Tool wear prediction model based on wear influence factor

This study proposed a new method for predicting tool wear curve over machining time through abscissa stretching or compressing based on wear influence factor, which is a tool wear prediction method with universal potential and relatively simple modeling and use. In this method, firstly, the relationship model between the tool wear rate and the cutting parameters needs to be built, and the wear influence factor can be derived from this relationship model. Then, it needs to record the curve of the tool wear value over machining time under a certain cutting parameters through experiments. This curve is called the benchmark tool wear curve, and the wear influence factor under these cutting parameters is called the benchmark wear influence factor. When the cutting parameters change, it is only required to solve the ratio between the wear influence factor under current cutting parameters and the benchmark wear influence factor, then use the ratio to stretch or compress the benchmark tool wear curve in the direction of the abscissa, that is the tool wear prediction curve under current cutting parameters. In this study, the tool wear curve under cutting parameter V=55m/min,a_p=0.08mm/tooth is selected as the benchmark tool wear curve, and tool wear curves under cutting parameter V=80m/min, a_p=0.12mm/tooth, and V=40m/min,a_p=0.06mm/tooth are accurately predicted. In the cross validation after the replacement of the benchmark tool wear curve, the prediction model also shows good prediction accuracy. The comprehensive optimization model of disc milling based on the wear influence factor shows that increasing the cutting line speed and reducing the feed per tooth can improve the cutting efficiency and reduce tool wear.