端銑刀壽命預測技術之研發

• Main Author: 劉晉元
• Other Authors: 江佩如
• Format: Others
• Language: zh-TW
• Published: 2019
• Online Access: http://ndltd.ncl.edu.tw/handle/4xk2s7

碩士 === 國立中正大學 === 機械工程系研究所 === 107 === Nowadays, with the development of technology, the mechanical field is developing in the direction of automation. However, the timing of cutting tool replacement is still judged based on the experience of the on-site personnel. This way not only consumes labor costs, but also increases the processing costs. Thus, we proposed an automatic method to predict the life remaining of the cutting tool such that the efficiency of the manufacturing process can be improved. In this study, Gaussian process training was applied to construct the tool wear curve. Based the obtained wear curve, the remaining useful life of the on-site cutting tool can be predicted. The experimental results show that with proposed method, although the prediction errors are large at the beginning of the manufacturing process, the error can be reduced to 5%~10% when the flank wear reaches 0.3~0.4 mm. This method can also be applied to multiple different manufacturing conditions with the same accuracy.