一种改进的SOM神经网络在污水处理故障诊断中的应用

被引：15

作者：

岳宇飞

罗健旭

机构：

[1] 华东理工大学自动化研究所

来源：

华东理工大学学报(自然科学版) | 2017年 / 43卷 / 03期

关键词：

故障诊断; 聚类; 自组织映射; 帝国竞争算法;

D O I：

10.14135/j.cnki.1006-3080.2017.03.015

中图分类号：

TP183 [人工神经网络与计算]; X703 [废水的处理与利用];

学科分类号：

摘要：

自组织映射(SOM)神经网络初始权值的选取对神经网络的性能有重要的影响。采用改进的帝国竞争算法(IICA)优化局部权重失真指数(LWDI)寻优SOM神经网络的初始权值;利用改进后的SOM神经网络(IICA-SOM)对污水处理过程数据进行聚类和故障诊断。实验结果表明,与传统的SOM算法相比,IICA-SOM算法取得了更好的聚类效果,且故障诊断的误诊率更低。

引用

页码：389 / 396

页数：8

共 8 条

[1] Imbalanced evolving self-organizing learning[J] . Qiao Cai,Haibo He,Hong Man.Neurocomputing . 2013
[2] Advanced monitoring platform for industrial wastewater treatment: Multivariable approach using the self-organizing map[J] . Mika Liukkonen,Ilkka Laakso,Yrj? Hiltunen.Environmental Modelling and Software . 2013
[3] Statistical Modeling of Contaminants Removal in Mature Integrated Constructed Wetland Sediments
Dong, Yu
Scholz, Miklas
Harrington, Rory
[J]. JOURNAL OF ENVIRONMENTAL ENGINEERING, 2012, 138 (10) : 1009 - 1017
[4] A novel self-organizing map (SOM) neural network for discrete groups of data clustering
Ghaseminezhad, M. H.
Karami, A.
[J]. APPLIED SOFT COMPUTING, 2011, 11 (04) : 3771 - 3778
[5] A combined measure for quantifying and qualifying the topology preservation of growing self-organizing maps
Delgado, Soledad
Gonzalo, Consuelo
Martinez, Estibaliz
Arquero, Agueda
[J]. NEUROCOMPUTING, 2011, 74 (16) : 2624 - 2632
[6] Subtraction analysis based on self-organizing maps for an industrial wastewater treatment process[J] . M. Heikkinen,H. Poutiainen,M. Liukkonen,T. Heikkinen,Y. Hiltunen.Mathematics and Computers in Simulation . 2010 (3)
[7] Self-organizing map and clustering for wastewater treatment monitoring
García, HL
González, LM
[J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2004, 17 (03) : 215 - 225
[8] SELF-ORGANIZED FORMATION OF TOPOLOGICALLY CORRECT FEATURE MAPS
KOHONEN, T
[J]. BIOLOGICAL CYBERNETICS, 1982, 43 (01) : 59 - 69

← 1 →