摘要
为了提高聚醚后处理的自动化程度、聚醚参数的精度和识别不同参数含量的聚醚,采用ARM为控制核心,Wincc组态软件为上位机,对聚醚的黏度、pH值、色度、水分参数等进行检测,并选取了5种不同参数含量的聚醚样品,分别采用主成分分析法和BP神经网络对聚醚样品进行模式识别。试验结果表明:采用主成分分析法的第一主成分和第二主成分的累积贡献率达90.235 2%,识别效果良好;而BP神经网络经过多次训练后,识别率达到100%。
In order to improve the degree of automation and the accuracy of polyether parameters and the identification of different parameters of poly,ARM was used as the control core,the Wincc configuration software was the host computer.The temperature,PH value,color,moisture content and so on were detected,five kinds of polyether samples with different parameters were selected,and the pattern recognition of polyether samples was performed by using principal component analysis and BP neural network respectively.The results show that the cumulative contribution rate of the first principal component and the seconed principal component of the principal component analysis method was 90.235 2%,and the recognition effect was good.And the recognition rate of BP neural network was 100% after several times of training.
出处
《仪表技术与传感器》
CSCD
北大核心
2017年第3期102-105,共4页
Instrument Technique and Sensor
基金
江苏省产学研项目(BY2016061-02)
关键词
聚醚后处理
ARM
WINCC
识别
主成分分析
BP神经网络
post treatment of polyether
ARM
Wincc
distinguish
principal component analysis
BP neural network
