Molten Iron Temperature Research Articles

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

In blast furnace ironmaking operation, the molten iron temperature and the silicon content ([Si]) are two key molten iron quality (MIQ) indices. The measurement, modelling and control of these indices have always been of importance in metallurgic engineering and automation. In this study, data-driven methods for online prediction and control of multivariate MIQ indices are proposed by integrating hybrid modelling and control techniques together. First, a data-driven hybrid method that combines canonical correlation analysis and correlation analysis is proposed to identify the most influential controllable variables as the modelling inputs from multitudinous factors. Then a data-driven online model for prediction of MIQ is established by recursive subspace identification (R-SI) with forgetting factor. Unlike the conventional SI modelling, the proposed R-SI-based online modelling only identifies subspace matrices for a data-driven input-output model without explicitly estimating the system matrices, which can reduce the computation complexity. Finally, a predictive controller is designed to maintain the MIQ indices at an expected level by using the developed MIQ prediction model as an online predictor. Since the parameters of the predictor are updated adaptively by the latest process data, the predictive controller can produce more reliable and stable control performance. Experiments using industrial data have verified the superiority and practicability of the proposed methods.

Data-Driven Nonlinear Subspace Modeling for Prediction and Control of Molten Iron Quality Indices in Blast Furnace Ironmaking

Blast furnace (BF) in ironmaking is a nonlinear dynamic process with complicated physical-chemical reactions, where multiphases and multifields interactions with long time delay phenomena take place during its operation. In BF operation, the molten iron temperature as well as the Si content ([Si]), the phosphorus content ([P]), and the sulfur content ([S]) is the most essential quality (MIQ) indices. The measurement, modeling, and control of these indices have always been important issues in metallurgic engineering and automation. This paper proposes a novel data-driven nonlinear state-space modeling method for the prediction and control of multivariate MIQ indices by integrating hybrid modeling and control techniques together. First, to improve modeling efficiency, a data-driven hybrid method that combines canonical correlation analysis and correlation analysis is established to identify the most influential controllable variables as the modeling inputs from multitudinous factors. Then, a Hammerstein model for the prediction of MIQ indices is established using the Least squares support vector machine-based nonlinear subspace identification method. Such a model is further simplified by using piecewise cubic Hermite interpolating polynomial method. Compared with the original Hammerstein model, it has been shown that this simplified model can not only significantly reduce the computational complexity, but can also exhibit a good reliability and accuracy for a stable prediction of MIQ indices. In order to verify the practicability of the developed model, it is applied to the design of a genetic algorithm based nonlinear predictive controller for the multivariate MIQ indices by directly taking the established model as a predictor. Industrial experiments show the advantages and effectiveness of the proposed approaches.

Temperature measurement of molten iron in taphole of blast furnace combined temperature drop model with heat transfer model

The molten iron temperature in the taphole of a blast furnace (BF) is an important variable which reflects the internal heat of the BF. However, there is no method to detect the temperature directly. To solve this difficulty, an approach to measure the temperature of molten iron in taphole is proposed in this paper. First, during the stable tapping period, a heat transfer model is established according to the principle of equal heat flux of the trench walls, which is used to calculate the molten iron temperature at different positions in the main pipeline according to the temperature measured by thermocouples buried in trench walls. Next, a main pipeline temperature drop model is established based on the pipe temperature drop theory. Finally, the output of heat transfer model is used as the data source for parameter identification in the temperature drop model. The least-squares method is adopted to identify the molten iron temperature in the taphole. The proposed approach was validated in a practical industrial experiment at the #2 BF in an iron making plant. The results illustrate the effectiveness and rationality of the proposed approach and provides credible temperature data for the control of the BF.

Multivariable Dynamic Modeling for Molten Iron Quality Using Incremental Random Vector Functional-link Networks

Molten iron temperature as well as Si, P, and S contents is the most essential molten iron quality (MIQ) indices in the blast furnace (BF) ironmaking, which requires strict monitoring during the whole ironmaking production. However, these MIQ parameters are difficult to be directly measured online, and large-time delay exists in off-line analysis through laboratory sampling. Focusing on the practical challenge, a data-driven modeling method was presented for the prediction of MIQ using the improved multivariable incremental random vector functional-link networks (M-I-RVFLNs). Compared with the conventional random vector functional-link networks (RVFLNs) and the online sequential RVFLNs, the M-I-RVFLNs have solved the problem of deciding the optimal number of hidden nodes and overcome the overfitting problems. Moreover, the proposed M-I-RVFLNs model has exhibited the potential for multivariable prediction of the MIQ and improved the terminal condition for the multiple-input multiple-output (MIMO) dynamic system, which is suitable for the BF ironmaking process in practice. Ultimately, industrial experiments and contrastive researches have been conducted on the BF No. 2 in Liuzhou Iron and Steel Group Co. Ltd. of China using the proposed method, and the results demonstrate that the established model produces better estimating accuracy than other MIQ modeling methods.

