中药多糖醇沉过程自动控制系统
|
摘要
以中药麦冬溶液为研究对象,去除药液中多余糖分为目标,针对中药多糖醇沉过程中的强非线性问题,采用基于径向基神经网络的预测方法。引入遗传算法作为负反馈回路,实现对多糖醇沉过程中pH值的控制。设定期望的p H值,由遗传算法计算得到乙醇和碱液量的最优值并通过串口发送给STM32单片机。单片机分别控制蠕动泵和离心泵输送碱液和乙醇,其中,碱液为开环控制,乙醇为闭环控制并采用PID算法。最终,通过控制乙醇和碱液添加量实现了系统对p H值的控制。实验结果验证了控制系统对解决中药溶液多糖析出过程的pH值控制问题稳定、有效。
For the strongly nonlinear problems in the polysaccharide alcohol precipitation process of traditional Chinese medicine,the prediction algorithm based on radial basis function( RBF) neural network was employed to remove redundant sugar in the liquid medicine. The ophiopogon japonicas solution was the research object. The genetic algorithm was introduced as a negative feedback loop to realize the control of p H value in polysaccharide alcohol precipitation process. An expected pH was given,the optimal values of the ethanol and alkali liquor were calculated by the genetic algorithm,and were sent to the STM32 single chip microcomputer through the serial port. The single chip microcomputer controlled the peristaltic pump and the centrifugal pump respectively to transport the alkali liquor and ethanol,where the open-loop control was adopted for alkali liquor,and closed-loop control was adopted for ethanol by PID algorithm. Finally, the system controlled pH value by additive amount of ethanol and alkali liquor. The experimental results verified the stability and validity of the system for the pH value prediction in polysaccharide precipitation process of traditional Chinese medicine solution.
For the strongly nonlinear problems in the polysaccharide alcohol precipitation process of traditional Chinese medicine,the prediction algorithm based on radial basis function( RBF) neural network was employed to remove redundant sugar in the liquid medicine. The ophiopogon japonicas solution was the research object. The genetic algorithm was introduced as a negative feedback loop to realize the control of p H value in polysaccharide alcohol precipitation process. An expected pH was given,the optimal values of the ethanol and alkali liquor were calculated by the genetic algorithm,and were sent to the STM32 single chip microcomputer through the serial port. The single chip microcomputer controlled the peristaltic pump and the centrifugal pump respectively to transport the alkali liquor and ethanol,where the open-loop control was adopted for alkali liquor,and closed-loop control was adopted for ethanol by PID algorithm. Finally, the system controlled pH value by additive amount of ethanol and alkali liquor. The experimental results verified the stability and validity of the system for the pH value prediction in polysaccharide precipitation process of traditional Chinese medicine solution.
引文
[1] Duan Hongjun,Li Qingwei. Integral feedback compensation control of Chinese medicine sugar precipitation[C]//Proceeding of the 11th World Congress on Intelligent Control, and Automation. China:Shenyang,IEEE,2014:3792-3795.
[2] Xiong Zhihua,Zhang Jie. Neural network model-based on-line reoptimisation control of fed-batch processes using a modified iterative dynamic programming algorithm[J]. Chemical Engineering and Processing Process Intensification,2005,44(4):477-484.
[3] Han Runping,Wang Yi,Zou Weihua,et al. Comparison of linear and nonlinear analysis in estimating the Thomas model parameters for methylene blue adsorption onto natural zeolite in fixed-bed column[J]. Journal of Hazardous Materials,2007,145(1):331-335.
[4] Liu Yande,Sun Xudong,Zhou Jianmin,et al. Linear and nonlinear multivariate regressions for determination sugar content of intact Gannan navel orange by Vis-NIR diffuse reflectance spectroscopy[J]. Mathematical and Computer Modelling,2010,51(11):1438-1443.
[5] Duan Hongjun,Ma Zhenhe,Zhu Shurong,et al. Modeling and optimization of polysaccharide precipitation of traditional Chinese medicine injection[J]. Int J Mach Learn&Cyber,2018,9(6):893-902.
[6] Duan Hongjun,Ma Zhenhe,Zhu Shurong,et al. Modeling method of polysaccharide precipitation of Traditional Chinese medicine injection[C]//The 7th IEEE International Conference on Awareness Science and Technology. China:Qinhuangdao,IEEE,2015:955-1000.
[7] Duan Hongjun,Ma Zhenhe,Zhu Shurong,et al. Experimental research on polysaccharide precipitation in Ophiopogonis japonicus liquid[C]//The 7th IEEE International Conference on Awareness Science and Technology,China:Qinhuangdao,IEEE,2015:1025-1030.
[8] Duan Hongjun, Ma Zhenhe, Zhu Shurong. Variable Structure Control of Polysaccharide Precipitation in Chinese Medicine Solution Based on Recurrent CMAC[C]//2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics. China:Hangzhou,IEEE,2015:62-65.
[9] Li Qingwei,Duan Hongjun. Model predictive control of a Chinese medicine sugar precipitation process[C]//Proceeding of the 11th World Congress on Intelligent Control, and Automation. China:Shenyang,IEEE,2014:4850-4853.
