Fault Classification in Cylinders Using Multilayer Perceptrons, Support Vector Machines and Guassian Mixture Models

Details Fault Classification in Cylinders Using Multilayer Perceptrons, Support Vector Machines and Guassian Mixture Models Fault Classification in Cylinders Using Multilayer Perceptrons, Support Vector Machines and Guassian Mixture Models

2007-05-02

arxiv.org/abs/0705.0197v1

Computer Assisted Mechanics and Engineering Sciences, Vol. 14, No. 2, 2007.

Computer Science

Artificial Intelligence

10 pages, 2 figures, 4 tables

Scientific paper

Gaussian mixture models (GMM) and support vector machines (SVM) are introduced to classify faults in a population of cylindrical shells. The proposed procedures are tested on a population of 20 cylindrical shells and their performance is compared to the procedure, which uses multi-layer perceptrons (MLP). The modal properties extracted from vibration data are used to train the GMM, SVM and MLP. It is observed that the GMM produces 98%, SVM produces 94% classification accuracy while the MLP produces 88% classification rates.

Affiliated with

Also associated with

No associations

Rating

Fault Classification in Cylinders Using Multilayer Perceptrons, Support Vector Machines and Guassian Mixture Models does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Fault Classification in Cylinders Using Multilayer Perceptrons, Support Vector Machines and Guassian Mixture Models, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Fault Classification in Cylinders Using Multilayer Perceptrons, Support Vector Machines and Guassian Mixture Models will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-674364