论文部分内容阅读
为了实现羊绒、羊毛纤维的快速、无损检测,建立了羊绒、羊毛近红外光谱数据库,包括228组各地羊绒、羊毛数据,并应用于羊绒、羊毛的定性检测上。首先介绍了羊绒、羊毛近红外光谱检测的数据库建立过程;然后,在对羊绒、羊毛原始近红外光谱进行预处理的基础上,对数据进行主成分分析,选出12种主成分,并结合改进的RBF模糊神经网络,建立羊绒、羊毛检测模型。通过与主成分分析-马氏距离建模方法的对比分析实验表明,建立近红外光谱数据库,并结合主成分分析和改进的RBF模糊神经网络的方法是一种有效的无损检测羊绒、羊毛的方法,可快速建立高精度的羊绒、羊毛纤维检测模型。
In order to realize the rapid and non-destructive testing of cashmere and wool fiber, a near-infrared spectrum database of cashmere and wool was established, which included 228 sets of cashmere and wool data from all over the country and applied to the qualitative detection of cashmere and wool. Firstly, the establishment of the database of cashmere and wool near-infrared spectroscopy was introduced. Then, based on the preprocessing of raw near-infrared spectra of cashmere and wool, the principal component analysis (PCA) was performed on the data to select 12 principal components, RBF fuzzy neural network to establish cashmere and wool testing model. By comparing with the method of principal component analysis and Mahalanobis distance modeling, experiments show that the method of establishing near-infrared spectroscopy database, combining with principal component analysis and improved RBF fuzzy neural network is an effective non-destructive testing method of cashmere and wool , Can quickly establish high-precision cashmere, wool fiber testing model.