Deep Neural Network Tool Chatter Model for Aluminum Surface Milling Using Acoustic Emmision Sensor

Abstract

Chatter is a self-excited vibration in any machining processes which contributes to the system instability due to resonance and resulting in an inaccuracy in machining product. Due to demand for a high precision product, industries are nowadays moving towards implementing a tool monitoring system as a feedback. Currently, an electromagnetic sensor was used to detect chatter in tools, but this sensor introduces a drawback such as bulky in size, sensitive to noise and not suitable to be implemented in the small machining center. This paper aims to propose a chatter identification model for face milling tool based on acoustic emission data for tool monitoring system. Acoustic emission data is collected at four level of cutting depth in milling with linear tool path movement on aluminum T6 6061 materials. the Deep Neural Network (DNN) model was developed using multiple deep-learning frameworks for the chatter detection system. This model approach shows a good agreement with experimental data with 4% error. As a conclusion, the DNN chatter identification model was successfully developed for the aluminum milling process applications. This finding is essential for anomaly detection during machining process and able to suggest for a better machining parameter for the aluminum machining process.