Intelligent Multivariable Modeling of Blast Furnace Molten Iron Quality Based on Dynamic AGA-ANN and PCA

Blast furnace (BF) ironmaking process has complex and nonlinear dynamic characteristics. The molten iron temperature (MIT) as well as Si, P and S contents of molten iron is difficult to be directly measured online, and large-time delay exists in offline analysis through laboratory sampling. A nonlinear multivariate intelligent modeling method was proposed for molten iron quality (MIQ) based on principal component analysis (PCA) and dynamic genetic neural network. The modeling method used the practical data processed by PCA dimension reduction as inputs of the dynamic artificial neural network (ANN). A dynamic feedback link was introduced to produce a dynamic neural network on the basis of traditional back propagation ANN. The proposed model improved the dynamic adaptability of networks and solved the strong fluctuation and resistance problem in a nonlinear dynamic system. Moreover, a new hybrid training method was presented where adaptive genetic algorithms (AGA) and ANN were integrated, which could improve network convergence speed and avoid network into local minima. The proposed method made it easier for operators to understand the inside status of blast furnace and offered real-time and reliable feedback information for realizing close-loop control for MIQ. Industrial experiments were made through the proposed model based on data collected from a practical steel company. The accuracy could meet the requirements of actual operation.

Continuous Temperature Measurement of Liquid Iron and Slag Tapped from a Blast Furnace

Temperature measurements of liquid pig iron coming out of a blast furnace are essential for estimating the thermal condition in the hearth. The temperature is generally monitored by a disposable thermocouple on a runner. This paper proposes radiometric temperature measurement that targets an iron-slag-mixed stream in front of a taphole. It enables non-contact continuous thermometry. Liquid iron and slag are spatially separated on a thermal image obtained by a CCD camera with a high-speed electronic shutter. Molten iron temperature is calculated from the iron radiance detected automatically by means of histogram processing of the thermal image. Regarding optically semitransparent molten slag, its radiance varies as a function of the thickness. Slag temperature is determined from the highest radiance, presuming that the emittance of sufficiently thick slag converges on a constant. The authors performed an on-site test at a blast furnace in ordinary operation. It was confirmed that both iron and slag temperatures were continuously monitored. The temperature data obtained from the test showed findings such as unsteady temperature difference between the two liquids and discontinuous temperature fluctuation. This imaging thermometry technique is expected to be used in a new sensor for blast furnace operation.

Application of Improved Local Models of Large Scale Database-based Online Modeling to Prediction of Molten Iron Temperature of Blast Furnace

The large scale database-based online modeling called LOM is the one of local modeling method. This method has been developed to apply the just-in-time modeling for the blast furnace by us. In this paper, we propose two new types of local models in LOM to improve the prediction performance. One is used weighted multiple regression model as a linear local model of LOM. The other is used on-line Bayesian learning model as a nonlinear local model of LOM. In order to compare the prediction performance of the two types of local models in LOM, we evaluate the prediction performance by using the real process data of the blast furnace.

Reduction Behavior of Carbon Composite Iron Ore Hot Briquette in Shaft Furnace and Scope on Blast Furnace Performance Reinforcement

The reduction and melting behavior of carbon composite iron ore hot briquette in shaft furnace are discussed. As these agglomerates are made by the use of thermal plasticity of coal, the reduction rate by chain reactions in interface between ore and coal could be increased. The carbon composite iron ore hot briquettes achieve 95 % reduction degree in about 10-min descent time to the 1 100°C heat reserve zone bottom end and the drop of molten iron temperature is kept to 20°C. As a result, it is expected that these new agglomerates could decrease the fuel rate and discharging amount of CO 2 as well as have a possibility of extension of furnace life. Finally the paper ends by shaping the future of blast furnace on environmental phases for the new century. Especially, it is expected that carbon composite iron ore hot briquette lowers temperature of heat reserve zone and shortens the length, suggesting the possibility of shortening of the reserve zone (inactivity zone), that is, shortening of the blast furnace height.

A Multi-Model Cooperative System for Predicting SI-Content of Molten Iron on Blast Furnace

In this paper, a Multi-model Cooperative System is presented, it can predict the Si-content of molten iron on blast furnace. The system consists of a coordinator and thijee models, Self-tuning Prcdictor, Expert System for Si-prediction, and Si-prediction by Molten Iron Temperature. By combining mathematical model with artificial intelligence technology, the system has made the hit rate of Si-prediction increased from 60% (by experienced operators) to above 80% ([Si] ± 0.1%), in the bad conditions at Anshan Iron & steel Coperation of China.