Chatter Detection in Milling With Acoustic Emissions and Deep Learning

Abstract

One of the main pillars of Industry 4.0 is the use of Machine Learning algorithms to make accurate predictions of the manufacturing environment in order to make informed decisions. Deep Learning algorithm, which is a subfield of machine learning, has been widely used and proven more effective than other classic computational intelligence methods in many fields such as aviation-aerospace, automotive, health, and finance. Deep learning algorithms, which lead to revolutionary new products and applications in these sectors, have also been gaining attention in the field of machining to make machine tools more intelligent to improve manufacturing efficiency. In this study, Convolutional Neural Networks (CNN) which is an architecture of deep learning has been implemented to detect chatter in a slot milling process. Chatter is vibrational phenomena and has severe effects on machining performance. The undesirable vibrations caused by chatter, may cause lower surface qualities and even tool breakages. Since chatter lowers the performance of the machining operations, it is very crucial to detect and take timely action. In this research, an acoustic emission (AE) sensor was mounted to the milling machine and collects acoustic emissions. Captured data was used for training and testing by the estimation model in order to detect chatter.