本文讨论了用人工神经网络对可转位刀片 3维断屑槽进行建模和预测的问题 ,提出了一种 3维槽型几何特征参数的提取方法 ,在此基础上建立了预测 3维断屑槽断屑范围的人工神经网络模型。试验结果表明 ,该模型的预测准确率达95 %以上 In this paper, the problem of modeling and predicting 3-D chip flutes of indexable inserts by using artificial neural networks is discussed. A 3-D geometry feature extraction method is proposed. On this basis, Artificial neural network model of chip fluff breaking range. The experimental results show that the prediction accuracy of the model is above 95%