基于进化神经网络的刀具寿命预测  

Prediction of cutting tool life based on evolutionary neural network

作　　者：徐玲[1] 杨丹[1] 王时龙[2] 聂建林[3] 

机构地区：[1]重庆大学计算机学院,重庆400030 [2]重庆大学软件学院,重庆400030 [3]重庆大学机械工程学院,重庆400030

出　　处：《计算机集成制造系统》2008年第1期167-171,182,共6页Computer Integrated Manufacturing Systems

基　　金：重庆市自然科学基金资助项目(8483);重庆市信息产业局发展资金资助项目(200501016)~~

摘　　要：为预测道具寿命,引入人工神经网络技术,建立了刀具寿命预测神经网络模型,同时对切削参数进行优化选择。在刀具寿命预测中,针对反向传播算法存在收敛速度慢、容易陷入局部极小值及全局搜索能力弱等缺陷,采用遗传算法训练反向传播神经网络,设计了进化神经网络的学习算法。实验和仿真结果表明:基于进化计算的反向传播神经网络可以克服单纯使用反向传播网络易陷入局部极小值等难题,刀具寿命的预测精度较高,从而为刀具需求计划制定、刀具成本核算,以及切削参数制定提供理论依据,节约了制造执行系统中的生产成本。Artificial neural network was introduced to predict cutting tool life, and neural network-based prediction model of cutting tool life as well as the optimizing selection of machining parameters were proposed. In the prediction process, there were some disadvantages in Back Propagation （BP） algorithm, such as low convergence speed, easily falling into local minimum point and weak global search capability. To settle these problems, a genetic algo- rithm was used to train BP neural network to replace classical learning algorithms. An evolutionary neural network learning algorithm was developed. Results of simulations and experiments showed that the evolutionary neural network based on genetic algorithm could effectively overcome the shortcoming of falling into local minimum point. This method could obtain higher prediction accuracy. As a result, it provided theoretical basis for the establishment of cutting tool requirements planning, the account of its cost and the selection of machining parameters, as well as reduced the cost in Manufacturing Execution System （MES）.

关 键 词：进化神经网络 遗传算法 刀具寿命 切削参数优化 

分 类 号：TH162[机械工程—机械制造及自动化]