基于优化相对主元分析的铝电解槽况诊断

doi:10.11772/j.issn.1001-9081.2014.08.2429

计算机应用 ›› 2014, Vol. 34 ›› Issue (8): 2429-2433.DOI: 10.11772/j.issn.1001-9081.2014.08.2429

基于优化相对主元分析的铝电解槽况诊断

黄迪¹,李太福²,³,易军²,田应甫⁴

1. 重庆科技学院安全工程学院，重庆401331
2. 重庆科技学院电气与信息工程学院，重庆401331；
3. 重庆大学自动化学院，重庆400044
4. 中国电力投资集团公司重庆天泰铝业有限公司，重庆401328

收稿日期:2014-02-11 修回日期:2014-03-27 出版日期:2014-08-01 发布日期:2014-08-10
通讯作者: 黄迪
作者简介:黄迪（1989-)，男(土家族)，湖北利川人，硕士研究生，主要研究方向：复杂系统建模与优化；李太福（1971-），男，四川资阳人，教授，博士，主要研究方向：复杂系统建模与优化、软测量、智能控制；易军（1973-），男，重庆北碚人，副教授，博士，主要研究方向：复杂系统建模与优化；田应甫（1954-），男，四川南充人，高级工程师，主要研究方向：有色金属冶炼。
基金资助:
国家自然科学基金资助项目;重庆市自然科学基金计划重点项目;重庆市自然科学基金;重庆市教委科学技术研究项目

Diagnosis of aluminum reduction cell status based on optimized relative principal component analysis

HUANG Di¹,LI Taifu²,³,YI Jun³,TIAN Yingfu⁴

1. School of Safety Engineering, Chongqing University of Science and Technology, Chongqing 401331, China;
2. College of Automation, Chongqing University, Chongqing 400044, China;
3. School of Electrical and Information Engineering, Chongqing University of Science and Technology, Chongqing 401331, China;
4. Chongqing Tiantai Aluminum Limited Corporation, China Power Investment Corporation, Chongqing 401328, China

Received:2014-02-11 Revised:2014-03-27 Online:2014-08-01 Published:2014-08-10
Contact: HUANG Di
Supported by:
;The Key Project of Natural Science Foundation of CQ

摘要/Abstract

摘要：

针对影响铝电解槽状态的参数较多且耦合性强、建立诊断模型的计算量巨大、诊断精度有限等问题，提出一种基于优化相对主元分析(ORPCA)的铝电解槽况诊断方法。利用相对主元分析(RPCA)方法在进行特征选择时的降维优势，提出一种有效的准则以确定主元的相对权重。通过遗传算法(GA)构造误报率适应度函数，考察观测样本在主元空间和残差空间里投影的变化，以获得搜索区域内最优的相对转换矩阵，使Hotelling's T2检验和预测平方差（SPE）检验的误报率降低到最小。对某厂170kA大型预焙槽的样本进行检验，实验结果表明，该方法在置信度为95%和97.5%时,T2检验误报率分别为16.79%和9.77%，SPE检验误报率分别为4.01%和1.75%。与同类算法相比，所提方法不但能准确诊断出铝电解槽中出现的异常状态，而且明显降低T2检验和SPE检验中出现误报的概率。

Abstract:

Concerning the problems that the parameters of the state of the aluminum reduction cells are multivariate and with strong coupling, the calculation of established diagnosis model is large and the precision of diagnosis is limited, this paper proposed Optimized Relative Principal Component Analysis (ORPCA) method to diagnose the status of aluminum reduction cells. An effective principle of determining the relative weight was put forward, which took advantage of Relative Principal Component Analysis (RPCA) in reducing dimensions. In the method, Genetic Algorithm (GA) was used to optimize the fitness function about false alarm rate. The diversification of the sample project in principal component space and residual space was observed to acquire the best relative transforming matrix, so the false alarm rate of Hotelling's T2 test and Squared Prediction Error (SPE) were reduced to the least. By using a group data of 170kA operating aluminum smelter from a factory, the experimental results show that, when the confidence coefficients are 95% and 97.5%, the false alarm rates of T2 test are 16.79% and 9.77% respectively, meanwhile, the false alarm rates of SPE test are 4.01% and 1.75% respectively. Compared with other similar algorithms, the proposed method can test the abnormal condition of aluminum reduction cells and obviously reduce the false alarm rate of Hotelling's T2 test and SPE test.

