基于对称Alpha稳定分布概率神经网络的铝电解槽况诊断

doi:10.3969/j.issn.0438-1157.2012.10.027

化工学报 ›› 2012, Vol. 63 ›› Issue (10): 3196-3201.DOI: 10.3969/j.issn.0438-1157.2012.10.027

基于对称Alpha稳定分布概率神经网络的铝电解槽况诊断

易军¹, 李太福^1,2, 田应甫³, 姚立忠⁴, 侯杰²

1. 重庆科技学院电气与信息工程学院, 重庆 401331;
2. 重庆大学自动化学院, 重庆 400044;
3. 重庆天泰铝业有限公司, 重庆 401328;
4. 西安石油大学电子工程学院, 陕西西安 710065

收稿日期:2012-02-18 修回日期:2012-03-29 出版日期:2012-10-05 发布日期:2012-10-05
通讯作者: 易军
作者简介:易军(1973- ),男,博士,讲师。
基金资助:
国家自然科学基金项目(61174015);重庆市自然科学基金重点项目(CSTC2012JJB40006);重庆市教委科学技术研究项目(KJ121410)重庆科技学院校内科研基金项目(CK2011B04)。

Diagnosis of status of aluminum reduction cells based on symmetric Alpha-stable probabilistic distribution neural network

YI Jun¹, LI Taifu^1,2, TIAN Yingfu³, YAO Lizhong⁴, HOU Jie²

1. School of Electronic & Information Engineering, Chongqing University of Science and Technology, Chongqing 401331, China;
2. School of Automation, Chongqing University, Chongqing 400044, China;
3. Chongqing Tiantai Aluminum Cor. Ltd., Chongqing 401328, China;
4. School of Electronic Engineering, Xi'an Shiyou University, Xi'an 710065, Shaanxi, China

Received:2012-02-18 Revised:2012-03-29 Online:2012-10-05 Published:2012-10-05
Supported by:
supported by the National Natural Science Foundation of China(61174015),Natural Science Foundation Project of Chongqing CSTC(CSTC2012jjb40006),Science and Technology Project of CQJW(KJ121410)and Campus Research Foundation of University of Science and Technology of Chongqing(CK2011B04).

摘要/Abstract

摘要： 在铝电解槽非稳态情况下,槽参数易发生局部突变,呈现非高斯概率分布,且各种槽参数相关性较强,无法满足概率神经网络中训练样本必须服从独立同分布的假设条件,影响槽况诊断的精确度。提出一种基于对称Alpha稳定分布概率神经网络的铝电解槽况诊断方法,利用其对非高斯分布数据的良好近似拟合能力,改进模式层的径向基函数,提高概率神经网络对槽参数局部突变的适应性。通过取自某厂170 kA大型预焙槽的样本进行检验表明,该方法能够对5种槽况做出正确的诊断,具有较强的分类精度和收敛速度。

关键词: 对称Alpha稳定分布, 概率神经网络, 故障诊断, 铝电解槽, 概率密度函数

Abstract: The numerous variables in non-steady state of aluminum reduction cells are non-Gaussian and impulsive.Due to correlation of variables,the condition that training samples must be independent and identically distributed is not fulfilled.For these reasons,it is too hard to diagnose the status of aluminum reduction cells in application.A diagnosis method for the status of aluminum reduction cells based on symmetric Alpha-stable(SαS)probabilistic distribution neural network was proposed.In the method,probability density function of SαS was introduced as radial basis function of model layer into the probabilistic neural network because such function had good fitting ability to non-Gaussian distributed data.And it also improved neural network approximation ability of partial pulse burst.By using 40 groups data of 170 kA operating aluminum smelter from a factory,this method could diagnose five statuses of aluminum reduction cells correctly and had not only stronger adaptability and robustness,but also approximation reliability and fast convergence.

Key words: symmetric Alpha-stable distribution, probabilistic neural network, fault diagnosis, aluminum reduction cell, probability density function

中图分类号:

TQ821
TF391

易军, 李太福, 田应甫, 姚立忠, 侯杰. 基于对称Alpha稳定分布概率神经网络的铝电解槽况诊断[J]. 化工学报, 2012, 63(10): 3196-3201.

YI Jun, LI Taifu, TIAN Yingfu, YAO Lizhong, HOU Jie. Diagnosis of status of aluminum reduction cells based on symmetric Alpha-stable probabilistic distribution neural network[J]. CIESC Journal, 2012, 63(10): 3196-3201.

