基于人工神经网络的半连续式混合厌氧消化产气量预测
|
摘要
研究采用BP神经网络和模糊神经网络(FNN)模型对逐步提高有机负荷的半连续式餐厨垃圾和猪粪混合厌氧消化试验进行日产气量预测。结果表明,BP神经网络模型的预测准确率为77.63%,FNN模型为82.33%,2种模型均可用于产气预测,但FNN模型在传统神经网络模型基础上加入了模糊控制,可提高其准确率,更适用于混合厌氧消化产气量预测。
The study established gas production prediction models based on BP neural network and fuzzy neural network( FNN) on a semi-continuous anaerobic co-digestion experiment of kitchen waste and pig manure with gradually increasing organic loading rate. The results showed that the prediction accuracy of BP neural network model was 77. 63%,and that of the FNN model was 82. 33%. Both models can be used to predict gas production,but the FNN model,which joined fuzzy control in the traditional neural network to improve its accuracy,is more suitable for the gas prediction of anaerobic co-digestion.
The study established gas production prediction models based on BP neural network and fuzzy neural network( FNN) on a semi-continuous anaerobic co-digestion experiment of kitchen waste and pig manure with gradually increasing organic loading rate. The results showed that the prediction accuracy of BP neural network model was 77. 63%,and that of the FNN model was 82. 33%. Both models can be used to predict gas production,but the FNN model,which joined fuzzy control in the traditional neural network to improve its accuracy,is more suitable for the gas prediction of anaerobic co-digestion.
引文
[1]张良均,曹晶,蒋世忠.神经网络实用教程.北京:机械工业出版社,2008
[2]曹刚,徐向阳,冯孝善.神经网络在厌氧消化过程中的模拟应用.中国沼气,2001,19(4):3-6,10Cao Gang,Xu Xiangyang,Feng Xiaoshan.Artificial neural network and its application in the anaerobic digestion processes.China Biogas,2001,19(4):3-6,10(in Chinese)
[3]Pramanik K.Use of artificial neural networks for prediction of cell mass and ethanol concentration in batch fermentation using saccharomyces cerevisiae yeast.Journal of Institute of Engineers,2004,85(9):31-35
[4]Nikhil B.O.,Visa A.,Lin C.Y.,et al.An artificial neural network based model for predicting H2production rates in a sucrose-based bioreactor system.World Academy of Science,Engineering and Technology,2008,37:20-25
[5]Holubar P.,Zani L.,Hager M.,et al.Modelling of anaerobic digestion using self-organizing maps and artificial neural networks.Water Science and Technology,2000,41(12):149-156
[6]Shi Y.,Gai G.,Zhao X.,et al.Influence and simulation model of operational parameters on hydrogen bio-production through anaerobic microorganism fermentation using two kinds of wastes.//San Francisco:Proceeding of the World Congress on Engineering and Computer Science,2009
[7]Strik D.P.,Domnanovich A.M.,Zani L.,et al.Prediction of trace compounds in biogas from anaerobic digestion using the MATLAB Neural Network Toolbox.Environmental Modeling&Software,2005,20(6):803-810
[8]Holubar P.,Zani L.,Hager M.,et al.Advanced controlling of anaerobic digestion by means of hierarchical neural networks.Water Research,2002,36(10):2582-2588
[9]张文阳,张良均,李娜,等.多元回归和BP人工神经网络在预测混合厌氧消化产气量过程中的应用比较.环境工程学报,2013,7(2):747-752Zhang Wenyang,Zhang Liangjun,Li Na,et al.Comparing multiple regression and BP artificial nerve net model used on prediction of anaerobic co-digestion gas-producing process.Chinese Journal of Environmental Engineering,2013,7(2):747-752(in Chinese)
