Training of Classifiers for Quality Control of On-Line Laser Brazing Processes with Highly Imbalanced Datasets

This paper investigates on the training of classifiers with highly imbalanced datasets for industrial quality control. The application is on-line process monitoring of laser brazing processes and only a limited amount of data of an imperfection class is available for training. Bayesian adaptation is used to derive a model of the imperfection class from a well sampled model of the class representing a high grade joint surface. For this application, we are able to show that with the sparse training data a performance comparable to a training with a balanced dataset is achievable and even a moderate increase of training data quickly yields a performance gain.

[1]  G. Box.  Science and Statistics , 1976 .

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

[3]  Dino Pedreschi,et al.  Machine Learning: ECML 2004 , 2004, Lecture Notes in Computer Science.

[4]  Robert P. W. Duin,et al.  Support Vector Data Description , 2004, Machine Learning.

[5]  Michael Schmidt,et al.  Possibilities for online process monitoring at laser brazing based on two dimensional detector systems , 2009 .

[6]  Stefan Kaierle Dr.-Ing.,et al.  Understanding the Laser Process , 2010 .

[7]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[8]  Michael Brady,et al.  Novelty detection for the identification of masses in mammograms , 1995 .

[9]  Julian Fiérrez,et al.  Bayesian adaptation for user-dependent multimodal biometric authentication , 2005, Pattern Recognit..

[10]  Bernhard Schölkopf,et al.  Estimating the Support of a High-Dimensional Distribution , 2001, Neural Computation.

[11]  Douglas A. Reynolds,et al.  Speaker Verification Using Adapted Gaussian Mixture Models , 2000, Digit. Signal Process..

[12]  Fritz Klocke,et al.  On-line quality control system for laser brazing , 2009 .

[13]  Stephen Kwek,et al.  Applying Support Vector Machines to Imbalanced Datasets , 2004, ECML.

[14]  Stan Matwin,et al.  Addressing the Curse of Imbalanced Training Sets: One-Sided Selection , 1997, ICML.

[15]  Yong Yan,et al.  Review of techniques for on-line monitoring and inspection of laser welding , 2005 .

[16]  Stefan Kaierle,et al.  Understanding the Laser Process , 2010 .

[17]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[18]  Volker Märgner,et al.  In-situ quality monitoring during laser brazing , 2010 .