BP神经网络预测控制在色素得率的应用
|
摘要
根据葡萄皮色素提取工艺过程中的提取剂浓度、温度、pH、时间等影响因素与输出结果色素提取率这一变量之间的非线性关系,建立了改进的BP神经网络预测模型。针对传统BP学习算法收敛速度慢、存在局部极值等不足,引入动量项以改进该学习算法。结合实际数据,运用迭代优化的控制算法对网络的权值和阈值进行不断训练并利用MATLAB进行仿真验证。研究结果证明了改进后的BP神经网络对色素提取率的预测控制具有精度高、泛化能力强,实用性强的优点,为色素得率提供了良好的理论基础和预测方法。
According to the nonlinear relationship between influencing factors including extracting agent concentration,temperature,pH and time In the extraction process of grape skin pigment and the outputs pigment extraction yield,the improved BP neural network prediction model is established.The traditional BP learning algorithm exists the deficiencies of a slow convergence speed and local extremum,momentum term is introduced to improve learning algorithm.The weights and thresholds of the network are trained、simulated and verified by MATLAB continually using iterative optimization control algorithm on the actual datas.The improved BP neural network has the advantages of high precision,strong generalization ability and strong practicability for pigment extraction yield prediction control,providing agood theoretical basis and prediction method for pigment yield.
According to the nonlinear relationship between influencing factors including extracting agent concentration,temperature,pH and time In the extraction process of grape skin pigment and the outputs pigment extraction yield,the improved BP neural network prediction model is established.The traditional BP learning algorithm exists the deficiencies of a slow convergence speed and local extremum,momentum term is introduced to improve learning algorithm.The weights and thresholds of the network are trained、simulated and verified by MATLAB continually using iterative optimization control algorithm on the actual datas.The improved BP neural network has the advantages of high precision,strong generalization ability and strong practicability for pigment extraction yield prediction control,providing agood theoretical basis and prediction method for pigment yield.
引文
[1]肖正春,张广伦.我国植物食用色素资源开发利用评价[J].中国野生植物资源,2014,33(1):45-54.
[2]李艳平,马西平.葡萄皮色素提取工艺研究[J].中国南方果树,2010,39(6):57-58.
[3]赵珍珍.红肉火龙果色素提取工艺优化及其化学成份分析[D].福州:福建农林大学,2012.
[4]罗漩,李颖,邓艳芹.响应面法提取葡萄皮色素及其稳定性的研究[J].中国调味品,2015,40(2):104-113.
[5]刘春,马颖.遗传算法和神经网络结合的PSD非线性校正[J].电子测量与仪器报,2015,29(8):1157-1163.
[6]杨国强.基于模糊自适应控制的锅炉温度控制[J].轻工机械,2013,31(2):52-55.
[7]丁硕,常晓恒.LM算法改进的BP网络在模式分类中的应用研究[J].电子测试,2014(2):33-35.
[8]宋志杰,王健.模糊聚类和LM算法改进BP神经网络的变压器故障诊断[J].高压电器,2013,49(5):54-58.
[9]程换新,伊飞.面向轻汽油醚化的BP神经网络的预测模型控制[J].石油化工自动化,2012,48(6):40-41.
[10]傅荟璇,赵红.MATLAB神经网络应用设计[M].北京:机械工业出版社,2010.
[11]朱江淼,宋文峰,高源,等.基于改进型BP神经网络的氢原子钟钟差预测[J].仪器仪表学报,2016,37(2):454-460.
[12]程换新,于沙家.面向脱硫系统的BP神经网络的预测控制[J].石油化工自动化,2015,51(5):39-42.
[13]余发山,康洪.基于GA优化BP神经网络的液压钻机故障诊断[J].电子测量技术,2016,39(2):134-137.
[14]余昆,杨文娇,陈玲.响应面分析法优化葡萄皮色素提取工艺[J].中外葡萄与葡萄酒,2013(2):27-31.
[15]杨新河,李勤,黄建安,等.普洱茶色素提取工艺条件的响应面分析及其抗氧化性活性研究[J]食品科学,2011,32(6):1-5.
[16]夏玫,陈立潮.BP神经网络泛化能力改进研究[D].太原:太原科技大学,2009.
[2]李艳平,马西平.葡萄皮色素提取工艺研究[J].中国南方果树,2010,39(6):57-58.
[3]赵珍珍.红肉火龙果色素提取工艺优化及其化学成份分析[D].福州:福建农林大学,2012.
[4]罗漩,李颖,邓艳芹.响应面法提取葡萄皮色素及其稳定性的研究[J].中国调味品,2015,40(2):104-113.
[5]刘春,马颖.遗传算法和神经网络结合的PSD非线性校正[J].电子测量与仪器报,2015,29(8):1157-1163.
[6]杨国强.基于模糊自适应控制的锅炉温度控制[J].轻工机械,2013,31(2):52-55.
[7]丁硕,常晓恒.LM算法改进的BP网络在模式分类中的应用研究[J].电子测试,2014(2):33-35.
[8]宋志杰,王健.模糊聚类和LM算法改进BP神经网络的变压器故障诊断[J].高压电器,2013,49(5):54-58.
[9]程换新,伊飞.面向轻汽油醚化的BP神经网络的预测模型控制[J].石油化工自动化,2012,48(6):40-41.
[10]傅荟璇,赵红.MATLAB神经网络应用设计[M].北京:机械工业出版社,2010.
[11]朱江淼,宋文峰,高源,等.基于改进型BP神经网络的氢原子钟钟差预测[J].仪器仪表学报,2016,37(2):454-460.
[12]程换新,于沙家.面向脱硫系统的BP神经网络的预测控制[J].石油化工自动化,2015,51(5):39-42.
[13]余发山,康洪.基于GA优化BP神经网络的液压钻机故障诊断[J].电子测量技术,2016,39(2):134-137.
[14]余昆,杨文娇,陈玲.响应面分析法优化葡萄皮色素提取工艺[J].中外葡萄与葡萄酒,2013(2):27-31.
[15]杨新河,李勤,黄建安,等.普洱茶色素提取工艺条件的响应面分析及其抗氧化性活性研究[J]食品科学,2011,32(6):1-5.
[16]夏玫,陈立潮.BP神经网络泛化能力改进研究[D].太原:太原科技大学,2009.