Classification for Damage Severity in Natural Fibre Composites Using Principal Component Analysis
AbstractThe present paper deals with an approach in predicting the classification of damage in natural fibre reinforced composites (NFC) panel using signal processing procedure as indicative parameters and principle component analysis as a learning tool. An impact event produced strain data and the response signal was investigated. An effective impact damage classification procedure is established using a principal component analysis approach. The system was trained to classify the damage class based on the input from the signal features. It has been observed that, the network can learn and classify effectively the damage size in the panel which is the combination features retained at about 84.5% of the variance.
Open access licenses
Open Access is by licensing the content with a Creative Commons (CC) license.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.