中图分类号:

TP206.3

黄迪李太福易军田应甫. 基于优化相对主元分析的铝电解槽况诊断[J]. 计算机应用, 2014, 34(8): 2429-2433.

HUANG Di LI Taifu YI Jun TIAN Yingfu. Diagnosis of aluminum reduction cell status based on optimized relative principal component analysis[J]. Journal of Computer Applications, 2014, 34(8): 2429-2433.

参考文献

［1］ FENG N. Aluminium electrolysis ［M］. Beijing: Chemical Industry Press, 2006.(冯乃祥.铝电解［M］.北京：化学工业出版社,2006.)
［2］YI J, LI T, TIAN Y, et al. Diagnosis of status of aluminum reduction cells based on symmetric Alpha-stable probabilistic distribution neural network ［J］. CIESC Journal, 2012, 63(10): 3196-3201.(易军,李太福,田应甫,等.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.)
［3］DENG S, MA H, XIE Q, et al. A study of on-line simulation and cell condition diagnosis expert system of prebaked cell for aluminum-reduction ［J］. Computer Measurement and Control, 2011, 19(8): 1850-1852.(邓胜祥,马和平,谢青松,等.预焙铝电解槽在线仿真槽况诊断专家系统研究［J］.计算机测量与控制,2011,19(8):1850-1852.)
［4］HAO L, WANG W, WU G, et al. Research on rough set-neural network fault diagnosis method ［J］. Journal of Northeastern University: Natural Science, 2003, 24(3): 252-255.(郝丽娜,王伟,吴光宇,等.粗糙集神经网络故障诊断方法研究［J］.东北大学学报:自然科学版,2003,24(3):252-255.)
［5］LIN J, WANG F, LIAO X. Aluminum reduction cell situation's forecast based on wavelet neural networks ［J］. Control Engineering of China, 2012, 19(002): 290-293.(林景栋,王丰,廖孝勇.基于小波神经网络的铝电解槽状态预测［J］.控制工程,2012,19(2):290-293.)
［6］YAN G, LIANG X, LONG Z, et al. Soft-sensing models of aluminum reduction cell's parameters based on least squares support vector machine ［J］. Journal of Chinese Computer Systems, 2011, 32(12): 2444-2448.(阎纲，梁昔明，龙祖强，等.铝电解槽参数的最小二乘支持向量机软测量模型［J］.小型微型计算机系统,2011,32(12):2444-2448.)
［7］HU J, LIU R, WEN C. Relative PCA-based fault detection and diagnosis method ［J］. Journal of Projectiles, Rockets, Missiles and Guidance, 2007, 27(3): 329-331.(胡静,刘荣利,文成林.基于相对主元分析的故障检测与诊断方法［J］.弹箭与制导学报,2007,27(3):329-331.)
［8］ZHOU D, HU Y. Fault diagnosis techniques for dynamic systems ［J］. Acta Automatica Sinica, 2009, 35(6): 748-758.(周东华,胡艳艳.动态系统的故障诊断技术［J］.自动化学报,2009,35(6):748-758.)
［9］NIE J, GAO W, ZHANG S. Detection and diagnosis of failures with BP neural network in dynamic precise point positioning ［J］. Geomatics and Information Science of Wuhan University, 2010, 35(3): 283-285.(聂建亮,高为广,张双成.利用BP神经网络的动态精密单点定位故障诊断算法［J］.武汉大学学报:信息科学版,2010,35(3):283-285.)
［10］WEN C, HU J, WANG T, et al. Relative PCA with applications of data compression and fault diagnosis ［J］. Acta Automatica Sinica, 2008, 34(9): 1128-1139.(文成林,胡静,王天真,等.相对主元分析及其在数据压缩和故障诊断中的应用研究［J］.自动化学报,2008,34(9):1128-1139.)
［11］WANG T, TANG T, WEN C, et al. Relative principal component analysis algorithm and its application in fault detection ［J］. Journal of System Simulation, 2007, 19(13): 2889-2894.(王天真,汤天浩,文成林,等.相对主元分析方法及其在故障检测中的应用［J］.系统仿真学报,2007,19(13):2889-2894.)
［12］MARTíNEZ R, CASTILLO O, AGUILAR L T. Optimization of interval type-2 fuzzy logic controllers for a perturbed autonomous wheeled mobile robot using genetic algorithms ［J］. Information Sciences, 2009, 179(13): 2158-2174.
［13］VALLADA E, RUIZ R. Genetic algorithms with path relinking for the minimum tardiness permutation flowshop problem ［J］. Omega, 2010, 38(1/2): 57-67.
［14］WANG J, LIU X, WEI G. Quality of service-based Web services optimal selection algorithm and its simulation ［J］. Journal of Tongji University: Natural Science, 2011, 39(4): 599-605.(王俊丽,柳先辉,卫刚.基于服务质量的Web服务优化选择算法及仿真［J］.同济大学学报:自然科学版,2011,39(4):599-605.)
［15］KRESTA J V, MACGREGOR J F, MARLIN T E. Multivariate statistical monitoring of process operating performance ［J］. The Canadian Journal of Chemical Engineering, 1991, 69(1): 35-47.
［16］WANG H, LI S. The bounds of restricted isometry constants for low rank matrices recovery ［J］. Science China: Mathematics, 2013, 56(6): 1117-1127.
［17］LI H, XIAO D. Survey on data driven fault diagnosis methods ［J］. Control and Decision, 2011, 26(1): 1-9.(李晗,萧德云.基于数据驱动的故障诊断方法综述［J］.控制与决策,2011,26(1):1-9.)
［18］NIAZI A, LEARDI R. Genetic algorithms in chemometrics ［J］. Journal of Chemometrics, 2012, 26(6): 345-351.

