基于数据属性划分的递阶ELM研究及化工应用

doi:10.3969/j.issn.0438-1157.2013.12.012

化工学报 ›› 2013, Vol. 64 ›› Issue (12): 4348-4353.DOI: 10.3969/j.issn.0438-1157.2013.12.012

基于数据属性划分的递阶ELM研究及化工应用

高慧慧, 贺彦林, 彭荻, 朱群雄

北京化工大学信息科学与技术学院, 北京 100029

收稿日期:2013-07-30 修回日期:2013-08-10 出版日期:2013-12-05 发布日期:2013-12-05
通讯作者: 朱群雄
作者简介:高慧慧（1991- ），女，硕士研究生。
基金资助:
国家自然科学基金项目（61074153）。

Research and chemical application of data attributes decomposition based hierarchical ELM neural network

GAO Huihui, HE Yanlin, PENG Di, ZHU Qunxiong

College of Information Science & Technology, Beijing University of Chemical Technology, Beijing 100029, China

Received:2013-07-30 Revised:2013-08-10 Online:2013-12-05 Published:2013-12-05
Supported by:
supported by the National Natural Science Foundation of China (61074153).

摘要/Abstract

摘要： 针对极限学习机（ELM）不能有效处理化工过程中强耦合、带噪声的高维数据建模问题，提出了一种基于数据属性划分的递阶ELM神经网络DHELM。该神经网络采用数据属性划分（DAD）方法对高维输入进行聚类、建立自联想子网，并将自联想子网所提取的特征分量作为极限学习机的输入进行建模。同时，利用UCI标准数据集进行了测试，通过工业应用实例进行了验证，并进行了模型对比。结果表明，DHELM网络在处理复杂高维数据时具有收敛速度快、建模精度高、网络稳定性强的特点，为神经网络发展及其化工应用提供了新思路。

关键词: 极限学习机, 自联想神经网络, 数据属性划分, 高维数据, 过程建模

Abstract: The extreme learning machine (ELM) is inefficient in high-dimensional data modeling during the chemical process,where the data is always strongly coupled and with much noise.Aiming at dealing with this problem,a data attributes decomposition based hierarchical ELM neural network (DHELM) is proposed.In the modeling process of DHELM,the data attributes decomposition (DAD) method is used to cluster the high-dimensional inputs and build the auto-associative subnets,and then the extracted characteristic components yielded by auto-associative subnets are inputted to extreme learning machine.Meanwhile,the effectiveness of DHELM is verified by the UCI standard data sets and an industry application object.Through the verification and comparison,the proposed DHELM model has the advantages of fast convergence speed with high modeling accuracy and strong network stability. Furthermore,it provides a new way for neural network development and its application to chemical processes.

Key words: extreme learning machine, auto-associative neural network, data attributes decomposition, high-dimensional data, process modeling

中图分类号:

TP29

高慧慧, 贺彦林, 彭荻, 朱群雄. 基于数据属性划分的递阶ELM研究及化工应用[J]. 化工学报, 2013, 64(12): 4348-4353.

GAO Huihui, HE Yanlin, PENG Di, ZHU Qunxiong. Research and chemical application of data attributes decomposition based hierarchical ELM neural network[J]. CIESC Journal, 2013, 64(12): 4348-4353.

参考文献 20

[1]	Huang Guangbin, Zhu Qinyu, Siew Chee-Kheong. Extreme learning machine:theory and applications[J].Neurocomputing, 2006, 70 (1/2/3):489-501
[2]	Huang Guangbin, Chen Lei.Enhanced random search based incremental learning machine[J].Neurocomputing, 2008, 71 (16/17/18):3460-3468
[3]	Wang Y G, Cao F L, Yuan Y B.A study on effectiveness of extreme learning machine[J].Neurocomputing, 2011, 74:2483-2490
[4]	Zhu Qinyu, Suganthan P N, Huang Guangbin, et al. Evolutionary extreme learning machine[J].Pattern Recognition, 2005, 38 (2):1759-1763
[5]	Hang Yanwei, Wu Dengguo, Li Jun.Structural healthy monitoring data recovery based on extreme learning machine[J].Computer Engineering, 2011, 37 (16):241-243
[6]	Zhang Yingwei, Zhang Pengchao.Optimization of nonlinear process based on sequential extreme learning machine[J].Chem.Eng.Sci., 2011, 66 (20):4702-4710
[7]	Huang Ting, Wang Xin, Li Lixue, Zhou Lidan, Yao Guang. Ultra-short term prediction of wind power based on multiples model extreme learning machine[J].Advances in Neural Networks, 2011, 6677:539-547
[8]	Tian Huixin, Mao Zhizhong.An ensemble ELM based on modified AdaBoost.RT algorithm for predicting the temperature of molten steel in ladle furnace[J].IEEE T.Autom.Sci.Eng., 2010, 7 (1):73-80
[9]	Li Kang, Deng Jing, He Haibo, Du Dajun.Compact extreme learning machine for biological systems[J].International Journal of Computational Biology and Drug Design, 2010, 3 (2):112-132
[10]	Mark A Kramer.Nonlinear principal component analysis using auto associative neural network[J].AIChE Journal, 1991, 37 (2):233-243
[11]	Cai Yi (才轶), Xu Yuan (徐圆), Zhu Qunxiong (朱群雄).Data filtering method and application based on auto-associative neural network[J].Computers and Applied Chemistry (计算机与应用化学), 2009, 26 (5):673-676
[12]	Aly M A, Atiya A F.Novel methods for the feature subset ensembles approach[J].International Journal on Artificial Intelligence and Machine Learning, 2006, 6 (4):21-27
[13]	Lior R, Oded M.Feature set decomposition for decision trees[J].Intelligent Data Analysis, 2005, 9:131-158
[14]	Zheng X Y, Xu Y, Zhu Q X, Peng S W.Data attributes decomposition-based hierarchical neural network[J].IEEE International Conference on ICIS, 2010, 1 (29/30/31):343-347
[15]	Paul Juell, Ron Marsh.A hierarchical neural network for human face detection[J].Pattern Recognition, 1996, 29 (5):781-787
[16]	Peng Di (彭荻), He Yanlin (贺彦林), Xu Yuan (徐圆), Zhu Qunxiong (朱群雄).Research and chemical application of data feature extraction based AANN-ELM neural network[J].CIESC Journal (化工学报), 2012, 63 (9):2920-2925
[17]	Clifford G, Tarassenko L, Townsend N.One-pass training of optimal architecture auto-associative neural network for detecting ectopic beats[J].Electron.Lett., 2011, 37 (18):1126-1127
[18]	Javier Sanz, Ricardo Perera, Consuelo Huerta.Fault diagnosis of rotating machinery based on auto-associative neural networks and wavelet transforms[J].J.Sound Vib., 2007, 302 (4):981-999
[19]	Abbas H M.Analysis and pruning of nonlinear auto-association networks[J].IEE Proc.-Vis.Image Signal Process., 2004, 151 (1):44-50
[20]	Xu Yuan (徐圆), Zhu Qunxiong (朱群雄).Alarm optimization for process industry based on matter-element analysis[J].Journal of Chemical Industry and Engineering (China) (化工学报), 2008, 59 (7):1609-1614

