Intelligent multivariable modeling of blast furnace molten iron quality based on dynamic AGA-ANN and PCA

Slag foaming directly affects the productivity and quality of steel during the electric arc furnace (EAF) process. Therefore, the slag foaming height needs to be monitored in real-time. However, direct measurement of the slag foaming height is difficult to achieve because the inside of the EAF consists of harsh environments, i.e., high temperature and the presence of gas and dust. A stepwise regression model of the slag foaming height was created using sensor data from the EAF. A total of 272 operational data sets from the EAF process were used to develop and validate the regression model. This data came from 140ton DC-EAF of Dongkuk Steel in Pohang, Korea. We randomly selected 80% of the data for developing the regression model; the remaining 20% of data were used for model validation. The model was validated using the validation benchmark coefficient of determination (R2) and correlation coefficients. As a result, the important variables of slag foaming were statistically selected a priori. Using the regression model, the slag foaming height can be predicted without additional sensors. Based on the developed model, the effects of oxygen injection and carbon injection on the slag foaming height of EAF were predicted and are discussed herein.

show abstract

“…Also, the distribution and autocorrelation of error as shown in Figures 3c, 3d, 4c and 4d indicate that the model is a good model. [37,38].…”

Section: Modeling Resultsmentioning

confidence: 99%

Modeling of slag foaming height of electric arc furnace using stepwise regression analysis

Lee

Kim

Hwang

et al. 2020

Metall. Res. Technol.

View full text Add to dashboard Cite

show abstract

“…However, the operation of BF ironmaking is complicated by high temperature, high pressure and hermetic environment. It is also complicated by multiphase coupling and multi-physics field coexisting [6], [10], [11]. These complexities exhibit a great challenge to develop an applicable first-principle model for estimating and reliably controlling these quality indices.…”

Section: Introductionmentioning

confidence: 99%

Recursive Learning-Based Bilinear Subspace Identification for Online Modeling and Predictive Control of a Complicated Industrial Process

2020

Self Cite

View full text Add to dashboard Cite

In this paper, a recursive learning based bilinear subspace identification (R-B-SI) algorithm is proposed for online modeling and data-driven predictive control of blast furnace (BF) ironmaking process with strong nonlinear time-varying dynamics. Different from the existing linear SI algorithms, the R-B-SI algorithm can make full use of the process data information by adding the Kronecker product term of input data and the Kronecker product term between input and output data into the data block Hankel matrices. Moreover, the parameters of the R-B-SI model can be updated online with the latest data using recursive learning. In order to adjust the sensitivity of the algorithm to the data at different sampling times, the forgetting factor is introduced into the involved recursive learning as well. Therefore, the nonlinear time-varying dynamics of process can be well captured and described by the R-B-SI model. As a result, the data-driven predictive controller designed by the R-B-SI prediction model with parameter adaption is always capable of achieving satisfactory control performances regardless of the variation in various process operating conditions. Data experiments using actual industrial data have verified the practicability and superiority of the proposed methods. INDEX TERMS Recursive bilinear subspace identification, online modeling, recursive learning, data-driven predictive control, blast furnace ironmaking process, nonlinear time-varying dynamics.

show abstract

“…In many countries, such as China, the steel industry is playing an important role in the national economy, and there are thus extensive interests in modelling and control of ironmaking BF. The control of BF system often means to control the final molten iron quality (MIQ) indices, which are generally characterised by the molten iron temperature (MIT) and the Si content ([Si] for short) [7]. The MIT is the essential index reflecting the thermal state, energy consumption and quality of hot metal.…”

Section: Introductionmentioning

confidence: 99%

“…Nowadays, adjustment of the MIQ indices still largely relies on manual operations of experienced on‐site operators, who monitor the status of the process and take proper actions to control the MIQ indices [1, 7, 8]. The main bottleneck is that direct online measurement on these quality indices is difficult to be realised with existing conventional sensors [8].…”

Section: Introductionmentioning

confidence: 99%

“…In the past decades, data‐driven modelling technologies for BF ironmaking has made significant progress, and some models have been proposed to predict the MIQ indices. Typical examples of these models are time series models [2], statistical models [2, 4, 9, 10], neural network models [2, 7, 8, 11], support vector machine models [5, 6, 12, 13], as well as other artificial intelligence models [2]. For example, Zeng et al [14, 15] established an input–output model for [Si] prediction using subspace identification method, and Marutiram and Radhikrishnan [16] developed an Auto‐Regressive and Moving Average model for [Si] prediction using linear regression method.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Data‐driven recursive subspace identification based online modelling for prediction and control of molten iron quality in blast furnace ironmaking

Zhou

Dai

Song

et al. 2017

IET Control Theory & Applications

Self Cite

View full text Add to dashboard Cite

Intelligent multivariable modeling of blast furnace molten iron quality based on dynamic AGA-ANN and PCA

Cited by 32 publications

References 14 publications

Modeling of slag foaming height of electric arc furnace using stepwise regression analysis

Modeling of slag foaming height of electric arc furnace using stepwise regression analysis

Recursive Learning-Based Bilinear Subspace Identification for Online Modeling and Predictive Control of a Complicated Industrial Process

Data‐driven recursive subspace identification based online modelling for prediction and control of molten iron quality in blast furnace ironmaking

Contact Info

Product

Resources

About