基于嵌入式系统的中药提取软测量方法研究
|
摘要
针对中药提取过程中软测量建模的计算机在线实现问题,将遗传算法(GA)和支持向量机(SVM)相结合,对葛根素在线提取过程进行软测量建模,并将该软测量模型固化到基于树莓派的嵌入式系统,构建了葛根素提取率的在线检测系统。该系统实现了下位机的在线实时温度数据采集、提取率计算、数据发送和结果三维显示,能完成上位机软件的软测量模型更新、数据存储、历史数据显示、数据包解析和三维坐标系显示提取效果等功能。与紫外分光光度计的离线检测方法相比较,本文方法得到平均相对误差为4.33%,具有实时性好、测量精度高、操作简便等优点。
A genetic algorithm(GA) and a support vector machine( SVM) have been combined to build a model of puerarin extraction in order to achieve on-line realization of the soft measurement modeling of Chinese medicine extraction. By combining a soft-measurement model and the embedded system of a Raspberry Pi,an on-line measurement system for the puerarin extraction ratio has successfully been established. The system comprises the functions of temperature data acquisition,extraction ratio calculation,data transmission and real-time three-dimensional display of the extraction result in the slave computer,with the functions of soft measurement model update,data storage,historical data display,packet analysis and three-dimensional coordinate system display of the extraction result in the host computer. An on-line measurement system of the puerarin extraction ratio has thus been implemented. Compared with a UV spectrophotometer off-line detection method,our method gives an average relative error of 4. 33%. Furthermore,our method has the advantages of good real-time characteristics,simple operation,and high precision.
A genetic algorithm(GA) and a support vector machine( SVM) have been combined to build a model of puerarin extraction in order to achieve on-line realization of the soft measurement modeling of Chinese medicine extraction. By combining a soft-measurement model and the embedded system of a Raspberry Pi,an on-line measurement system for the puerarin extraction ratio has successfully been established. The system comprises the functions of temperature data acquisition,extraction ratio calculation,data transmission and real-time three-dimensional display of the extraction result in the slave computer,with the functions of soft measurement model update,data storage,historical data display,packet analysis and three-dimensional coordinate system display of the extraction result in the host computer. An on-line measurement system of the puerarin extraction ratio has thus been implemented. Compared with a UV spectrophotometer off-line detection method,our method gives an average relative error of 4. 33%. Furthermore,our method has the advantages of good real-time characteristics,simple operation,and high precision.
引文
[1]徐芳芳,毕宇安,王振中,等.过程分析技术在中药注射剂生产过程中的应用研究进展[J].中草药,2016,47(14):2563-2567.XU F F,BI Y A,WANG Z Z,et al.Review on process analytical technology application in production process of Chinese medicine injection[J].Chinese Traditional&Herbal Drugs,2016,47(14):2563-2567.(in Chinese)
[2]乔宗良,张蕾,周建新,等.一种改进的CPSO-LSSVM软测量模型及其应用[J].仪器仪表学报,2014,35(1):234-240.QIAO Z L,ZHANG L,ZHOU J X,et al.Soft sensor modeling method based on improved CPSO-LSSVM and its applications[J].Chinese Journal of Scientific Instrument,2014,35(1):234-240.(in Chinese)
[3]阮宏镁,田学民,王平.基于联合互信息的动态软测量方法[J].化工学报,2014,65(11):4497-4502.RUAN H M,TIAN X M,WANG P.Dynamic soft sensor method based on joint mutual information[J].CIESC Journal,2014,65(11):4497-4502.(in Chinese)
[4]WU J Q,SUN Y K,HUANG Y H,et al.Soft sensor modeling based on GRNN for biological parameters of marine protease fermentation process[C]∥Proceedings of the 33rd Chinese Control Conference,Nanjing,2014:5102-5106.
[5]Wang J S,Han S.Feed-forward neural network soft-sensor modeling of flotation process based on particle swarm optimization and gravitational search algorithm[J/OL].Computational Intelligence and Neuroscience.(2015-10-25).http:∥dx.doi.org/10.1155/2015/147843.
[6]刘翠翠,郭为民,苏杰,等.基于PCA和支持向量机的电站入炉煤量软测量技术[J].自动化与仪器仪表,2015(10):213-214,218.LIU C C,GUO W M,SU J,et al.Soft sensing technology for power station boiler based on PCA and support vector machine[J].Automation&Instrumentation,2015(10):213-214,218.(in Chinese)
[7]李建强,赵凯,牛成林,等.基于GA-SVM的电站锅炉烟气含氧量软测量模型[J].热力发电,2017,46(4):63-69.LI J Q,ZHAO K,NIU C L,et al.GA-SVM-based softsensor model for oxygen content in flue gas of utility boilers[J].Thermal Power Generation,2017,46(4):63-69.(in Chinese)
[8]CHAYALAKSHMI C L,JANGAMSHETTI D S,SONOLI S.Design and development of an ARM platform based embedded system for measurement of boiler efficiency[C]∥2013IEEE Symposium on Industrial Electronics&Applications.Kuching,2014:39-43.
[9]张新胜.基于ARM的一次风流量软测量仪表研发[D].北京:华北电力大学,2016.ZHANG X S.Development of soft sensor instrument for primary air flow based in ARM[D].Beijing:North China Electric Power University,2016.(in Chinese)
[10]张庆洪.基于径向基神经网络的汽车油耗软测量及监测系统研究[D].长沙:湖南大学,2014.ZHANG Q H.Soft measurement and monitoring system of vehicle fuel consumption based on the RBF neural network[D].Changsha:Hunan University,2014.(in Chinese)
[11]ELSAYED S M,SARKER R A,ESSAM D L.A new genetic algorithm for solving optimization problems[J].Engineering Applications of Artificial Intelligence,2014,27(C):57-69.
