基于传感器阵列优化的东北山参品质检测方法研究  

Study of Radix Ginseng Quality Detecting Method Based on Sensor Array Optimization

作　　者：赵格格[1] 俞瑜[1] 郑乐[1] 楼雄伟[1] 李剑[1] 惠国华[1] 

机构地区：[1]浙江农林大学信息工程学院,杭州311300

出　　处：《传感技术学报》2017年第5期789-794,共6页Chinese Journal of Sensors and Actuators

基　　金：浙江省公益技术研究项目(2017C31010)

摘　　要：研究了一种基于传感器阵列优化的储存山参品质检测方法。实验记录气体传感器阵列对山参样品的响应信号,采用传感器载荷分析的方法对传感器阵列响应信号进行优化。优化后传感器阵列主成分区分度提高了10.46%。优化后传感器阵列检测信号输入非线性数据共振模型,基于系统输出互相关系数COE(Cross Correlation Coefficient,)特征值经由线性拟合方法构建储存山参品质检测模型Q=(COE_(max)-0.23)/0.02(R^2=0.990 26)。验证实验结果表明所构建的模型的预报准确度为83.3%。所探索的方法有望在储存中药材品质检测领域得到广泛应用。Different from usual storage method, storage condition of Chinese medicine is specially installed. Tradi- tional Chinese medicine radix ginseng quality determination method using M.O.S sensor array optimization was stud- ied in this paper. Sensor array responses to ginseng samples under different storage time were measured. Sensor loading analysis results demonstrated that sensor array optimization improved principal component analysis （PCA） discrimination degree of ginseng samples in different quality. Non-linear stochastic resonance （SR） was utilized for optimized measurement data analysis. Cross correlation coefficient （ COE ） quantitatively discriminated all samples. Ginseng quality determination model Q = （ COEmax - 0.23 ）/0.02 （ R2 = 0.990 26 ） was developed by linear fitting regression of COEmax values. Validating experiments results indicated that the developed model presented a quality predicting accuracy of 83.3% for ginseng sample. The proposed method is promising in the Chinese medicine quality rapid detection.

关 键 词：山参 品质 传感器阵列 非线性 特征值 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]