摘要
为了提高pH试纸检测pH值的准确性,基于BP神经网络,设计了pH试纸自动检测系统。在相同环境对标准比色卡、显色pH试纸拍照,分别提取H、S、V三个分量作为BP神经网络的训练和测试数据,利用基于BP神经网络的检测算法在MATLAB环境下完成仿真并将结果与人工比色法的结果对比。对于普通pH试纸,最大误差是0.08.最小误差是0.01。对于精密pH试纸,最大误差是0.08,最小误差是0.02。基于BP神经网络的pH试纸自动检测系统不仅可精确检测pH值,且具有高效、稳定、自动化程度高等特点。
In order to improve the accuracy of pH value of pH test paper,an automatic detection system for pH test paper was designed,which based on BP neural network.In the same environment,the standard colorimetric card and the color-developed pH test paper were taken pictures,and the three components of H,S and V were extracted as the training and test data of BP neural network,and the simulation algorithm based on BP neural network was used to complete the simulation in MATLAB environment.The results were compared to the results of the artificial colorimetric method.For normal pH test strips,the maximum error is 0.08 and the minimum error is 0.01.For precision pH test strips,the maximum error is 0.08 and the minimum error is 0.02.The BP neural network-based pH test strip automatic detection system not only accurately detects the pH value,but also has the characteristics of high efficiency,stability,high degree of automation and so on.
作者
王震洲
李鑫圆
Wang Zhenzhou;Li Xinyuan(School of Information Science and Engineering,Hebei University of Science and Technology,Shijiazhuang 050018,China)
出处
《电子测量与仪器学报》
CSCD
北大核心
2019年第10期181-186,共6页
Journal of Electronic Measurement and Instrumentation
基金
河北省科技支撑计划(17210803D)
河北省教育厅青年基金(QN2018095)资助项目