[1]	朱霖, 宁芊, 雷印杰, 陈炳才. 基于遗传算法选优的集成手段与时序卷积网络的涡扇发动机剩余寿命预测[J]. 计算机应用, 2020, 40(12): 3534-3540.
[2]	王思鹏, 杜昌平, 叶志贤, 宋广华, 郑耀. 基于多步神经网络观测器的扑翼飞行器缓变故障检测[J]. 计算机应用, 2020, 40(8): 2449-2454.
[3]	胡珉, 白雪, 徐伟, 吴秉键. 多维时间序列异常检测算法综述[J]. 计算机应用, 2020, 40(6): 1553-1564.
[4]	吴婕, 吕永乐. 基于多项式系数自回归模型的雷达性能参数最优组合预测[J]. 计算机应用, 2019, 39(4): 1117-1121.
[5]	刘帅, 刘长良, 甄成刚. 风电机组齿轮箱的多变量时间序列故障预警[J]. 计算机应用, 2019, 39(4): 1229-1233.
[6]	杨光周敬利熊婷姬厚灵. 基于随机丢包网络的网络存储系统故障检测方法[J]. 计算机应用, 2012, 32(03): 795-799.
[7]	叶卫东, 杨涛. 融合极点对称模态分解与时频分析的单通道振动信号盲分离方法[J]. 计算机应用, 2016, 36(10): 2933-2939.

基于优化相对主元分析的铝电解槽况诊断

Diagnosis of aluminum reduction cell status based on optimized relative principal component analysis

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

编辑推荐

Metrics