论文信息 - Damage identification using support vector machines

Damage identification using support vector machines

Support vector machines have recently been established as a powerful tool for classification and regression problems. Their use in the field of damage identification is illustrated here with reference to two problems which can be naturally cast in terms of classification. The first is a fault classification problem for ball bearings and the second looks at locating damage within a framework structure. The performance is compared to more established means of engineering pattern recognition.

Keith Worden | A J Lane | K. Worden | A. Lane

[1] Vladimir N. Vapnik,et al. The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[2] John Moody,et al. Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[3] Gilbert Strang,et al. Introduction to applied mathematics , 1988 .

[4] Stephen J. Roberts,et al. Supervised and unsupervised learning in radial basis function classifiers , 1994 .

[5] Lionel Tarassenko,et al. Guide to Neural Computing Applications , 1998 .

[6] Vladimir Cherkassky,et al. Learning from Data: Concepts, Theory, and Methods , 1998 .

[7] Keith Worden,et al. DAMAGE DETECTION USING OUTLIER ANALYSIS , 2000 .

[8] Keith Worden,et al. Damage identification using multivariate statistics: Kernel discriminant analysis , 2000 .