Nonlinear Prediction of the Hot Metal Silicon Content in the Blast Furnace

Saxén, Henrik; Pettersson, Frank

doi:10.2355/isijinternational.47.1732

Cited by 108 publications

(74 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the method is somewhat sensitive to the initial weights, it is usually advisable to start from many random starting points (i.e., weight matrices) and make a statistical evaluation of the results. 25) In order to treat the problem in the same way as in the previous subsection, an analysis with the following setup was undertaken: All the seven individual lengths (i.e., l i , iϭ1, …, 6 and Dl) as well as all the remaining combinations required to cover the cases in Eq. (3), i.e., l 1 ϩl 2 , l 1 ϩl 3 , l 2 ϩl 3 , l 1 ϩl 2 ϩl 3 , l 4 ϩl 5 , l 4 ϩl 6 , l 5 ϩl 6 and l 4 ϩl 5 ϩl 6 were used as inputs.…”

Section: Detection Of Optimal Inputs and Networkmentioning

confidence: 99%

Assessment of the State of the Blast Furnace High Temperature Region by Tuyere Core Drilling

2009

Self Cite

View full text Add to dashboard Cite

Tuyere core drillings give a unique opportunity to probe the blast furnace and detect changes in both physical and chemical conditions of its high-temperature region. In this paper the findings from drill cores taken from a blast furnace are used to characterize the internal state of the furnace hearth, quantified by an erosion model estimating the available hearth volume. The complex relation is studied by entertaining neural network models using different combinations of inputs consisting of the extent of the distinct tuyerelevel zones (raceway, bird's nest, dead man, etc.) of the core samples. The resulting model can be used to gain knowledge of the relation between tuyere level conditions and hearth states, and to classify the findings from future core drillings. The results also throw light on possible reasons for thermal cycles observed in the hearth of the furnace studied.KEY WORDS: tuyere core drillings; blast furnace; hearth state; neural network pruning. 203© 2009 ISIJ ternative, tuyere core drillings have been used at many plants since the 1990's 5-7) : A steel pipe is drilled into the furnace through an opened tuyere at a stoppage, and the pipe with its core filled with the bed is withdrawn, quenched and opened for analysis. Typically, the length of the distinct regions, the particle size of the coke, the metallurgical and mineralogical state of the materials and the presence of iron and slag in the sample are analyzed.Tuyere drillings are performed regularly at Rautaruukki's two blast furnaces during shorter stoppages.9) The sample tubes are 5.5 m long and the withdrawn core has a diameter of 205 mm; typically, the core length is shorter than the maximum drill penetration, l max , into the bed due to compression of the core. The drill penetration, in turn, depends on the physical state of the dead man. After drilling, the core samples are analyzed physically and chemically. In the present work, the modeling effort is focused on the lengths of the different sections identified in the drill core (cf. Fig. 1). Based on the characteristics of the sampled coke and iron, the core is divided in to six regions (with the corresponding number given in parentheses): (1) bosh, (2) flame, (3) raceway, (4) bird's nest, (5) iron agglomerate, and (6) dead man, and their lengths l i (iϭ1...6) are recorded. The difference between the maximum penetration of the drill and the total core length, l c ϭ∑ 6 iϭ1 l i represents the total compression of the sample, Dlϭl max Ϫl c . These lengths from twenty two drill core samples from one of the Rautaruukki furnaces were used for modeling (cf. Table 1). Figure 2 shows a photograph of a core with the different regions indicated. Lining Temperatures and Heath VolumeThe internal state of the furnace hearth can be assessed on the basis of refractory temperatures measured by thermocouples in the hearth bottom and sidewall lining. These temperature measurements can be used to estimate the remaining thickness of the lining and also formation of buildup material (skull) on the hot fa...

show abstract

Section: Detection Of Optimal Inputs and Networkmentioning

confidence: 99%

Assessment of the State of the Blast Furnace High Temperature Region by Tuyere Core Drilling