[10] Kara Yakup,Acar Boyacioglu,Melek,et al. Predicting direction of stock price index movement using artificial neural networks and support vector machines:The sample of the Istanbul Stock Exchange[J]. Expert Systems with Applications,2011,38(5):5311-5319.
[11] Wu Sung Choi. A multi-industry bankruptcy prediction model using back-propagation neural network and multivariate discriminant analysis[J]. Expert Systems with Applications,2013,40(8):2941-2946.
[12] Han Honggui,Chen Qili Qiao Junfei. An efficient self-organizing RBF neural network for water quality prediction[J]. Neural Networks the Official Journal of the International Neural Network Society,2011,24(7):717-725.
[13] Benghanem Mohamed,Mellit Adel. Radial Basis Function Networkbased prediction of global solar radiation data:Application for sizing of a stand-alone photovoltaic system at Al-Madinah,Saudi Arabia[J]. Energy,2010,35(9):3751-3762.
[14]王长清,余丙涛,潘德强.基于STM32的逐阳帆控制系统设计[J].电子技术应用,2015,41(12):25-27,31.
[15]褚衍贺,陈洪建,商艳兰. RBF神经网络在变速箱齿轮故障诊断中的应用[J].微型机与应用,2010,29(17):94-97.
[16]邵永.中药溶液糖析出建模与参数优化方法研究[D].秦皇岛:东北大学秦皇岛分校,2016.
[2] Xiong Zhihua,Zhang Jie. Neural network model-based on-line reoptimisation control of fed-batch processes using a modified iterative dynamic programming algorithm[J]. Chemical Engineering and Processing Process Intensification,2005,44(4):477-484.
[3] Han Runping,Wang Yi,Zou Weihua,et al. Comparison of linear and nonlinear analysis in estimating the Thomas model parameters for methylene blue adsorption onto natural zeolite in fixed-bed column[J]. Journal of Hazardous Materials,2007,145(1):331-335.
[4] Liu Yande,Sun Xudong,Zhou Jianmin,et al. Linear and nonlinear multivariate regressions for determination sugar content of intact Gannan navel orange by Vis-NIR diffuse reflectance spectroscopy[J]. Mathematical and Computer Modelling,2010,51(11):1438-1443.
[5] Duan Hongjun,Ma Zhenhe,Zhu Shurong,et al. Modeling and optimization of polysaccharide precipitation of traditional Chinese medicine injection[J]. Int J Mach Learn&Cyber,2018,9(6):893-902.
[6] Duan Hongjun,Ma Zhenhe,Zhu Shurong,et al. Modeling method of polysaccharide precipitation of Traditional Chinese medicine injection[C]//The 7th IEEE International Conference on Awareness Science and Technology. China:Qinhuangdao,IEEE,2015:955-1000.
[7] Duan Hongjun,Ma Zhenhe,Zhu Shurong,et al. Experimental research on polysaccharide precipitation in Ophiopogonis japonicus liquid[C]//The 7th IEEE International Conference on Awareness Science and Technology,China:Qinhuangdao,IEEE,2015:1025-1030.
[8] Duan Hongjun, Ma Zhenhe, Zhu Shurong. Variable Structure Control of Polysaccharide Precipitation in Chinese Medicine Solution Based on Recurrent CMAC[C]//2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics. China:Hangzhou,IEEE,2015:62-65.
[9] Li Qingwei,Duan Hongjun. Model predictive control of a Chinese medicine sugar precipitation process[C]//Proceeding of the 11th World Congress on Intelligent Control, and Automation. China:Shenyang,IEEE,2014:4850-4853.
[10] Kara Yakup,Acar Boyacioglu,Melek,et al. Predicting direction of stock price index movement using artificial neural networks and support vector machines:The sample of the Istanbul Stock Exchange[J]. Expert Systems with Applications,2011,38(5):5311-5319.
[11] Wu Sung Choi. A multi-industry bankruptcy prediction model using back-propagation neural network and multivariate discriminant analysis[J]. Expert Systems with Applications,2013,40(8):2941-2946.
[12] Han Honggui,Chen Qili Qiao Junfei. An efficient self-organizing RBF neural network for water quality prediction[J]. Neural Networks the Official Journal of the International Neural Network Society,2011,24(7):717-725.
[13] Benghanem Mohamed,Mellit Adel. Radial Basis Function Networkbased prediction of global solar radiation data:Application for sizing of a stand-alone photovoltaic system at Al-Madinah,Saudi Arabia[J]. Energy,2010,35(9):3751-3762.
[14]王长清,余丙涛,潘德强.基于STM32的逐阳帆控制系统设计[J].电子技术应用,2015,41(12):25-27,31.
[15]褚衍贺,陈洪建,商艳兰. RBF神经网络在变速箱齿轮故障诊断中的应用[J].微型机与应用,2010,29(17):94-97.
[16]邵永.中药溶液糖析出建模与参数优化方法研究[D].秦皇岛:东北大学秦皇岛分校,2016.