Milling status Detection Based on Vibration Using Neural Network
Thanh-Dat Phan†, Quoc-Manh Nguyen‡*
†Thai Nguyen University of Technology, Thai Nguyen city, Vietnam
‡Hung Yen University of Technology and Education, Hung Yen, Vietnam
Corresponding Author Email: firstname.lastname@example.org
This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
The use of Neural Network (NN) has spread out in many field of modern life because of its ability in learning and solving prediction and classification problem. In this research, we want to use a NN to defy whether the cutting tool of milling is actually working (i.e., milling) or not (i.e., idling) based on the vibration of 3 axes. Data harvested during experiments were analyzed, processed and used in batch learning (i.e., offline learning). Previous works showed the result of up to 93% classification. Our goal is to investigate the data and reach a higher performance. Therefore, the NN is adopted to recognize the milling status and is implemented by Matlab. Moreover, Genetic Algorithm was used to optimize the NN topology including three parameters: number of tapped delay parameters, number of Fast Fourier Transform (FFT) coefficients and number of hidden neurons. A preferable recognition rate of 99.6% was achieved.