TY - GEN
T1 - Failure detection using support vector machine and artificial neural networks
T2 - 8th International Conference on Condition Monitoring and Machinery Failure Prevention Technologies 2011, CM 2011/MFPT 2011
AU - Fuqing, Yuan
AU - Kumar, Uday
AU - Galar, Diego
PY - 2011
Y1 - 2011
N2 - Failure detection is a crucial step for condition based maintenance. The importance of failure detection necessitates an efficient and effective failure pattern identification method. Artificial Intelligence (AI) techniques emerging as prospective pattern recognition techniques in failure detection has been showing its adaptability, flexibility and efficiency. In literature, numerous artificial techniques have been invented based on different principles and motivations. Artificial Neural Networks (ANN), Support Vector Machines (SVM) are two important techniques of them. Regardless of variations of the two AI techniques, this paper discusses the mathematical theories of these two techniques. Later on discusses their theoretical similarity and difference. Eventually using the commonest ANN, SVM, an example is presented on failure detection using a wide used bearing data. Their performances are compared in terms of accuracy, computational cost, robustness.
AB - Failure detection is a crucial step for condition based maintenance. The importance of failure detection necessitates an efficient and effective failure pattern identification method. Artificial Intelligence (AI) techniques emerging as prospective pattern recognition techniques in failure detection has been showing its adaptability, flexibility and efficiency. In literature, numerous artificial techniques have been invented based on different principles and motivations. Artificial Neural Networks (ANN), Support Vector Machines (SVM) are two important techniques of them. Regardless of variations of the two AI techniques, this paper discusses the mathematical theories of these two techniques. Later on discusses their theoretical similarity and difference. Eventually using the commonest ANN, SVM, an example is presented on failure detection using a wide used bearing data. Their performances are compared in terms of accuracy, computational cost, robustness.
KW - Artificial Neural Networks (ANN)
KW - Artificial Techniques
KW - Failure Detecting
KW - Failure Detection
KW - Support Vector Machines (SVM)
UR - https://www.scopus.com/pages/publications/84905757608
M3 - Conference contribution
AN - SCOPUS:84905757608
SN - 9781618390141
T3 - 8th International Conference on Condition Monitoring and Machinery Failure Prevention Technologies 2011, CM 2011/MFPT 2011
SP - 189
EP - 201
BT - 8th International Conference on Condition Monitoring and Machinery Failure Prevention Technologies 2011, CM 2011/MFPT 2011
PB - British Institute of Non-Destructive Testing
Y2 - 20 June 2011 through 22 June 2011
ER -