基于小波包神经网络的食品中锌、铁、锰元素电化学同时检测方法研究  

Electroanalytical Chemistry Method for Determination of Trace Elements in Food Based on Assistant Wavelet Neural Networks

作　　者：殷勇[1] 陈朝魁[2] 易军鹏[1] 

机构地区：[1]河南科技大学,河南洛阳471003 [2]洛阳师范学院,河南洛阳471022

出　　处：《食品科学》2008年第6期342-345,共4页Food Science

基　　金：河南省科技攻关计划项目(0324010008)

摘　　要：为了实现食品中锌、铁、锰微量元素的同时检测,深入研究了差分脉冲阴极溶出伏安(DPCSV)法的测试条件。运用小波包对测试数据分解,提取了不同信号频率带内的能量值作为测试数据的特征信息。将这种特征信息训练BP神经网络,建立了3种微量元素同时测量的检测模型。实际样品检测结果表明,该检测方法抗干扰能力强、测试准确、快捷,具有实际应用价值。A multivariate calibration method was used for the data analysis of trace dements determination, which is based on the combination of wavelet packet decomposition and neural network. Firstly, the differential pulse cathodic stripping voltammetry （DPCSV） signal was decomposed by wavelet packet, and the eigenvector was extracted based on the power features which are distributed in different frequency bands. Then a three layers BP network was used for training the features. The forecast results and calculated results of samples showed that the method has strong anti-jamming capability, high measure accuracy and practical values.

关 键 词：小波包分析 人工神经网络 电化学 检测 微量元素 

分 类 号：TS207.5[轻工技术与工程—食品科学] TP183[轻工技术与工程—食品科学与工程]