苹果可溶性固形物便携式检测实验研究

发布时间：2018-05-24 18:10

本文选题：便携式 + 近红外光谱　；参考：《光谱学与光谱分析》2017年10期

【摘要】：为实现苹果可溶性固形物的便携式快速检测,搭建了以STS光谱仪和自制样品杯作为光谱检测装置的苹果可溶性固形物便携式检测平台。采用自行设计的检测平台采集了苹果的近红外漫反射光谱,对比分析了不同的光照角度、光源与探头距离对光谱响应特性的影响,建立了苹果可溶性固形物偏最小二乘模型(PLS)和最小二乘支持向量机模型(LS-SVM),采用连续投影算法及主成分分分析法对最小二乘支持向量机模型进行了优化,并对比分析了两种检测模型的优劣。其中当光源距探头距离为15mm光源角度为45°时,结合偏最小二乘法建立苹果的可溶性固形物定量检测模型精度最高。模型的预测集相关系数为0.924,预测均方根误差为0.334%。实验结果表明,采用四周照射、底部接收并结合避光圈的这种结构布置能够有效的克服杂散光现象并且提高了光谱中的有效信息。研究可为快速、便携的苹果可溶性固形物检测仪器的设计提供参考依据和理论支撑。
[Abstract]:In order to realize the portable and rapid detection of the soluble solids of apple, a portable detection platform for soluble solids of apple was set up with STS spectrometer and self-made sample cup as the spectral detection device. The near-infrared diffuse reflectance spectra of apple were collected by using the self-designed detection platform. The effects of different illumination angles, the distance between the light source and the probe on the spectral response characteristics were compared and analyzed. The partial least squares (PLS) and least squares support vector machine (LS-SVM) models of apple soluble solids were established. The model was optimized by continuous projection algorithm and principal analysis method. The advantages and disadvantages of the two detection models are compared and analyzed. When the distance from the light source to the probe is 45 掳for the 15mm light source, the accuracy of the quantitative detection model of soluble solids in apple is the highest with the partial least square method. The correlation coefficient of prediction set is 0.924, and the root mean square error of prediction is 0.334. The experimental results show that the structure arrangement with four directions, bottom receiving and avoiding ring can effectively overcome the stray light phenomenon and improve the effective information in the spectrum. The research can provide a reference and theoretical support for the design of a fast and portable apple soluble solids detection instrument.
【作者单位】：华东交通大学机电与车辆工程学院;
【基金】：国家高技术研究发展计划(863计划)项目(SS2012AA101306) 江西省杰出青年人才资助计划项目(20171BCB23060) 柑橘黄龙病拉曼结合高光谱快速诊断机理与方法(61640417) 江西省科技支撑计划项目(20121BBF60054) 南方山地果园智能化管理技术与装备协同创新中心(赣教高字[2014]60号) 江西省优势科技创新团队(20153BCB24002)资助
【分类号】：O657.33;TS255.2

【相似文献】