摘要
本文通过红外光声光谱扫描,建立不同破损级别纸张的预测模型,以达到快速检测纸张破损程度的目的。研究发现不同破损级别的纸张有明显的聚类特点,利用概率神经网络建立纸张破损级别模型的预测准确率达到62%。未来在优化模型的同时,拟增加纸张各组分的定量研究,建立纸张破损程度与纸张物质变化的相关关系并达到实时监测的目的。
In this paper, the prediction model of paper with different breakage grades is established by infrared photoacoustic spectrum scanning, in order to quickly detect the degree of paper breakage. It was found that the paper with different damage levels had obvious clustering characteristics. The prediction accuracy of paper damage level model based on probabilistic neural network reached 62%. In the future, while optimizing the model, it is proposed to increase the quantitative study of paper components, establish the correlation between the degree of paper damage and the change of paper material, and achieve the purpose of real-time monitoring.
引文
[1]中华人民共和国文化部.古籍特藏破损定级标准:WH/T 22-2006[S].北京:北京出版社,2007.
[2]MCCARTY G W, REEVES J B, REEVES V B, et al.Mid-infrared and Near-infrared diffuse reflectance spectroscopy for soil carbon measurement[J]. Soil Science Society of America Journal, 2002,66(2):640-646.
[3]MCCARTY G W, REEVES J B. Comparison of near infrared and mid infrared diffuse reflectance spectroscopy for field-scale measurement of soil fertility parameters[J].Soil Science,2006,171(2):94-102.
[4]许禄,邵学广.化学计量学方法[M].2版.北京:科学出版社, 2004:130.
[5]苏亮,宋绪丁.基于Matlab的概率神经网络的实现及应用[J].计算机与现代化, 2011(11):47-50.
[6]侯刚健,赵军.浅析纸张的老化因素与高校图书馆应采取的措施[J].科技情报开发与经济2010,20(12):50-51.
[7]郭京波,陶宗娅,罗学刚.竹木质素的红外光谱与X射线光电子能谱分析[J].化学学报,2005,63(16):1536-1540.
[8]熊磊,于东伟.酸处理后纤维素分子结构的显微红外光谱分析[J].纤维素科学与技术,2013,21(2):59-62.
[9]张志清.文献纸张的自然老化及其研究[J].档案学研究,1998(2):60-61.