A system for classification of time-series data from industrial non-destructive device
作者： J.A. Perez-Benitez , L.R. Padovese
DOI: 10.1016/J.ENGAPPAI.2012.09.006
关键词:
摘要: This work proposes a system for classification of industrial steel pieces by means magnetic nondestructive device. The proposed presents two main stages, online stage and off-line stage. In stage, the classifies inputs saves misclassification information in order to perform posterior analyses. optimization topology Probabilistic Neural Network is optimized Feature Selection algorithm combined with increase rate. searches signal spectrogram combining three basic elements: Sequential Forward algorithm, Cluster Grow rate gradient analysis Backward Selection. Also, trash-data recycling obtain optimal feedback samples selected from misclassified ones.
fapesp.br
sci-hub.se 参考文章(19)
Alex J. Smola, Bernhard Schölkopf, A tutorial on support vector regression Statistics and Computing. ,vol. 14, pp. 199- 222 ,(2004) , 10.1023/B:STCO.0000035301.49549.88
Chih-Yang Tsai, An iterative feature reduction algorithm for probabilistic neural networks Omega-international Journal of Management Science. ,vol. 28, pp. 513- 524 ,(2000) , 10.1016/S0305-0483(99)00077-8
Yong Wang, Lin Li, Jun Ni, Shuhong Huang, Feature selection using tabu search with long-term memories and probabilistic neural networks Pattern Recognition Letters. ,vol. 30, pp. 661- 670 ,(2009) , 10.1016/J.PATREC.2009.02.001
Michael R. Berthold, Jay Diamond, Constructive training of probabilistic neural networks Neurocomputing. ,vol. 19, pp. 167- 183 ,(1998) , 10.1016/S0925-2312(97)00063-5
Varanon Uraikul, Christine W. Chan, Paitoon Tontiwachwuthikul, Artificial intelligence for monitoring and supervisory control of process systems Engineering Applications of Artificial Intelligence. ,vol. 20, pp. 115- 131 ,(2007) , 10.1016/J.ENGAPPAI.2006.07.002
A.A. Carvalho, J.M.A. Rebello, L.V.S. Sagrilo, C.S. Camerini, I.V.J. Miranda, MFL signals and artificial neural networks applied to detection and classification of pipe weld defects NDT & E International. ,vol. 39, pp. 661- 667 ,(2006) , 10.1016/J.NDTEINT.2006.04.003
A. Masnata, M. Sunseri, Neural network classification of flaws detected by ultrasonic means NDT & E International. ,vol. 29, pp. 87- 93 ,(1996) , 10.1016/0963-8695(95)00053-4
J.A. Pérez-Benitez, L.R. Padovese, Feature Selection and Neural Network for analysis of microstructural changes in magnetic materials Expert Systems With Applications. ,vol. 38, pp. 10547- 10553 ,(2011) , 10.1016/J.ESWA.2011.02.088
R Vicen, R Gil, P Jarabo, M Rosa, F López, D Martı́nez, Non-linear filtering of ultrasonic signals using neural networks. Ultrasonics. ,vol. 42, pp. 355- 360 ,(2004) , 10.1016/J.ULTRAS.2003.11.002
Francesca Cau, Alessandra Fanni, Augusto Montisci, Pietro Testoni, Mariangela Usai, A signal-processing tool for non-destructive testing of inaccessible pipes Engineering Applications of Artificial Intelligence. ,vol. 19, pp. 753- 760 ,(2006) , 10.1016/J.ENGAPPAI.2006.05.005