[10]王俭,胡筱敏,郑龙熙,等.基于BP模型的大气污染预报方法的研究.环境科学研究,2002,15(5):62-64Wang Jian,Hu Xiaomin,Zheng Longxi,et al.Study on forecasting of air pollution based on BP Model.Research of Environmental Sciences,2002,15(5):62-64(in Chinese)
[11]Hecht-Nielsen R.Neurocomputing.Menlo Park,:AddisonWeslsy Publishing Company,1990
[12]朱大奇,史慧.人工神经网络原理及应用.北京:科学出版社,2006
[13]Kurkova V.Kolmogorov’s theorem and multilayer neural networks.Neural Networks,1992,5(3):501-506
[14]侯媛彬,杜京义,汪梅.神经网络.西安:西安电子科技大学出版社,2007
[15]姜勇.电力系统短期负荷预测的模糊神经网络方法.继电器,2002,30(7):11-13Jiang Yong.Fuzzy neural network for short-term load forecasting.Relay,2002,30(7):11-13(in Chinese)
[2]曹刚,徐向阳,冯孝善.神经网络在厌氧消化过程中的模拟应用.中国沼气,2001,19(4):3-6,10Cao Gang,Xu Xiangyang,Feng Xiaoshan.Artificial neural network and its application in the anaerobic digestion processes.China Biogas,2001,19(4):3-6,10(in Chinese)
[3]Pramanik K.Use of artificial neural networks for prediction of cell mass and ethanol concentration in batch fermentation using saccharomyces cerevisiae yeast.Journal of Institute of Engineers,2004,85(9):31-35
[4]Nikhil B.O.,Visa A.,Lin C.Y.,et al.An artificial neural network based model for predicting H2production rates in a sucrose-based bioreactor system.World Academy of Science,Engineering and Technology,2008,37:20-25
[5]Holubar P.,Zani L.,Hager M.,et al.Modelling of anaerobic digestion using self-organizing maps and artificial neural networks.Water Science and Technology,2000,41(12):149-156
[6]Shi Y.,Gai G.,Zhao X.,et al.Influence and simulation model of operational parameters on hydrogen bio-production through anaerobic microorganism fermentation using two kinds of wastes.//San Francisco:Proceeding of the World Congress on Engineering and Computer Science,2009
[7]Strik D.P.,Domnanovich A.M.,Zani L.,et al.Prediction of trace compounds in biogas from anaerobic digestion using the MATLAB Neural Network Toolbox.Environmental Modeling&Software,2005,20(6):803-810
[8]Holubar P.,Zani L.,Hager M.,et al.Advanced controlling of anaerobic digestion by means of hierarchical neural networks.Water Research,2002,36(10):2582-2588
[9]张文阳,张良均,李娜,等.多元回归和BP人工神经网络在预测混合厌氧消化产气量过程中的应用比较.环境工程学报,2013,7(2):747-752Zhang Wenyang,Zhang Liangjun,Li Na,et al.Comparing multiple regression and BP artificial nerve net model used on prediction of anaerobic co-digestion gas-producing process.Chinese Journal of Environmental Engineering,2013,7(2):747-752(in Chinese)
[10]王俭,胡筱敏,郑龙熙,等.基于BP模型的大气污染预报方法的研究.环境科学研究,2002,15(5):62-64Wang Jian,Hu Xiaomin,Zheng Longxi,et al.Study on forecasting of air pollution based on BP Model.Research of Environmental Sciences,2002,15(5):62-64(in Chinese)
[11]Hecht-Nielsen R.Neurocomputing.Menlo Park,:AddisonWeslsy Publishing Company,1990
[12]朱大奇,史慧.人工神经网络原理及应用.北京:科学出版社,2006
[13]Kurkova V.Kolmogorov’s theorem and multilayer neural networks.Neural Networks,1992,5(3):501-506
[14]侯媛彬,杜京义,汪梅.神经网络.西安:西安电子科技大学出版社,2007
[15]姜勇.电力系统短期负荷预测的模糊神经网络方法.继电器,2002,30(7):11-13Jiang Yong.Fuzzy neural network for short-term load forecasting.Relay,2002,30(7):11-13(in Chinese)