浮选工艺指标KPCA-ELM软测量模型及应用

doi:10.3969/j.issn.0438-1157.2012.09.035

化工学报 ›› 2012, Vol. 63 ›› Issue (9): 2892-2898.DOI: 10.3969/j.issn.0438-1157.2012.09.035

浮选工艺指标KPCA-ELM软测量模型及应用

李海波¹, 柴天佑^1,2, 岳恒^1,2

1. 东北大学流程工业综合自动化国家重点实验室, 辽宁沈阳 110004;
2. 东北大学自动化研究中心, 辽宁沈阳 110004

收稿日期:2012-06-13 修回日期:2012-06-20 出版日期:2012-09-05 发布日期:2012-09-05
通讯作者: 李海波
作者简介:李海波(1976-),男,博士研究生。
基金资助:
国家重点基础研究发展计划项目(2009CB320601)。

Soft sensor of technical indices based on KPCA-ELM and application for flotation process

LI Haibo¹, CHAI Tianyou^1,2, YUE Heng^1,2

1. State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang 110004, Liaoning, China;
2. Research Center of Automation, Northeastern University, Shenyang 110004, Liaoning, China

Received:2012-06-13 Revised:2012-06-20 Online:2012-09-05 Published:2012-09-05
Supported by:
supported by the National Basic Research Program of China(2009CB320601).

摘要/Abstract

摘要： 精矿品位和尾矿品位是浮选过程重要的工艺技术指标,其难以实现在线检测,且与过程控制变量具有强非线性、不确定性等综合复杂特性,难以直接采用精确的数学模型描述,主要依靠人工化验分析。人工采样化验周期较长,难以满足控制要求,使得浮选精矿品位偏低,尾矿品位偏高,因此建立浮选品位指标的软测量方法受到工业界广泛关注。在分析浮选过程工艺指标相关影响因素的基础上,建立一种基于主元分析KPCA(kernel principal component analysis)和极限学习机ELM(extreme learning machine)的软测量模型。为了消除离群点对软测量模型精度的影响,采用基于稳健位置估计的方法识别离群点,利用核主元分析对软测量模型的输入数据进行降维,提取非线性主元,然后用极限学习机进行建模。该建模方法已成功应用于中国西北某选矿厂浮选车间,工业应用结果表明该方法有很高的预报精度,对生产有一定的指导意义。

关键词: 浮选, 核主元分析, 极限学习机, 软测量

Abstract: In the flotation process,the concentrate grade and the tailing grade are crucial technical indices which can not be measured online continuously.They can hardly be described using accurate mathematical model for strong nonlinearities and uncertainties among technical indices and operating variables,mainly measured off-line by artificial laboratory.The long cycle of artificial laboratory is difficult to meet the control requirement of grade indices,so study of grade indices soft measurement method attracts more attention.By analyzing the relations between the technical indices and such boundary variables,a soft sensor model of technical indices based kernel principal component analysis(KPCA)and extreme learning machine(ELM)was proposed innovatively to estimate the concentrate grade and the tailing grade.To solve the outliers,missing data points of the outliers and deviation from normal values are detected.KPCA is applied to compress the input data,and select the nonlinear principle component.ELM is used to process regression modeling.The proposed model is successfully applied to the flotation process of a hematite ore processing plant in China.Industrial application results show that the soft sensor model has high accuracy and guidance to real production.

Key words: flotation, KPCA, ELM, soft sensor

中图分类号:

TP273

李海波, 柴天佑, 岳恒. 浮选工艺指标KPCA-ELM软测量模型及应用[J]. 化工学报, 2012, 63(9): 2892-2898.

LI Haibo, CHAI Tianyou, YUE Heng. Soft sensor of technical indices based on KPCA-ELM and application for flotation process[J]. CIESC Journal, 2012, 63(9): 2892-2898.