[12]吴景龙,杨淑霞,刘承水.基于遗传算法优化参数的支持向量机短期负荷预测方法[J].中南大学学报(自然科学版),2009,40(1):180-184.WU J L,YANG S X,LIU C S.Parameter selection for support vectormachines based on genetic algorithms to short-term power load forecasting[J].Journal of Central South University(Science and Technology),2009,40(1):180-184.(in Chinese)
[13]马富涛,张建良,刘云彩.基于人工智能算法的高炉布料数值模拟[J].钢铁,2017,52(6):18-25.MA F T,ZHANG J L,LIU Y C.BF burden distribution numerical simulation based on genetic algorithm[J].Iron and Steel,2017,52(6):18-25.(in Chinese)
[14]黄文秀.粒子群优化算法的发展研究[J].软件,2014,35(4):73-77.HUANG W X.Research development of particle swarm optimization algorithm[J].Software,2014,35(4):73-77.(in Chinese)
[15]LI X Q,DING X,ZHANG Y,et al.Io T family robot based on Raspberry Pi[C]∥2016 International Conference on Information System and Artificial Intelligence.Hong Kong,2016:622-625.
[16]ZHANG X X,DANG Y Y,FU A Y.Design and research of intelligent remote control fan based on single chip microcomputer and bluetooth technology[C]∥2017 International Conference on Information Science and Technology.Wuhan,2017.
[2]乔宗良,张蕾,周建新,等.一种改进的CPSO-LSSVM软测量模型及其应用[J].仪器仪表学报,2014,35(1):234-240.QIAO Z L,ZHANG L,ZHOU J X,et al.Soft sensor modeling method based on improved CPSO-LSSVM and its applications[J].Chinese Journal of Scientific Instrument,2014,35(1):234-240.(in Chinese)
[3]阮宏镁,田学民,王平.基于联合互信息的动态软测量方法[J].化工学报,2014,65(11):4497-4502.RUAN H M,TIAN X M,WANG P.Dynamic soft sensor method based on joint mutual information[J].CIESC Journal,2014,65(11):4497-4502.(in Chinese)
[4]WU J Q,SUN Y K,HUANG Y H,et al.Soft sensor modeling based on GRNN for biological parameters of marine protease fermentation process[C]∥Proceedings of the 33rd Chinese Control Conference,Nanjing,2014:5102-5106.
[5]Wang J S,Han S.Feed-forward neural network soft-sensor modeling of flotation process based on particle swarm optimization and gravitational search algorithm[J/OL].Computational Intelligence and Neuroscience.(2015-10-25).http:∥dx.doi.org/10.1155/2015/147843.
[6]刘翠翠,郭为民,苏杰,等.基于PCA和支持向量机的电站入炉煤量软测量技术[J].自动化与仪器仪表,2015(10):213-214,218.LIU C C,GUO W M,SU J,et al.Soft sensing technology for power station boiler based on PCA and support vector machine[J].Automation&Instrumentation,2015(10):213-214,218.(in Chinese)
[7]李建强,赵凯,牛成林,等.基于GA-SVM的电站锅炉烟气含氧量软测量模型[J].热力发电,2017,46(4):63-69.LI J Q,ZHAO K,NIU C L,et al.GA-SVM-based softsensor model for oxygen content in flue gas of utility boilers[J].Thermal Power Generation,2017,46(4):63-69.(in Chinese)
[8]CHAYALAKSHMI C L,JANGAMSHETTI D S,SONOLI S.Design and development of an ARM platform based embedded system for measurement of boiler efficiency[C]∥2013IEEE Symposium on Industrial Electronics&Applications.Kuching,2014:39-43.
[9]张新胜.基于ARM的一次风流量软测量仪表研发[D].北京:华北电力大学,2016.ZHANG X S.Development of soft sensor instrument for primary air flow based in ARM[D].Beijing:North China Electric Power University,2016.(in Chinese)
[10]张庆洪.基于径向基神经网络的汽车油耗软测量及监测系统研究[D].长沙:湖南大学,2014.ZHANG Q H.Soft measurement and monitoring system of vehicle fuel consumption based on the RBF neural network[D].Changsha:Hunan University,2014.(in Chinese)
[11]ELSAYED S M,SARKER R A,ESSAM D L.A new genetic algorithm for solving optimization problems[J].Engineering Applications of Artificial Intelligence,2014,27(C):57-69.
[12]吴景龙,杨淑霞,刘承水.基于遗传算法优化参数的支持向量机短期负荷预测方法[J].中南大学学报(自然科学版),2009,40(1):180-184.WU J L,YANG S X,LIU C S.Parameter selection for support vectormachines based on genetic algorithms to short-term power load forecasting[J].Journal of Central South University(Science and Technology),2009,40(1):180-184.(in Chinese)
[13]马富涛,张建良,刘云彩.基于人工智能算法的高炉布料数值模拟[J].钢铁,2017,52(6):18-25.MA F T,ZHANG J L,LIU Y C.BF burden distribution numerical simulation based on genetic algorithm[J].Iron and Steel,2017,52(6):18-25.(in Chinese)
[14]黄文秀.粒子群优化算法的发展研究[J].软件,2014,35(4):73-77.HUANG W X.Research development of particle swarm optimization algorithm[J].Software,2014,35(4):73-77.(in Chinese)
[15]LI X Q,DING X,ZHANG Y,et al.Io T family robot based on Raspberry Pi[C]∥2016 International Conference on Information System and Artificial Intelligence.Hong Kong,2016:622-625.
[16]ZHANG X X,DANG Y Y,FU A Y.Design and research of intelligent remote control fan based on single chip microcomputer and bluetooth technology[C]∥2017 International Conference on Information Science and Technology.Wuhan,2017.