用聚类分析和人工神经网络解析漆器漆膜裂解色谱图

Analyzing the Pyrolysis Gas Chromatogram of Lacquer Film on Lacquerware by the Use of Cluster Analysis and Artificial Neural Networks

摘要: 采用聚类分析法和变步长的误差反向传播人工神经网络方法，解析漆器漆膜的裂解色谱数据，获得了漆器漆膜隐含的年代信息。结果表明，本法为解析古代漆器漆膜年代信息提供了一条有效的新途径。

Abstract: The chromatograms obtained from lacquer film on lacquerware by using of py-rolysis gas chromatography were analyzed by the method of cluster analysis and error back-propagation algorithm of step change of artificial neural networks. The results obtainedproved that the method furnished an effective new way for determining the ages of the an-cient lacquer film on lacquerware.