摘要
为建立一种快速无损的快递塑料包裹袋检验的分析方法,利用红外光谱对57个快递塑料包裹袋样品进行检验。结合主成分分析法对数据降维;通过聚类分析法将样品分类;利用多层感知机模型进行分析和验证;构建决策树模型进行分类和预测。结果表明,57个快递塑料包裹袋在人工神经网络的训练集和测试集中正确率均达到100%,利用决策树在相同的训练集和测试集中正确率分别达到90.62%和90%。该方法方便快捷,对样品无损且用量少,可以为快递塑料包裹袋的分类提供有力的支持。
In order to establish a fast and non-destructive analysis method for the inspection of express plastic wrapping bags,57 express plastic wrapping bags samples were tested by infrared spectroscopy.Combined with principal component analysis,the data dimension reduction was reduced.Samples were classified through cluster analysis.Multi-layer perceptron model was used to analyze and verify,and a decision tree model was built for classification and prediction.The results show that the accuracy rate of 57 express plastic wrap bags in the training set and test set of the artificial neural network has reached 100%,and the accuracy rate of the training set and test set of the decision tree reaches 90.62%and 90%,respectively.This method is convenient and fast,lossless for samples and small dosage,and can provide strong support for the classification of express plastic wrapping bags.
作者
周飞翔
姜红
胡晓光
陈敏璠
莫修浩
ZHOU Feixiang;JIANG Hong;HU Xiaoguang;CHEN Minfan;MO Xiuhao(Detective College,People s Public Security University of China,Beijing 100038,China;Criminal Investigation Department,Gansu Police Vocational College,Lanzhou 730046,China;Beijing Jianzhi Technology Company Limited,Beijing 100038,China)
出处
《塑料工业》
CAS
CSCD
北大核心
2023年第6期110-114,共5页
China Plastics Industry
基金
中国人民公安大学2021年度基科费重点项目(2021JKF212)。
关键词
快递塑料包裹袋
红外光谱
化学计量学
Express Plastic Packaging Bags
Infrared Spectroscopy
Chemometrics
作者简介
周飞翔,男,2000年生,硕士研究生,专业方向为人工智能。626623269@qq.com;通信作者:姜红,女,1963年生,教授,硕士生导师,研究方向为理化物证检验。jiangh2001@163.com。
