Milling Status Detection Based On Vibration Using Neural Network

• Main Authors: Phan Thanh Dat, 潘 達 強
• Other Authors: Shih-Hung Yang
• Format: Others
• Language: en_US
• Published: 2016
• Online Access: http://ndltd.ncl.edu.tw/handle/mkujrn

碩士 === 逢甲大學 === 機械與電腦輔助工程學系 === 104 === Milling Status Detection is a project to monitor condition of CNC machines with the help of Neural Network (NN). The use of NN has spread out in many field of modern life because of its ability in learning and solving prediction and classification problem. In this study, we want to use a NN to increase the efficiency of milling machine. A wireless sensing system was designed to collect the data from milling process as described in [8]. This system achieved the recognition rate of milling and idle detection up to 93%. 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 and Nondominated Sort Genetic Algorithm (NSGA – II) was used to optimize the NN topology including three parameters: number of tapped delay parameters, number of FFT coefficients and number of hidden neurons. A preferable recognition rate of 99.6% was achieved with the Genetic Algorithm implemented.