Modeling of the Thermal State Change of Blast Furnace Hearth With Support Vector Machines

Gao, Chuanhou; Jian, Ling; Si, Luo

doi:10.1109/tie.2011.2159693

Cited by 140 publications

(55 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…40) Additionally, the hit rate (HR) index is often adopted in industrial blast furnace ironmaking processes. [21][22][23][24][25][26][27][28] Three indices of RMSE, RE, and HR are defined, respectively. (18) where ŷ q and y q are the predicted value and the actual value, respectively.…”

Section: Industrial Silicon Content Predictionmentioning

confidence: 99%

“…To online predict the silicon content, various data-driven soft sensor modeling approaches, including various neural networks, [7][8][9][10][11][12][13][14] partial least squares, 14,15) fuzzy inference systems, 16) nonlinear time series analysis, [17][18][19][20] subspace identification, 21) support vector regression (SVR) and least squares SVR (LSSVR), [22][23][24] and others [25][26][27][28][29] have been investigated. A recent overview of black-box models for short-term silicon content prediction in blast furnaces can be referred to.…”

Section: Introductionmentioning

confidence: 99%

“…[30][31][32] Among them, SVR and LSSVR have shown promising prediction performance, especially when the training data are insufficient. [22][23][24]33) One main disadvantage of most existing data-driven modeling approaches for the silicon content is that a single global model is built. However, it is not enough to describe all the process characteristics only using a single model, [34][35][36][37][38][39][40] especially for some complicated regions with insufficient information.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Adaptive Weighting Just-in-Time-Learning Quality Prediction Model for an Industrial Blast Furnace

Chen

Liu

2017

ISIJ Int.

View full text Add to dashboard Cite

Development of accurate soft sensors for online quality prediction (e.g., silicon content) in an industrial blast furnace is a difficult task. A novel just-in-time-learning (JITL) prediction approach using adaptive feature-weighting for similar samples is developed. First, a dual-objective joint-optimization framework is proposed to introduce both input and output information into the model. Then, a suitable similarity criterion with feature weighting strategy is formulated, which is not considered in conventional JITL methods. Moreover, the trade-off parameter in the joint-optimization problem can be chosen automatically, without the time-consuming cross-validation procedure. The proposed method is applied to online predict the silicon content in an industrial blast furnace in China. Compared with other JITL-based soft sensors, better prediction performance has been obtained.

show abstract

Section: Industrial Silicon Content Predictionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Weighting Just-in-Time-Learning Quality Prediction Model for an Industrial Blast Furnace

Chen

Liu

2017

ISIJ Int.

View full text Add to dashboard Cite

show abstract

“…Because of the severe lag characters of BF, the conditions of BF is generally under "reasonable-deteriorative-reasonable"repeatedly state. It is essential to carry out the prediction for the descent speed of burden layer for the operators to adjust the next charging and maintain the stable running of BF (Gao and Jian, 2012).…”

Section: Introductionmentioning

confidence: 99%

Prediction of Burden Descent Speed Based on Improved Extreme Learning Machine

2016

Rev. Téc. Ing. Univ. Zulia

View full text Add to dashboard Cite

The shape of burden surface is an important indicator that relates closely to working condition in blast furnace. It is the most important for the operators to master the position and descent speed of burden layer, and can guide the operators for the next burden charging. This paper utilizes an advanced predictive technique, called extreme learning machine, to develop a descent speed prediction model of burden layer according to radar data and status information in blast furnace.At the same time, in order to improve generalization ability of extreme learning machine algorithm, the parameters of network are optimized by using Fishing Strategy. In the simulation part, we have collected the raw production data in iron-making process, and have obtained the satisfied results by using the proposed approach.

show abstract

“…Up until now, some typical data-based control methods have been developed, for example: iterative feedback tuning (IFT), iterative learning control (ILC), model free adaptive control (MFAC), simultaneous perturbation stochastic approximation (SPSA), and virtual reference feedback tuning (VRFT), etc. We can divide them into two broad categories: the first one needs to perform system identification and establish the approximate models with the measured data first, using approaches such as neural networks (NN) [7]- [9] [10] and support vector machines (SVM) [11]- [13], and then designs the controllers according to these approximate models; the other one could directly control the system with the measured data, where no model identification of the plant is needed, but it is subject to some kind of restrictions or prior assumptions.…”

Section: Introductionmentioning

confidence: 99%

A Data-Based State Feedback Control Method for a Class of Nonlinear Systems

Wang

Liu

2013

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

Abstract-In this paper, a data-based state feedback control method is developed for a class of nonlinear systems. It is a real-time control method, which requires little prior knowledge about the system dynamics, and does not need to know or to build the mathematical model of the system. We apply a fast sampling technique to sample the state signal, which contains useful information of the system. The zero-order hold (ZOH) and the control switch are also used to obtain system information. The feedback gain matrix is calculated and adjusted according to these sampled data. Theoretical analysis on the convergence and simulation results demonstrate the feasibility of this data-based control method.Index Terms-Control switch, data-based state feedback control, fast sampling technique, nonlinear systems, real-time control, sampled state data, zero-order hold.

show abstract

Modeling of the Thermal State Change of Blast Furnace Hearth With Support Vector Machines

Cited by 140 publications

References 30 publications

Adaptive Weighting Just-in-Time-Learning Quality Prediction Model for an Industrial Blast Furnace

Adaptive Weighting Just-in-Time-Learning Quality Prediction Model for an Industrial Blast Furnace

Prediction of Burden Descent Speed Based on Improved Extreme Learning Machine

A Data-Based State Feedback Control Method for a Class of Nonlinear Systems

Contact Info

Product

Resources

About