Silicon Content In Molten Iron Research Articles

Improved algorithm of extreme gradient boosting for predicting silicon content in large proportion pellet smelting process

The silicon content in molten iron is an important indicator, to characterize the temperature of blast furnace (BF) and the quality of molten iron, which is of great significance to the stable operation of large proportion pellets in the BF smelting. Aiming at the problem of poor prediction performance and insufficient accuracy of silicon content, a prediction model of silicon content in molten iron was established based on KMeans++ and improved XGBoost algorithm to divide the information from different BF conditions in the smelting process, The genetic algorithm(GA) was adopted to optimize the model iteratively, which improved the accuracy of the results and reduced the training time for optimal results. The experimental result showed that the prediction hit of the model was improved by clustering the data and reached above 90% on average, and the accurate prediction of silicon content in molten iron in case of a large proportion of pellets of BF smelting was realized.

Dynamic Prediction Model of Silicon Content in Molten Iron Based on Comprehensive Characterization of Furnace Temperature

The silicon content of the molten iron is an important indicator of the furnace temperature trend in blast furnace smelting. In view of the multi-scale, non-linear, large time lag and strong coupling characteristics of the blast furnace smelting process, a dynamic prediction model for the silicon content of molten iron is established based on the analysis of comprehensive furnace temperature characterization data. The isolated forest algorithm is used to detect anomalies and analyze the causes of the anomalies in conjunction with the blast furnace mechanism. The maximum correlation-minimum redundancy mutual information feature selection method is used to reduce the dimensionality of the furnace temperature characterization data. The grey correlation analysis with balanced proximity is used to obtain the correlation between the furnace temperature characterization parameters and the silicon content of the molten iron at different time lags and to integrate the furnace temperature characterization data set. The GRA-FCM model is used to divide the parameter set of the integrated furnace temperature characterization and construct a parameter directed network from multiple control parameters to multiple state parameters. The GWO-SVR model is used to predict the state parameters of each delay step by step to achieve dynamic prediction of the silicon content of the molten iron. Finally, the control parameters are adjusted backwards according to the prediction results of the state parameters and the silicon content of the molten iron and expert experience to achieve accurate control of the furnace temperature. Starting from the actual production situation of a blast furnace, the characteristic parameters are divided into control parameters and state parameters. This model establishes a multi-step dynamic prediction and closed-loop control model of “control parameters-state parameters-silicon content in hot metal-control parameters”.

A Multiobjective Evolutionary Nonlinear Ensemble Learning With Evolutionary Feature Selection for Silicon Prediction in Blast Furnace.

In the blast furnace ironmaking process, accurate prediction of silicon content in molten iron is of great significance for maintaining stable furnace conditions, improving hot metal quality, and reducing energy consumption. However, most of the current research works employ linear correlation coefficient methods to select input features in modeling, which may not fully take the nonlinear and coupling relationships between features into account. Therefore, this article considers the input feature selection issue of silicon content prediction model from a new perspective and proposes a multiobjective evolutionary nonlinear ensemble learning model with evolutionary feature selection mechanism (MOENE-EFS), in which extreme learning machine is adopted as the base learner. MOENE-EFS takes the input feature scheme of each base learner as well as their network structure and parameters as decision variables and proposes a modified nondominated sorting differential evolution algorithm to optimize two conflicting objectives, i.e., accuracy and diversity of base learners, simultaneously. Through the optimization, a set of Pareto optimal base learners with high accuracy and strong diversity can be obtained. Moreover, different from the linear ensemble methods commonly used in classical evolutionary ensemble learning, this article proposes a nonlinear ensemble method to combine the obtained base learners based on differential evolution. Experimental results indicate that the two proposed strategies, i.e., evolutionary feature selection and nonlinear ensemble, are very effective in improving the accuracy and stability of the prediction model. MOENE-EFS also outperforms the other prediction models in both benchmark data and practical industrial data. Furthermore, analysis on the input features of all Pareto optimal base learners shows that the evolutionary feature selection is capable of selecting essential features and is consistent with human experience, which indicates it is a promising method to deal with the input feature selection issue in silicon content prediction.