2009

Self Cite

View full text Add to dashboard Cite

show abstract

“…On the other hand, although moving-window-based recursive soft sensors can gradually be adapted to new operational conditions, how to choose a suitable moving-window size for complex blast furnace ironmaking processes is difficult. 10,11,17) Additionally, most recursive models may not function well in a new operational region until a sufficient period of time has passed because of the time delay when they adapt themselves to new operational conditions. Recently, the just-in-time LSSVR (JLSSVR) modeling approach has been applied to industrial ironmaking processes.…”

Section: Introductionmentioning

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%

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

“…This is one of the reasons that prediction of silicon content has attracted considerable research interests; among them are models like statistical model 1) and fuzzy models, 2,3) neural networks and nonlinear methods. [4][5][6] Recently, several researchers have paid attention to the chaotic and fractal characteristics of silicon content in ironmaking process, 7,8) which clearly indicates a strong nonlinearity. It is also shown in Ref.…”

Section: Introductionmentioning

confidence: 99%

Wiener Model Identification of Blast Furnace Ironmaking Process

et al. 2008

View full text Add to dashboard Cite

To account for the nonlinearity of blast furnace ironmaking process, a nonlinear Wiener model identification algorithm is presented. The system consists of a linear time invariant (LTI) subsystem followed by a static nonlinearity. The inverse of the nonlinearity is assumed to be a linear combination of known nonlinear basis functions and the linear subspace algorithm is used to identify the model. The inputs to the model are parameters regarded to be most responsible for the fluctuation of thermal state in blast furnace while the output to the model is silicon content in hot metal. The identified Wiener model is then tested on datasets obtained from No. 6 Blast Furnace from Baotou Steel. It is found that the blast furnace of concern is a short memory system, so that for each prediction the Wiener method is retrained. It is shown that the retrained model well improves the predictive accuracy.KEY WORDS: blast furnace iron-making; silicon content; Wiener model; subspace algorithm. the chamber, so that chemical reactions take place throughout the furnace as the material moves downward. The end products are usually molten iron and slag phases tapped from the bottom, and flue gases exiting from the top of the furnace.The critical operating parameters are the temperature and silicon content in hot metal. It has been shown that silicon content has a linear approximation relation with temperature. Furthermore, the silicon content is a good measure of the heat content and the course of the blast furnace process. Therefore, only silicon content is chosen as an output variable for the process model. In the meantime, a large number of variables are monitored and they become the basis for the blast furnace operators to judge the status of blast furnace. Since not all monitored process variables have an influence on the fluctuation of silicon content in hot metal, selections must be made. According to engineering knowledge and controllability of variables, we select out 7 process variables 20) as the model inputs and silicon content in hot metal as the model output to construct the predictive model. These process variables include: the quantity of blast, the temperature of blast, the pressure of blast, the quantity of coal powder, the pressure of top gas, the coke ratio and the quantity of oxygen. Delay time for each input variable for this specific blast furnace is given in Table 1. Subspace MethodsSubspace methods are a relatively recent development in the field of system identification which is most suitable for multi-variable identification. There are 3 main subspace methods, i.e., N4SID developed by van Overschee and De Moor, 15) CVA developed by Larimore 16) and MOESP developed by Verhaegen and Dewilde. 17) For the 3 algorithms, N4SID and CVA have been seen much more applications. The CVA algorithm was based on mathematical statistics and time series analysis methods while the N4SID algorithm is more closely related to linear system theory. For the present work, we use the N4SID algorithm to identify the linear block of...

show abstract

Nonlinear Prediction of the Hot Metal Silicon Content in the Blast Furnace

Cited by 108 publications

References 20 publications

Assessment of the State of the Blast Furnace High Temperature Region by Tuyere Core Drilling

Assessment of the State of the Blast Furnace High Temperature Region by Tuyere Core Drilling

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

Wiener Model Identification of Blast Furnace Ironmaking Process

Contact Info

Product

Resources

About