摘要
在机床加工中,刀具的振动往往给工件带来负面影响。因此,研究刀具振动趋势就显得尤为重要。振动信号预测可看作是时间序列预测,故在MATLAB中,采用BP和RBF神经网络分别建立了非线性预测模型对其进行预测。结果表明,RBF网络有更好的预测精度。
In the machine processing, cutter vibration usually have a negative effect on the workpiece. Therefore, the research on the trend of cutter vibration is particularly important. The forecast for vibration signals is consider as time -series forecasting. So The BP and RBF neural network were adopted to establish nonlinear models for predicting a time series. The results show that the RBF neural network has higher accuracy.
作者
牛雨生
NIU Yu-sheng (School of Mechanical Engineering&Automatization, North University of China, Taiyuan 030051, China)
出处
《电脑知识与技术》
2012年第2期939-941,共3页
Computer Knowledge and Technology