参考文献 20

[1]	Macvog T J.Contemplative stance for chemical process [J].Automation,1992,28(2):441-442
[2]	Liu Ruilan(刘瑞兰),Su Hongye(苏宏业),Chu Jian(褚健).A soft sensor modeling algorithm based on modified fuzzy neural network [J].Information and Control(信息与控制),2003,32(4):367-370
[3]	Yoo C K,Lee I B.Soft sensor and adaptive model based dissolved oxygen control for biological wastewater treatment processes [J].Environmental Engineering Science,2004,21(3):331-340
[4]	Rumellhart D E,Hinton G E, Williams R J.Learning internal representations by error propagation [J].Parallel Distrib. Process:Explanations Microstructure of Cognition,1986,1(1):318-362
[5]	Ferrari S,Stengel R F.Smooth function approximation using neural networks[J].IEEE Trans.Neural Netw.,2005,16(1):24-38
[6]	Park J,Sandberg I W.Universal approximation using radial basis-function networks[J].Neural Comput.,1991,3(1):246-257
[7]	Kwok T Y,Yeung D Y.Objective functions for training new hidden units in constructive neural networks [J].IEEE Trans. Neural Netw.,1997,8(5):1131-1148
[8]	LeCun Y,Bottou L,Orr G B, Müller K R.Efficient backprop[J].Lecture Notes Comput. Sci.,1998,1524:9-50
[9]	Ngia L S H,Sjöberg J,Viberg M.Adaptive neural nets filter using a recursive levenberg-marquardt search direction//Proc.Asilomar Conf.Signals,Syst.,Comput.1998:697-701
[10]	Huang G B,Zhu Q Y,Siew C K.Extreme learning machine:a new learning scheme of feedforward neural networks//Proceedings of International Joint Conference on Neural Networks.Piscataway:Institute of Electrical and Electronics Engineers Inc,2004:985-990
[11]	Wang G,Zhao Y,Wang D.A protein secondary structure prediction framework based on the Extreme Learning Machine [J].Neurocomputing,2008,72:262-268
[12]	Huang G B,Zhu Q Y,Mao K Z,et al.Can threshold networks be trained directly？[J].IEEE Transaction on Circuits and Systems Ⅱ,2006,53(3):187-191
[13]	Ipek H,Ankara H.The application of statistical process control [J].Minerals Engineering,1999,12(7):827-835
[14]	Zamprogna E,Barolo M,Seborg D E.Optimal selection of soft sensor inputs for batch distillation columns using principal component analysis [J].Journal of Process Control,2005,15(1):39-52
[15]	Schölkopf B,Smola A J,Müller K R.Nonlinear component analysis as a kernel eigenvalue problem [J].Neural Computation,1998,10(5):1299-1319
[16]	Huang G B,Zhu Q Y,Siew C K.Real-time learning capability of neural networks.Singapore:School of Electrical and Electronic Engineering,Nanyang Technological University,2003
[17]	Huang G B,Zhu Q Y,Siew C K.Extreme learning machine:theory and applications [J].Neurocomputing,2006,60:489-501
[18]	Tamura S,Tateishi M.Capabilities of a four-layered feedforward neural network:four layers versus three [J].IEEE Trans. Neural Networks,1997,8(2):251-255
[19]	Huang G B.Learning capability and storage capability of two-hidden-layer feedforward network [J].IEEE Trans. Neural Networks,2003,14(2):274-281
[20]	Luo Jiahong(罗家洪).Matrix Theory Analysis(矩阵理论分析)[M].Guangzhou:South China University of Technology Press,2003

浮选工艺指标KPCA-ELM软测量模型及应用

Soft sensor of technical indices based on KPCA-ELM and application for flotation process

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]	闫琳琦, 王振雷. 基于STA-BiLSTM-LightGBM组合模型的多步预测软测量建模[J]. 化工学报, 2023, 74(8): 3407-3418.
[2]	邵伟明, 韩文学, 宋伟, 杨勇, 陈灿, 赵东亚. 基于分布式贝叶斯隐马尔可夫回归的动态软测量建模方法[J]. 化工学报, 2023, 74(6): 2495-2502.
[3]	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.
[4]	李亚芾, 付亮亮, 白浩隆, 白丁荣, 许光文. 菱镁矿浮选尾矿直接合成同时制备镁橄榄石和镁砂研究[J]. 化工学报, 2022, 73(8): 3679-3687.
[5]	罗顺桦, 王振雷, 王昕. 基于二子空间协同训练算法的半监督软测量建模[J]. 化工学报, 2022, 73(3): 1270-1279.
[6]	刘聪, 谢莉, 杨慧中. 基于改进DPC的青霉素发酵过程多模型软测量建模[J]. 化工学报, 2021, 72(3): 1606-1615.
[7]	陈忠圣, 朱梅玉, 贺彦林, 徐圆, 朱群雄. 基于分位数回归CGAN的虚拟样本生成方法及其过程建模应用[J]. 化工学报, 2021, 72(3): 1529-1538.
[8]	李东, 黄道平, 刘乙奇. 基于协同训练的半监督异构自适应软测量建模方法的研究[J]. 化工学报, 2020, 71(5): 2128-2138.
[9]	杜宇浩, 阎高伟, 李荣, 王芳. 基于局部线性嵌入的测地线流式核多工况软测量建模方法[J]. 化工学报, 2020, 71(3): 1278-1287.
[10]	杨逸俊,王振雷,王昕. 基于最近邻与神经网络融合模型的软测量建模方法[J]. 化工学报, 2020, 71(12): 5696-5705.
[11]	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.
[12]	侯延彬,高宪文,李翔宇. 采油过程多尺度状态特征生成的有杆泵动态液面预测[J]. 化工学报, 2019, 70(S2): 311-321.
[13]	廉小亲, 王俐伟, 安飒, 魏伟, 刘载文. 基于SOM-RBF神经网络的COD软测量方法[J]. 化工学报, 2019, 70(9): 3465-3472.
[14]	秦美华, 朱红求, 李勇刚, 陈俊名, 张凤雪, 李文婷. 基于STA-K均值聚类的电化学废水处理过程离子浓度软测量[J]. 化工学报, 2019, 70(9): 3458-3464.
[15]	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.