中文摘要：

刀具使用寿命会直接影响刀具需求计划制定、刀具生产准备以及切削参数制定等。然而，由于刀具使用寿命的影响因素众多，目前虽然有多种刀具使用寿命的预测方法，但这些方法存在结果准确性不佳或对新材料新工艺无从入手等缺陷，均无法对刀具使用寿命进行有效快捷的准确预测。采用人工神经网络技术，针对反向传播算法存在收敛速度慢、容易陷入局部极小值、全局搜索能力弱等缺陷，采用蚁群优化算法（ACO）训练BP神经网络，建立了基于ACO-BP算法的铣刀寿命预测神经网络模型，在兼顾网络学习速度的同时保证了模型的全局搜索能力及鲁棒性。

英文摘要：

The tool useful life will directly affect the establishment of tools requirement plan, manufacturing preparation bag and the optimization of cutting parameters. Due to the poor accuracy of calculation result and the difficulty of calculation for new materials and new technologies, traditional methods are unable to carry out efficient and effective tool life prediction. Artificial neural network was introduced to predict the cutting tool life. In the prediction process, there were some disadvantages in the back propagation （BP） algorithm, such as low convergence speed, easily falling into local minimum point and weak global search capability. Therefore, the ant colony optimization （ACO） algorithm is used to train BP neural network and build the ACO-BP neural network-based prediction model of cutting tool life which satisfies the requirement of global search capability robustness for the model.