Classification of Acoustic Emission Signals Collected During Mode I Delamination on Glass/Polyester Composites by Integration of the Principal Component Analysis and Fuzzy Clustering Means

Document Type : Original Article

Authors

• jahan Taghizadeh
• mehdi Ahmadi Nadjafabadi

10.22067/fum-mech.v22i2.10609

Abstract

Acoustic emission (AE) can be use to discriminate the different types of damage occurring in a constrained composite. However, the main problem associated with data analysis is the discrimination between the different acoustic emission sources. The objective of the cluster analysis is to separate a set of data into several classes that reflect the internal structure of the data. Indeed, cluster analysis is an important tool for investigating and interpreting data. In this paper, we intend to use two kinds of classifier techniques: a mathematical procedure that is called principal component analysis (PCA) and an unsupervised one fuzzy clustering means (FCM). Glass/polyester composites specimens used for the validation of the proposed methodologies. We worked on glass/polyester unidirectional specimens, subjected to duration of Mode I delamination within different configurations, awaiting preferential damage modes in the material.

---