高等学校化学学报 ›› 1997, Vol. 18 ›› Issue (5): 696.

• 论文 • 上一篇    下一篇

模式识别用于压电晶体传感器阵列识别可燃物质

邢婉丽, 方艳红, 何锡文   

  1. 南开大学化学系, 天津, 300071
  • 收稿日期:1996-04-01 出版日期:1997-05-24 发布日期:1997-05-24
  • 通讯作者: 何锡文
  • 作者简介:邢婉丽, 女, 28岁, 博士研究生.
  • 基金资助:

    国家自然科学基金

Detection of Combustible Material with Piezoelectric Crystal Sensor Array Using Pattern-Recognition Techniques

XING Wan-Li, FANG Yan-Hong, HE Xi-Wen   

  1. Department of Chemistry, Nankai University, Tianjin, 300071
  • Received:1996-04-01 Online:1997-05-24 Published:1997-05-24

摘要: 用7个压电晶体组成传感器阵列,每个晶体上分别涂有不同种类的气相色谱固定液,通过测定各种可燃物质燃烧时放出的混合气体来识别所燃物质,在识别中分别应用了人工神经网络法(ANN)和逐步判别分析法(SDA).讨论了解决神经网络开始训练时不收敛或产生麻痹现象的方法,提出了训练数据选取的新方法─—训练集逐步扩展法.实验证明:人工神经网络对被测物质的识别准确率达100%,高于逐步判别分析法(83%).

关键词: 人工神经网络, 压电晶体传感器阵列, 逐步判别分析

Abstract: Agas sensors array with seven piezoelectric crystals each coated with a different partially selective coating material was constructed to identify four kinds of combustible material which generate smoke contammg different components.The signals from the sensors were analyzed with both conventional multivariate analysis, stepwise discriminant analysis (SDA), and artificial neural networks (ANN).The results show that the predictions were even better with ANNmodels.In our experiment, we have reported a new method for training data selection," stepwise expanding training set method" to solve the problem that the network can not converge at the beginning of training.

Key words: Artificial neural networks (ANN), Piezoelectric crystal sensor array, Stepwise discriminant analysis(SDA)

TrendMD: