Abstract
Laser metal deposition (LMD) is an advanced additive manufacturing (AM) process used to build or repair metal parts layer by layer for a range of different applications. Any presence of deposition defects in the part produced causes change in the mechanical properties and might cause failure to the part. Corrective remedies to fix these defects will increase the machining time and costs. In this work, a novel defects monitoring system was proposed to detect and classify defects in real time using an acoustic emission (AE) sensor and an unsupervised pattern recognition analysis (K-means clustering) in conjunction with a principal component analysis (PCA). A time domain and frequency domain relevant descriptors were used in the classification process to improve the characterization of the defects sources. The methodology was found to be efficient in distinguishing two types of signals that represent two kinds of defects, which are cracks and porosities. A cluster analysis of AE data is achieved and the resulting clusters correlated with the defects sources during laser metal deposition. It was found that cracks and pores that occur during LMD can be detected using an AE sensor. Pores produce acoustic emission events with high energy, shorter decay time, and less amplitude when compared to cracks. Specifically, the signal energy is a crucial feature in identifying the AE defect source mechanisms. The frequency is not significant; it has a little contribution to the classification solution.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have