Silicon content prediction and industrial analysis on blast furnace using support vector regression combined with clustering algorithms

Silicon content prediction is quite significant for supervising the state of blast furnace and is usually selected as the indicator to represent the thermal state. In practical industry, the fluctuation exists in the operation of blast furnace all the time. What’s worse, it is inaccurate to build the predictive model with many outliers. To solve these problems, this paper has developed a model to predict the silicon content using support vector regression (SVR) combined with clustering algorithms, including hard C-means (HCM) clustering and fuzzy C-means (FCM) clustering. Through data processing, the data points are clustered based on the similarity, and then different SVR models are established. In order to make full use of FCM, a new method using multiple SVRs and FCM based on membership degree (MFCM-SVRs) is proposed where the membership degree is applied to eliminate the outliers. Simulation results verify that the multiple SVRs based on HCM (HCM-SVRs) and MFCM-SVRs possess superiority in terms of accuracy and speed, which makes the method serve better for practical production.

[1]  Sen Zhang,et al.  A modified ELM algorithm for the prediction of silicon content in hot metal , 2014, Neural Computing and Applications.

[2]  Hakyeon Lee,et al.  Evaluation of new service concepts using rough set theory and group analytic hierarchy process , 2012, Expert Syst. Appl..

[3]  S. A. Akbar,et al.  A mathematical model to characterise effects of liquid hold-up on bosh silicon transport in the dripping zone of a blast furnace , 2011 .

[4]  Xinping Guan,et al.  Nonlinear generalized predictive control based on online least squares support vector machines , 2014, Nonlinear Dynamics.

[5]  Kuo-Ping Lin,et al.  A Novel Evolutionary Kernel Intuitionistic Fuzzy $C$ -means Clustering Algorithm , 2014, IEEE Transactions on Fuzzy Systems.

[6]  Ujjwal Maulik,et al.  Unsupervised Pixel Classification in Satellite Imagery Using Multiobjective Fuzzy Clustering Combined With SVM Classifier , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[7]  An Luo,et al.  Power Electronic Hybrid System for Load Balancing Compensation and Frequency-Selective Harmonic Suppression , 2012, IEEE Transactions on Industrial Electronics.

[8]  Luo Ping.  Prediction of Silicon Content in Hot Metal Based on SVR Optimized by Chaos Particle Swarm Optimization , 2009 .

[9]  Bijaya K. Panigrahi,et al.  A hybrid SVM-PSO model for forecasting monthly streamflow , 2013, Neural Computing and Applications.

[10]  Tingting Guo,et al.  Short-Term Load Forecasting for Electric Power Systems Using the PSO-SVR and FCM Clustering Techniques , 2011 .

[11]  G. H.Shakouri,et al.  Outlier detection in fuzzy linear regression with crisp input-output by linguistic variable view , 2013, Appl. Soft Comput..

[12]  Jian Chen,et al.  A predictive system for blast furnaces by integrating a neural network with qualitative analysis , 2001 .

[13]  Lizhi Cheng,et al.  Neighbourhood weighted fuzzy c-means clustering algorithm for image segmentation , 2014, IET Image Process..

[14]  Chuanhou Gao,et al.  Modeling of the Thermal State Change of Blast Furnace Hearth With Support Vector Machines , 2012, IEEE Transactions on Industrial Electronics.

[15]  Zhao Zaixin,et al.  Neighbourhood weighted fuzzy c-means clustering algorithm for image segmentation , 2014 .

[16]  Rong Zhu,et al.  Modeling of an Impinging Oxygen Jet on Molten Bath Surface in 150 t EAF , 2011 .

[17]  Jianping Li,et al.  Multiple-kernel SVM based multiple-task oriented data mining system for gene expression data analysis , 2011, Expert Syst. Appl..

[18]  Mario Vanhoucke,et al.  Support Vector Machine Regression for project control forecasting , 2014 .

[19]  Lin Shi,et al.  Model of Hot Metal Silicon Content in Blast Furnace Based on Principal Component Analysis Application and Partial Least Square , 2011 .

[20]  Chuanhou Gao,et al.  Rule Extraction From Fuzzy-Based Blast Furnace SVM Multiclassifier for Decision-Making , 2014, IEEE Transactions on Fuzzy Systems.

[21]  Witold Pedrycz,et al.  Set-valued samples based support vector regression and its applications , 2015, Expert Syst. Appl..

[22]  Cong Jin,et al.  Software reliability prediction model based on support vector regression with improved estimation of distribution algorithms , 2014, Appl. Soft Comput..

[23]  Chuanhou Gao,et al.  Binary Coding SVMs for the Multiclass Problem of Blast Furnace System , 2013, IEEE Transactions on Industrial Electronics.

[24]  Xiaowei Yang,et al.  A Kernel Fuzzy c-Means Clustering-Based Fuzzy Support Vector Machine Algorithm for Classification Problems With Outliers or Noises , 2011, IEEE Transactions on Fuzzy Systems.

[25]  Pierpaolo D'Urso,et al.  Fuzzy clustering of human activity patterns , 2013, Fuzzy Sets Syst..

[26]  T. Velmurugan,et al.  Performance based analysis between k-Means and Fuzzy C-Means clustering algorithms for connection oriented telecommunication data , 2014, Appl. Soft Comput..

[27]  Chenn Q. Zhou,et al.  Numerical analysis of blast furnace hearth inner profile by using CFD and heat transfer model for different time periods , 2008 .

[28]  Saibal Ganguly,et al.  A reduced order thermo-chemical model for blast furnace for real time simulation , 2007, Comput. Chem. Eng..

[29]  S. Du,et al.  Numerical analysis on transient thermal flow of the blast furnace hearth in tapping process through CFD , 2014 .

[30]  JuiHsi Fu,et al.  A multi-class SVM classification system based on learning methods from indistinguishable chinese official documents , 2012, Expert Syst. Appl..

[31]  Jiu-sun Zeng,et al.  Data-driven predictive control for blast furnace ironmaking process , 2010, Comput. Chem. Eng..

[32]  Xueyi Liu,et al.  Prediction of Silicon Content in Hot Metal Based on Bayesian Network , 2007, Third International Conference on Natural Computation (ICNC 2007).

[33]  Chi-Jie Lu.  Hybridizing nonlinear independent component analysis and support vector regression with particle swarm optimization for stock index forecasting , 2012, Neural Computing and Applications.

[34]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.