Forecasting Model of Silicon Content in Molten Iron Using Wavelet Decomposition and Artificial Neural Networks

Silicon content forecasting models have been requested by the operational team to anticipate necessary actions during the blast furnace operation when producing molten iron, to control the quality of the product and reduce costs. This paper proposed a new algorithm to perform the silicon content time series up to 8 h ahead, immediately after the molten iron chemical analysis is delivered by the laboratory. Due to the delay of the laboratory when delivering the silicon content measurement, the proposed algorithm considers a minimum useful forecasting horizon of 3 h ahead. In a first step, it decomposes the silicon content time series into different subseries using the Maximal Overlap Discrete Wavelet Packet Transform (MODWPT). Next, all subseries forecasts were determined through Nonlinear Autoregressive (NAR) networks, and finally, these forecasts were summed to furnish the long-term forecast of silicon content. Using data from a real industry, we showed that the prediction error was within an acceptable range according to the blast furnace technical team.

Double-hyperplane fuzzy classifier design for tendency prediction of silicon content in molten iron

It is very difficult to control a blast furnace efficiently because of the characteristics of the closed smelting and the system's large delay. It is very helpful for blast furnace control to establish a model that can accurately predict the tendency of silicon content in molten iron. In this article, a nonparallel hyperplane–based fuzzy classifier is proposed reconciling the model accuracy with the model interpretability. Each hyperplane is as close as possible to one class of samples and as far as possible from the other class of samples. This leads to two small quadratic programming problems instead of a large one as a support vector machine–based fuzzy classifier. This makes our classifier faster than a support vector machine–based fuzzy classifier. We evaluate the proposed method on blast furnace data and synthetic data, which verifies the effectiveness.

Classification of blast furnace internal state based on FLS and its application in furnace temperature prediction

The real-time and accurate prediction of the molten iron silicon content of the blast furnace plays an important role in regulating the temperature of the blast furnace and stabilizing the furnace condition. When the time is large, the accuracy and credibility of the forecast results decrease rapidly, which is not conducive to on-site operators to carry out production operations according to the forecast results. To this end, this paper adds a state variable to each piece of data through the flexible least square parameter estimation method, and selects the training set in a state similar to the test sample. This makes the selection of training data more accurate and reliable. Application examples show that the method proposed in this paper improves the accuracy of silicon content prediction results and has good guiding significance for actual production operations.

A Comparison Study of Subspace Identification of Blast Furnace Ironmaking Process

Blast Furnace (BF) iron making process is an extremely complex industrial process. The molten iron silicon content is considered as an important indicator of the thermal status of the blast furnace. The stabilization control of blast furnace depends on the molten iron silicon content. Three classic subspace identification methods including MOESP (Multivariable Output-Error State sPace), CVA (Canonical Variate Analysis) and SSARX (Subspace identification method ARX) are considered to establish the state space model of blast furnace ironmaking process. The inputs to the model are the most responsible and easily measured variables for the fluctuation of thermal state in blast furnace while the output to the model is the molten iron silicon content. The identified state space models are then tested on datasets obtained from No.1 BF in LiuGang Iron and Steel Group Co. of China. Experiment results show that the blast furnace ironmaking process can be reliably modeled by these subspace identification methods. Further, the SSARX method outperforms over the other two subspace identification methods with closed loop data.

Prediction method of silicon content in blast furnace hot metal based on IPSO-HKELM

Aiming at the problem that the silicon content of molten iron can not be detected online, a model for predicting silicon content in molten iron based on Hybrid Kernel Extreme Learning Machine optimized by Improved Particle Swarm Optimization Algorithm (IPSO-HKELM) is proposed. Firstly, the input variables are reduced by PCA, and then the prediction model of molten iron content based on HKELM is established. In this paper, PSO is used to optimize the kernel parameters of HKELM. Aiming at the problem that PSO is easy to fall into local optimum, the Inertia weight reduced with the number of iterations and the random back-based learning mutation operation are introduced, so that PSO can jump out of the local minimum point more easily and get the optimal result. Experiments show that the prediction model of silicon-based silicon content based on IPSO-HKELM has high prediction accuracy and short time, which can meet the actual production needs.