基于数据属性划分的递阶ELM研究及化工应用

Research and chemical application of data attributes decomposition based hierarchical ELM neural network

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 20

相关文章 15

编辑推荐

Metrics

本文评价

[1]	郑书闽, 郭鹏程, 颜建国, 王帅, 李文博, 周淇. 微小通道内过冷流动沸腾阻力特性实验及预测研究[J]. 化工学报, 2023, 74(4): 1549-1560.
[2]	贺彦林, 田业, 顾祥柏, 徐圆, 朱群雄. 基于正则化的函数连接神经网络研究及其复杂化工过程建模应用[J]. 化工学报, 2020, 71(3): 1072-1079.
[3]	王雅欣,徐宝昌,徐朝农,董秀娟,许立伟. 基于工厂数据的注意力LSTM网络辨识方法[J]. 化工学报, 2020, 71(12): 5664-5671.
[4]	代学志,熊伟丽. 基于核极限学习机的快速主动学习方法及其软测量应用[J]. 化工学报, 2020, 71(11): 5226-5236.
[5]	杨新, 麻哲瑞, 申赫男, 陈鸿伟. 基于多尺度特征能量-核极限学习机的双循环流化床气流堵塞故障智能诊断[J]. 化工学报, 2019, 70(7): 2616-2625.
[6]	张晓晗, 汪平江, 顾祥柏, 徐圆, 贺彦林, 朱群雄. 基于主元提取的鲁棒极限学习机研究及其化工建模应用[J]. 化工学报, 2019, 70(2): 475-480.
[7]	朱宝, 乔俊飞. 基于自编码神经网络特征提取的回声状态网络研究及过程建模应用[J]. 化工学报, 2019, 70(12): 4770-4776.
[8]	牛培峰, 王枭飞, 刘楠, 王愿宁, 常玲芳, 张先臣. ASOS-ELM建模方法及在汽轮机热耗率预测中的应用[J]. 化工学报, 2018, 69(9): 3924-3931.
[9]	许玉格, 孙称立, 赖春伶, 罗飞. 基于不平衡学习的集成极限学习机污水处理故障诊断[J]. 化工学报, 2018, 69(7): 3114-3124.
[10]	张雷, 张小刚, 陈华. 基于Gath-Geva算法和核极限学习机的多阶段间歇过程软测量[J]. 化工学报, 2018, 69(6): 2576-2585.
[11]	朱群雄, 张晓晗, 顾祥柏, 徐圆, 贺彦林. 基于特征提取的函数连接神经网络研究及其化工过程建模应用[J]. 化工学报, 2018, 69(3): 907-912.
[12]	徐圆, 张伟, 张明卿, 贺彦林. 基于FEEMD-AE与反馈极限学习机组合模型预测研究与应用[J]. 化工学报, 2018, 69(3): 1064-1070.
[13]	刘厦, 刘石, 任婷. 基于SA-ELM的声学层析成像温度分布重建算法[J]. 化工学报, 2017, 68(6): 2434-2446.
[14]	易维淋, 田学民, 张汉元. 基于重构的半监督ELM及其在故障诊断中的应用[J]. 化工学报, 2017, 68(6): 2447-2454.
[15]	李琨, 韩莹, 佘东生, 魏泽飞, 黄海礁. 基于IFOA-KELM-MEA模型的游梁式抽油机采油系统井下工况的短期预测[J]. 化工学报, 2017, 68(1): 188-198.