基于神经网络的炭气凝胶孔结构的预测与优化模型研究

杨榛; 乔文明; 梁晓怿

doi:10.1016/S1872-5805(17)60108-2

基于神经网络的炭气凝胶孔结构的预测与优化模型研究

doi: 10.1016/S1872-5805(17)60108-2

华东理工大学化学反应工程国家重点实验室, 特种功能高分子材料及相关技术教育部重点实验室, 上海 200237

基金项目: 国家自然科学基金（21177038）.

详细信息

通讯作者:
梁晓怿.E-mail:xyliang73@sina.com

中图分类号: TQ127.1⁺1
计量
- 文章访问数: 481
- HTML全文浏览量: 114
- PDF下载量: 416
- 被引次数: 0
出版历程
- 收稿日期: 2016-10-28
- 录用日期: 2017-02-25
- 修回日期: 2017-01-29
- 刊出日期: 2017-02-28

Modelling and optimization of the pore structure of carbon aerogels using an artificial neural network

State Key Laboratory of Chemical Engineering, Key Laboratory for Special functional Polymer Materials and Their Related Technologies, Ministry of Education, East China University of Science and Technology, Shanghai 200237, China

Funds: National Natural Science Foundation of China (51174144); Key Scientific and Technological Projects in Shanxi Province (20110321039).

摘要

摘要: 如何控制和预测孔结构是炭气凝胶研究的重要课题。然而，由于耗时耗财，导致实验方法研究控制和预测孔结构成为难题。本文提出一种基于神经网络的炭气凝胶孔结构的预测与优化模型，并采用遗传算法设计和优化模型，对六种典型训练算法模型性能进行比较分析。利用该模型对孔径和吸附容量进行预测，两者的预测相关系数分别为0.992和0.981，预测均方根误差分别为0.077和0.054。经测试，该模型与实验研究的结果相符，并有效的应用于预测和控制炭气凝胶实验参数。
- 炭气凝胶 /
- 孔结构 /
- 神经网络 /
- 训练算法 /
- 模型
Abstract: An intelligent simulation method for predicting and optimizing the pore structure of carbon aerogels is proposed by using an artificial neural network (ANN) algorithm. The ANN model has been optimized based on an improved genetic algorithm from six typical training algorithms. The volumes and diameters of pores in the simulated samples are predicted by the optimized ANN model, which shows correlation coefficients R² of 0.992 and 0.981 and root-mean-square prediction errors (RMSPE) of 0.077 and 0.054 between the predicted and experimental values for the volumes and diameters of pores, respectively. The proposed model is expected to have practical applications in the pore structure control of carbon aerogels.
- Carbon aerogels /
- Pore structure /
- Neural network /
- Training algorithms /
- Modelling

HTML全文

下载: 全尺寸图片幻灯片

参考文献(20)

Pekala R W. Organic aerogels from the polycondensation of resorcinol with formaldehyde[J]. J Mater Sci, 1989, 24: 3221-3227.

Pekala R W, Alviso C T, Kong F M. Aerogels derived from multifunctional organic monomers[J]. J Non-Cryst Solids, 1992, 145: 90-98.

Liu X M, Zhang R, Zhan L, et al. Impedance of carbon aerogel/activated carbon composites as electrodes of electrochemical capacitors in aprotic electrolyte[J]. New Carbon Mater, 2007, 22: 153-158.

Saliger R, Fischer U, Herta C. High surface area carbon aerogels for supercapacitors[J]. J Non-Cryst Solids, 1998, 2259: 335-342.

Moreno C C, Maldonado H F J. Carbon aerogels for catalysis applications: An overview[J]. Carbon, 2005, 43: 455-465.

Ying T Y, Yang K L, Yiacoumi S. Electrosorption of ions from aqueous solutions by nanostructured carbon aerogel[J]. J Colloid Interf Sci, 2002, 250: 18-27.

Timung S, Mandal T K. Prediction of flow pattern of gas-liquid flow through circular microchannel using probabilistic neural network[J]. Appl Soft Comput, 2013, 13:1674-1685.

Eynard J, Grieu S, Polit M. Wavelet-based multi-resolution analysis and artificial neural networks for forecasting temperature and thermal power consumption[J]. Eng Appl Artif Intel, 2011, 24: 501-516.

Kiranyaz S, Ince T, Yildirim A, et al. Evolutionary artificial neural networks by multi-dimensional particle swarm optimization[J]. Neural Networks, 2009, 22: 1448-1462.

Kuzmanovski I, Novi M, Trpkovska M. Automatic adjustment of the relative importance of different input variables for optimization of counter-propagation artificial neural networks[J]. Analytica Chem Acta, 2009, 642: 142-147.

Wang S C, Cong D X, Sun R J. Predicting saturates of sour vacuum gas oil using artificial neural networks and genetic algorithms[J]. Expert Syst Appl, 2010, 37: 4768-4771.

Plumb A P, Rowe R C, York P, et al. Optimisation of the predictive ability of artificial neural network (ANN) models: A comparison of three ANN programs and four classes of training algorithms[J]. Eur J Pharm Sci, 2005, 25: 395-405.

Long D H, Zhang J, Yang J H, et al. Preparation and microstructure control of carbon aerogels produced using m-cresol mediated sol-gel polymerization of phenol and furfural[J].New Carbon Mater, 2008, 23: 165-170.

Papadopoulos V D, Beligiannis G N, Hela D G. Combining experimental design and artificial neural networks for the determination of chlorinated compounds in fish using matrix solid-phase dispersion[J]. Appl Soft Comput, 2011, 11: 5155-5164.

McCulloch W, Pitt W. A logical calculus of the ideas immanent[J]. Math Biophys, 1943, 5: 115-133.

Khanmohammadi M, Garmarudi A B, Khoddami N, et al. A novel technique based on diffuse reflectance near-infrared spectrometry and back-propagation artificial neural network for estimation of particle size in TiO₂ nano particle samples[J]. J Microchemical, 2010, 95: 337-340.

Hanafizadeh P, Zavasan R A, Khaki H R. An expert system for perfume selection using artificial neural network[J]. Expert Syst Appl, 2010, 37: 8879-8887.

Perlovsky L. Neural Networks and Intellection[M]. Oxford University Press, 2001.

James T L, Barkhi R, Johnson J D. Platform impact on performance of parallel genetic algorithms: Design and implementation considerations[J]. Eng Appl Artif Intel, 2006, 19: 843-856.

Davis L, Reinhold V N. Handbook of Genetic Algorithms[M]. New York, 1991.

施引文献

资源附件(0)

访问统计