechanical bearing using features extracted from vibration and acoustic emission signals. However, different sensors and the corresponding features exhibit varied response to different faults. Moreover, a number of different features can be used as inputs to a classifier ANN. Identification of the most useful features is important for an efficient classification as opposed to using all features from all channels, leading to very high computational cost and is, consequently, not desirable. Furthermore, determining the ANN structure is a fundamental design issue and can be critical for the classification performance. We show that a GA can be used to select a smaller subset of features that together form a genetically fit family for successful fault identification and classification tasks. At the same time, an appropriate structure of the ANN, in terms of the number of nodes in the hidden layer, can be determined, resulting in improved performance.
KW - Artificial neural networks
KW - Condition monitoring
KW - Fault diagnosis
KW - Genetic algorithms
KW - Hybrid techniques
KW - Rotating mechanical systems
UR - http://www.scopus.com/inward/record.url?scp=33750962698&partnerID=8YFLogxK
U2 - 10.1016/j.asoc.2005.10.001
DO - 10.1016/j.asoc.2005.10.001
M3 - Article
AN - SCOPUS:33750962698
SN - 1568-4946
VL - 7
SP - 441
EP - 454
JO - Applied Soft Computing
JF - Applied Soft Computing
IS - 1
ER -