Research on Intelligent Manufacturing Problem in Process Industry

In this paper, the practical problems of blast furnace iron making are considered, taking into account the influence of sulfur content [S], coal injection volume PML, blast volume FL and molten iron silicon content [Si], and extracting parameters according to data and data analysis. Because the parameters of this problem are more parameters and the nonlinear relationship is stronger, the control of parameters in the BP neural network model has become the focus of this paper. This paper finds that the BP neural network prediction model has a relatively high success rate for both numerical and furnace temperature rise and fall directions, and has wide applicability. At the same time, in the context of intelligent manufacturing in the process industry, the blast furnace iron making process can be greatly optimized, which is reflected in the reduction of raw material usage, production increase, and emission reduction.

Study on Carbothermal Reduction of Titania in Molten Iron

Abstract In order to improve the reduction rate of titania in molten iron, various iron powders containing C, Si, Mn and S were melted. The experiments were carried out on the reduction of titania through a high-temperature tube furnace at 1,723–1,823 K. The quantitative effects of C, Si, Mn, S and temperature on the reduction of titania were investigated in the current study. The results demonstrated that when the carbon content, the manganese content and the temperature increased by 1 %, 0.1 % and 100 K, the reduction rate increased by 0.008 %/h, 0.001125 %/h and 0.0235 %/h, respectively; when the sulfur content increased by 0.01 %, the reduction rate decreased by 0.004875 %/h; the reduction rate was irregular with the change of silicon content in molten iron. The phase at the reaction interface after the experiment was confirmed to be the Fe2Ti3O9 which was considered to be the combination product between iron oxide and titania; the lower titanium oxides were unstable and hard to be observed. The reduction was affected by the concentration of various elements in molten iron and the activity interaction coefficients between various elements. The rate constants for reduction were calculated at 1,723 K, 1,773 K and 1,823 K; the apparent activation energy was calculated as 209 kJ/mol through the rate constants and temperatures according to the Arrhenius equation.

Preparation of an electrochemical sensor for measuring the silicon content in molten iron

A silicon sensor for measuring the silicon content in molten iron that included a new membrane electrode was synthesized by coating a slurry of CaF2, SiO2 and 5% Polyvinyl alcohol (PVA) onto the surface of a ZrO2 (MgO) solid electrolyte tube, followed by sintering in a high purity Ar atmosphere. The influences of the preparation conditions, such as the chemical composition, solid (CaF2+SiO2 powder) to liquid (5% PVA solution) ratio and sintering temperature, on the coating layer adhesive properties, active ingredients and detection performance of the formed auxiliary electrode layer were systematically investigated. It is indicated that the synthesized coating layer showed strong adhesive properties and the main active ingredients were SiO2 (ZrSiO4) solid particles-CaO·MgO·2SiO2 solid solution under the optimum preparation conditions. The as-prepared silicon sensor, which was used to detect the silicon content in molten iron at 1450°C, exhibited superior performance. When the silicon content ranged from 0.5 to 1.5% in liquid iron, the testing result from the silicon sensor with a response time of 15s and steady time greater than 30s agreed well with the values from the chemical analysis method.

Data-Driven Dynamic Modeling for Prediction of Molten Iron Silicon Content Using ELM with Self-Feedback

Silicon content ([Si] for short) of the molten metal is an important index reflecting the product quality and thermal status of the blast furnace (BF) ironmaking process. Since the online detection of [Si] is difficult and larger time delay exists in the offline assay procedure, quality modeling is required to achieve online estimation of [Si]. Focusing on this problem, a data-driven dynamic modeling method is proposed using improved extreme learning machine (ELM) with the help of principle component analysis (PCA). First, data-driven PCA is introduced to pick out the most pivotal variables from multitudinous factors to serve as the secondary variables of modeling. Second, a novel data-driven ELM modeling technology with good generalization performance and nonlinear mapping capability is presented by applying a self-feedback structure on traditional ELM. The feedback outputs at previous time together with input variables at different time constitute a dynamic ELM structure which has a storage ability to tackle data in different time and overcomes the limitation of static modeling of traditional ELM. At last, industrial experiments demonstrate that the proposed method has a better modeling and estimating accuracy as well as a faster learning speed when compared with different modeling methods with different model structures.