参考文献 15

[1]	Vogti H,Thonstad J.The voltage of alumina reduction cells prior to the anode effect[J].Journal of Applied Electrochemistry,2002,32:241-249
[2]	Majid N A A,Taylor M P,Chen J J,Stam M A,Mulder A,Young B R.Aluminum process fault detection by multiway principal component analysis[J].Control Engineering Practice,2011,19:367-379
[3]	Li Hesong(李贺松),Yin Xiaobao(殷小宝),Huang Yongbo(黄涌波),Ding Liwei(丁立伟),Jiang Changwei(姜昌伟).Diagnosis system of different status of aluminum reduction cells based on anode current fluctuation[J].CIESC Journal(化工学报),2011,62(6):1770-1777
[4]	Yin Ensheng(殷恩生).The 160kA Center Prebake Aluminum Cutting Production Technology and Management(160 kA中心下料预焙铝电解槽生产工艺及管理)[M].Changsha:Central South University Press,2004
[5]	Peter M Enier.Further development of the temperature model[J].Light Metals,1996(9):445-449
[6]	Jiang Shaolong(姜绍龙).Research on intelligent health diagnosis system for aluminum electrolysis cells.Beijing:Tsinghua University,2005
[7]	Specht D F.Probabilistic neural networks[J].Neural Networks,1990,3(1):109-118
[8]	Cai Qulin(蔡曲林),Liu Puyin(刘普寅).A new supervised learning algorithm for probabilistic neural network[J].Fuzzy Systems and Mathematics(China)(模糊系统与数学),2006,20(6):83-87
[9]	Li Chunfang(李春芳),Liu Lianzhong(刘连忠),Lu Zhen(陆震).Probabilistic neural network based on data field[J].Acta Electronica Sinica(China)(电子学报),2011,8:1739-1745
[10]	Nikias C L,Shao M.Signal Processing with Alpha-stable Distributions and Applications[M].New York:Wiley,1995
[11]	Diego S G,Ercan E K,Diego P R.Finite mixture of α-stable distributions[J].Digital Signal Processing,2009,19(2):250-264
[12]	Samorodnitsky G,Taqqu M.Stable Non-Gaussian Random Processes:Stochastic Models with Infinite Variance[M].London:Chapman and Hall,1994
[13]	Kuruoglu E E,Fitzgerald W J,Rayner P J W.Near optimal detection of signals in impulsive noise modeled with a symmetric α-stable distribution[J].Communications Letters,IEEE,1998,2(10):282-284
[14]	Mehdi K,Mehdi B,Gholam A R A.Improvement of auto-regressive integrated moving average models using fuzzy logic and artificial neural networks(ANNs)[J].Neurocomputing,2009,72(4/5/6):956-967
[15]	Mueller M E,Blanquart G,Pitsch H.Hybrid method of moments for modeling soot formation and growth[J].Combustion and Flame,2009,156(6):1143-1155

基于对称Alpha稳定分布概率神经网络的铝电解槽况诊断

Diagnosis of status of aluminum reduction cells based on symmetric Alpha-stable probabilistic distribution 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 15

相关文章 15

编辑推荐

Metrics

本文评价

[1]	明迁, 高逸, 胡剑, 李盛杰, 王金江. 热交换器泄漏故障虚拟感知方法研究[J]. 化工学报, 2023, 74(4): 1836-1846.
[2]	高学金, 程琨, 韩华云, 高慧慧, 齐咏生. 基于中心损失的条件生成式对抗网络的冷水机组故障诊断[J]. 化工学报, 2022, 73(9): 3950-3962.
[3]	杨静, 林振康, 汤君, 樊铖, 孙克宁. 电池系统的故障特征以及多故障的诊断与识别[J]. 化工学报, 2022, 73(8): 3394-3405.
[4]	孙哲, 金华强, 李康, 顾江萍, 黄跃进, 沈希. 基于知识数据化表达的制冷空调系统故障诊断方法[J]. 化工学报, 2022, 73(7): 3131-3144.
[5]	张成, 潘立志, 李元. 基于加权统计特征KICA的故障检测与诊断方法[J]. 化工学报, 2022, 73(2): 827-837.
[6]	张弛, 李浩, 胡海涛, 朱翀, 张玉莹, 南国鹏, 舒悦. 基于自动特征工程的飞行器轴承故障诊断[J]. 化工学报, 2021, 72(S1): 430-436.
[7]	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.
[8]	邓佳伟, 邓晓刚, 曹玉苹, 张晓玲. 基于加权统计局部核主元分析的非线性化工过程微小故障诊断方法[J]. 化工学报, 2019, 70(7): 2594-2605.
[9]	王耀武, 彭建平, 狄跃忠, 蒿鹏程. 铝电解槽干式防渗料在电解过程中的反应机理探讨[J]. 化工学报, 2019, 70(3): 1035-1041.
[10]	翟坤, 杜文霞, 吕锋, 辛涛, 句希源. 一种改进的动态核主元分析故障检测方法[J]. 化工学报, 2019, 70(2): 716-722.
[11]	鲁春燕, 李炜. 基于深度置信网络的炼化空压机故障诊断方法[J]. 化工学报, 2019, 70(2): 757-763.
[12]	彭开香, 张传放, 马亮, 董洁, 焦瑞华, 唐鹏. 面向系统层级的复杂工业过程全息故障诊断[J]. 化工学报, 2019, 70(2): 590-598.
[13]	顾炳斌, 熊伟丽. 基于多块信息提取的PCA故障诊断方法[J]. 化工学报, 2019, 70(2): 736-749.
[14]	李沛洁, 杨博, 李宏光. 基于关联规则的条件状态模糊Petri网及其在故障诊断中的应用[J]. 化工学报, 2018, 69(8): 3517-3527.
[15]	王占伟, 王林, 梁坤峰, 袁俊飞, 王智伟. 基于融合的贝叶斯网络的冷水机组故障诊断[J]. 化工学报, 2018, 69(7): 3167-3173.