摘要
针对电火花线切割机床可靠性数据较少、传统可靠性预计方法无法进行可靠性预计或预计误差较大的问题,提出了基于神经网络进行电火花线切割机床可靠性预计的方法。将可靠度与对应的时间序列相结合,采用时间序列法对其进行统计分析,然后应用神经网络向外推测,从而得出电火花线切割机床可靠度的预计结果。通过实例证明,应用该方法对电火花线切割机床可靠度预计结果的最大误差为0.0082,远远高于其它方法的预计精度。
The reliability data of Wire Electrical Discharge Machining （WEDM） is so few that the reliability of WEDM can not be predicted by traditional reliability prediction method; or the reliability prediction error is large. A reliability prediction method of WEDM based on the neural network is proposed in this paper. The reliability is combined with the time series which is corresponding with the reliability, then it is analyzed by time series method; the reliability prediction result can be achieved by the extrapolation of the neural network. It is proved by the instance that the biggest error of reliability prediction is 0.0082; it is more accurate than the other prediction methods.
出处
《机械》
2009年第3期1-3,共3页
Machinery
基金
国家自然科学基金项目(50875021)
