摘要
针对接触式测量中众多影响因素与测头预行程误差变化之间的非线性映射关系,提出基于径向基函数神经网络的预行程误差预测新方法。对RBF神经网络结构进行改进并建立预测模型,从理论上证明该方法能克服预测过程中网络容易陷入局部极小的问题,并可满足预行程误差预测高精度、高速度的性能要求。
According to the nonlinear mapping relationship between many influencing factors and the pre-travel error of probe in contact measurement, a new pre-travel error prediction method based on the radial basis function neural network is proposed. Mathematical model is established in combination with structure improvement for RBF Neural Networks. It is proved theoretically that the method can o- vercome the limitation of local infinitesimal, and can meet the requirements for accurateness and speediness of pre-travel error prediction.
出处
《重庆理工大学学报（自然科学）》
CAS
2012年第10期16-18,24,共4页
Journal of Chongqing University of Technology：Natural Science
