期刊名称：Canadian Journal on Artificail Intelligence, Machin Learning and Pattern Recognition
出版年度：2010
卷号：1
期号：2
页码：7-25
出版社：AM Publishers Corporation Canada
摘要：This paper develops an artificial neural network (ANN) model to determine tool wear parameters such as average principal flank wear, average auxiliary flank wear, average maximum flank wear and average surface roughness as a function of cutting speed, feed rate, depth of cut and machining time. The model selects a feed-forward back-propagation ANN with twenty five hidden neurons as the optimum network. We test the model with marching data from a real field. The results show that the model can be useful to forecast tool wear and surface roughness in response to the model parameters under minimum quantity lubrication (MQL) environment.
