神经网络在超声-电火花复合加工参数预测中的应用

超声-电火花复合加工参数的选择及合理搭配对加工方法的应用、生产率的提高和工具电极的损耗都极其重要，是稳定高效加工进行的前提和保证。通过分析复合加工的主要影响因素，建立了基于BP人工神经网络的超声电火花加工工艺参数优化系统和相应的数据库系统。在给定条件下，系统得到的加工参数更加趋于合理，复合加工系统的总体性能得到提高，克服了传统单纯依赖于工艺数据库的参数选取系统的局限性。试验结果与预测结果有较好的一致性，表明了该系统可为超声电火花加工提供合理可靠的加工方案，系统更加便于用户操作。

Application of Artificial Neural Network for the Parameters predicted for Ultrasonic Vibration Assisted Electro-discharge Machining

The study of parameters predicted system for ultrasonic vibration assisted electro-discharge machining(UEDM) is necessary and important for the practical application,the improvement of machining efficiency and minimizing the tool wear ratio(TWR).In this paper,the model and the corresponding database are built for UEDM based on the back propagation algorithm artificial neural network(ANN) to optimize machining parameters,which realizes the intelligent predicted of machining parameters.As shown by the experiment results,the predictions are in accord with the test results,which shows that the reasonable and reliable plan of UEDM can be provided by the system.