摘要
为了提高制浆过程中的在线预测纸浆卡伯值的精度,提出采用径向基函数网络来建立纸浆卡伯值近红外光谱法在线测量模型。结果表明,这种算法由于既考虑到了近红外光谱响应的非线性因素,又可防止BP网络在建模时出现训练速度慢、容易陷入局部最小和“过拟合”的现象,利用这种网络建立的纸浆卡伯值测量模型与一元回归、多元回归、主成分回归等线性方法和BP算法相比,具有更高的预测精度。
The radial basis function network is proposed to use in the determination of pulp kappa number with near-infrared spectroscopy in order to increase precision of kappa number determination. The results proved that precision of kappa number prediction was enhanced with the use of the radial basis function network as compared with linear algorithms such as principal component regression, muhivariable linear regression and nonlinear algorithms such as BP algorithm.
出处
《计算机与应用化学》
CAS
CSCD
北大核心
2006年第10期952-954,共3页
Computers and Applied Chemistry
基金
国家自然科学基金(30170756
30471365)
山东省中青年科学家奖励基金(048505005)