Fuzzy Prediction of Molten Iron Silicon Content in BF Based on Hierarchical System

A hierarchical fuzzy system model is presented based on data driving, and then, the model is used to predict the molten iron silicon content in BF. As input variables this model uses the control parameters of a current BF such as moisture, pulverized coal injection, oxygen addition, coke ratio etc. And variables employed to develop the model have been obtained from data collected online from Blast Furnace of Baotou Steel plant. This paper utilizes the fuzzy clustering algorithm combined nearest neighbor clustering and fuzzy c-means clustering to classify the input space. The simulation and error results show that the prediction based on hierarchical fuzzy model and data-driven method has good approximation and fit the output characteristics of the system. The most important point is that the number of fuzzy rules is greatly reduced.

The fractal structure of silicon content in molten iron in blast furnace

With ［Si］ time series of No. 1 BF at Laiwu Iron and Steel Group Co. and No.6 BF at Linfen Iron and Steel Group Co. as sample space, and based on rescaled range analysis and method of box dimension, the Hurst exponents of ［Si］ time series of these two BFs and the box dimensions are figured out to be ranging from 0.257 and 0.224 and 1.712 and 1.724, respectively. The complex degree of ［Si］ time series is described, and it is also proved that ［Si］ time series is a long-term negative association fractal time series. With the correlative parameter fixed, the simulated trend was pictured by the theory of iterated function system.

Chaotic analysis for blast furnace ironmaking process

Based on the algorithm of Kolmogorov entropy presented by Grassberger and Procac cia, as the time series data of silicon content in molten iron of No.1 BF at Laiwu and No.6 BF at Linfen Iron and Steel Group Cos. to be as samples, their Kolmo gorov entropy are computed to be (01453±00151)nats·h-1-1 an d (01553±00140)nats·h-1-1, and the time scales of forecasti ng in both BFs are estimated to be about 688 and 644h respectively. Since the value of Kolmogorov entropy is finite and positive, there is chaos in both b last furnace ironmaking processes, and the idea that Kolmogorov entropy may be u sed to judge the condition of BF is presented.

Modified chaotic adding weight one_rank local_region forecasting for silicon content in molten iron of blast furnace

Based on the usual chaotic-weighting first-rank local-region forecas ting model, a modification is made for the predictor in matrix and vector simulation instead of single variant. Then the modified forec asting model is applied to pr edict silicon content in molten iron of the medium-sized blast furnace in China, and good results are obtained. Finally, we find that the value of Kolmogo rov entropy has a great effect on the hitting accuracy of the prediction .

Development of zirconia electrolyte sensor with auxiliary electrode for the in situ measurement of dissolved silicon in molten iron

In Japan, hot metal pretreatments, such as desiliconization and dephosphorization processes, are applied in most steel making companies. The key to better operation of desiliconization is to use a sensing device that allows the silicon content in molten iron to be rapidly determined. Accordingly, we have investigated a zirconia electrolyte sensor with an auxiliary electrode for the instantaneous measurement of the silicon content in molten iron. To study the effects of the auxiliary electrode, four kinds of silicon sensors coated with various forms of ZrO 2/ZrSiO 4 mixtures as an auxiliary electrode have been tested. These sensors are used for measuring the electromotive force (e.m.f.) of iron melt in a 300 kg induction furnace. The response time becomes shorter with increasing boundary density of the auxiliary electrode. Furthermore, there appears to be a better correlation between e.m.f. and silicon activity in molten iron with the use of a high boundary density. These results indicate that a kind of equilibrium, in which a SiO 2 is fixed, is formed rapidly with the increase of boundary density at the hot metal/solid electrolyte/auxiliary electrode triphasic interface. Using this sensor, the silicon content in molten iron can be estimated to within ±0.015% Si by measuring the e.m.f. and the metal temperature.