摘要
【目的】采用小波压缩结合遗传算法,优选脐橙糖度近红外光谱在线检测的建模变量,提高在线检测精度。【方法】利用近红外光谱检测装置采集脐橙样品的光谱,并将其转换为反射比光谱,在700.28～933.79nm波段,利用小波变换将一阶微分处理后的近红外反射比光谱变量压缩成小波系数变量。经遗传算法优选后,建立偏最小二乘法(PLS)模型,并对该模型的预测结果进行评价。【结果】利用小波压缩结合遗传算法优选变量建立的脐橙糖度PLS模型,预测效果最优,模型的相关系数为0.759,模型预测均方根误差为0.468°Brix。【结论】采用小波压缩结合遗传算法对变量进行优选,可提高脐橙糖度近红外光谱在线检测的精度。
【Objective】In order to improve the precision of detecting sugar content of navel orange by online near infrared（NIR） spectroscopy,wavelet transform and genetic algorithm were applied to select the NIR variables.【Method】Spectra was measured in near infraed diffuse reflectance mode using the dynamic spectra detecting system.In the wavelength range of 700.28-933.79 nm,the first derivative spectra were compressed into the variables of wavelet coefficient by wavelet transform（WT）.The partial least squares（PLS） models were developed with the variables selected by genetic algorithm（GA）.The prediction was used to evaluate the predictive ability of the models.【Result】By comparison the predictive performance of the PLS model for navel orange SSC that developed with the variables using WT and GA variables was the best.The correlation coefficient（r） of predictive mode was 0.759,and the root mean square error of prediction（RMSEP） was 0.468 °Brix.【Conclusion】The experiment showed that the precision for detecting sugar content of navel orange by WT,GA and online NIR technique was improved.
出处
《西北农林科技大学学报（自然科学版）》
CSCD
北大核心
2012年第1期215-220,共6页
Journal of Northwest A&F University(Natural Science Edition)
基金
国家自然科学基金项目(61178036)
科技部农业科技成果转化资金项目(2011GB2C500008)
江西省对外科技合作计划项目(2009BHB15200)
江西省主要学科学术和技术带头人培养对象计划项目(2009DD00700)
关键词
近红外光谱
小波压缩
遗传算法
在线检测
脐橙糖度
near infrared spectroscopy
wavelet transform compress
genetic algorithm
online detecting
sugar content of navel orange
