Chemical Composition Of Sinter Research Articles

Prediction of Sinter Chemical Composition Based on Ensemble Learning Algorithms

Prediction of Sinter Chemical Composition Based on Ensemble Learning Algorithms

Thermodynamic modeling of zinc recovery from ferrous metallurgy sludge

Ferrous metallurgy enterprises continuously fill dumps with steelmaking and blast furnace sludge with high zinc content. Sludge occupying significant territories of enterprises is not involved in production and harms the environment. Since zinc leads to the formation of deposits in the blast furnace, manufacturers cannot involve this sludge in sinter processing. In addition, working with sludge can lead to problems such as decrease in iron content in the sinter, decrease in productivity of sintering machines, and increase in fluctuations in the sinter chemical composition. At the same time, zinc-containing sludge can become a valuable secondary product. Zinc remains a scarce metal, which encourages the development of technologies for processing zinc-containing materials. Extraction of zinc from sludge is difficult because it is not in oxide, but in sulfate or sulfide forms. In this paper, the possibilities of zinc extraction from sludge using the FactSage software package are evaluated. The authors present results of thermodynamic calculations of the possibility of zinc extraction from four types of sludge from two Russian ferrous metallurgical plants – EVRAZ NTMK and MECHEL. The data of chemical and phase analyses of this sludge are considered, as well as simulated graphs of zinc extraction dependencies from them. The graphs were built on basis of the received data from FactSage package. Addition of the reducing agent to the sludge varied, as well as temperature of the process. In addition, the possibility of abandoning carbon as a reducing agent was evaluated. To save the reducing agent, an optimal mixture of the company’s sludge was selected, in which coke consumption can be minimized.

ESTIMATION OF INFLUENCE OF VARIOUS TYPES OF FLUXES ON THE CHEMICAL COMPOSITION OF CHROMITE SINTER

The calculation of sinter chemical composition from chromite fines and various silica and alumina-silica fluxing agents was made and described.

Using BP Neural Network to Predict the Sinter Comprehensive Performance: TFe and Fuel Consumption

The principal objective of blast furnace is to produce high quality molten iron at a high rate with a low consumption. It is very important to control sinter chemical composition and comprehensive performance. This is because the sinter is the main raw material for ironmaking. In this paper, a predictive system for sinter chemical composition TFe and the solid fuel consumption was established based on BP neural network, which was trained by actual production data. The MATLAB m file editor was used to write code directly in this paper. Practical application shows the applications of the system not only can reduce the work difficulty of technical personnel, but also can improve the hit ratio of production index and the productivity.

Using BP Neural Network to Predict the Sinter Comprehensive Performance: FeO and Sinter Yield

Sinter is the main raw material for ironmaking. It is very important to control sinter chemical composition and comprehensive performance. In this paper, a predictive system for sinter chemical composition FeO and the sinter yield was established based on BP neural network, which was trained by actual production data. The MATLAB m file editor was used to write code directly in this paper.The application results show that the prediction system has high accuracy rate, stability and reliability, the sintering productivity was improved effectively.

Prediction Model of the Sinter Comprehensive Performance Based on Neural Network

The sinter quality and the stability of composition could directly affect the yield, quality and energy consumption of ironmaking production. It is important for iron and steel industry to steadily control sinter chemical composition and analyze sintering energy consumption. The MATLAB m file editor was used to write code directly in this paper. A predictive system for two important sinter chemical composition (TFe and FeO), sinter output and sintering solid fuel consumption of was established based on BP neural network, which was trained by actual production data.) The application results show that the prediction system has high accuracy rate, stability and reliability, the sintering productivity was improved effectively.

Experience with Stabilization of the Chemical Composition of Sinter by Means of the MAYA on-Line Analyzer

The raw materials used to make sinter vary in their composition, which is one of the main obstacles to stabilizing the iron content and basicity of sinter. Automated real-time monitoring of the chemical composition of those materials with the MAYA laser analyzer made by the company Laser Distance Spectrometry makes it possible to obtain information on these parameters in the on-line regime and use them for real-time correction of charge composition. An automated system for flux-batching that was developed at the Novolipetsk Metallurgical Combine on the basis of the MAYA laser analyzer is making it possible to stabilize the composition of the sinter. The use of more stable sinter in turn leads to a reduction in coke use in blast furnaces.

Application of expert system for controlling sinter chemical composition

A predictive model of sinter chemical composition was developed to predict R (CaO/SiO2), TFe and SiO2 (CaO is calculated from R and SiO2). Based on the backpropagation neural network algorithm, it used the predictive result as a precondition. An expert system was designed to assist in controlling the sinter chemical composition by estimating the change of all the relative chemical components and providing the necessary adjustment. After the system commenced, the hit ratio of the predictive model was consistently over 90% and the goal of controlling chemical composition was achieved.

Real-time operation guide system for sintering process with artificial intelligence

In order to optimize the sintering process, a real-time operation guide system with artificial intelligence was developed, mainly including the data acquisition online subsystem, the sinter chemical composition controller, the sintering process state controller, and the abnormal conditions diagnosis subsystem. Knowledge base of the sintering process controlling was constructed, and inference engine of the system was established. Sinter chemical compositions were controlled by the strategies of self-adaptive prediction, internal optimization and center on basicity. And the state of sintering was stabilized centering on permeability. In order to meet the needs of process change and make the system clear, the system has learning ability and explanation function. The software of the system was developed in Visual C++ programming language. The application of the system shows that the hitting accuracy of sinter compositions and burning through point prediction are more than 85%; the first-grade rate of sinter chemical composition, stability rate of burning through point and stability rate of sintering process are increased by 3%, 9% and 4%, respectively.

Investigation of sinter plant production rate and RDI by neural networks

Data from the Rautaruukki Raahe sinter plant were analyzed with feed-forward neural networks. The resulting models were used to investigate and optimize the sinter plant production rate and the reduction degradation index (RDI) that is an important sinter quality indicator for small blast furnaces. Especially, the effects of controllable parameters such as the chemical composition of sinter, physical conditions of raw materials and factors reflecting the sintering event were studied.

Optimization of Chemical Composition and Microstructure of Iron Ore Sinter for Low-temperature Drip of Molten Iron with High Permeability

To discuss sinter condition for lowering dripping temperature of molten iron and enhancing reducibility, reduction behavior of sinter samples with extensive range of chemical composition was measured with reduction test under load. Basicity was found to have dominant influence on dripping temperature and should be in the range between 1.0 and 1.5. A further decrease in dripping temperature was achieved by decreasing Al2O3 content and increasing MgO content in sinter, which was related with low liquidus temperature, low viscosity and fast smelting-reduction of slag containing low FeO content. In contrast, reducibility and mineralogy of sinter influenced softening-melting behavior as well. Increasing fine pores could improve softening-melting behavior as a result of enhancing reducibility. Finally optimized sinter, containing 1.0-1.5 basicity, low Al2O3 and high MgO content was proposed. This chemical composition of sinter could lower dripping temperature by 80°C with fairly high permeability of sinter layer compared to conventional sinter. Possibility of the further improvement of softening-melting behavior at a constant chemical composition with controlling sinter mineralogy was discussed.

Production of Sinter of a Prescribed Chemical Composition

Improving the quality of the iron-ore-based materials used in blast-furnace smelting is an effective means of reducing coke consumption and improving the other technical-economic indices that characterize the production of pig iron. One important factor in solving this problem is narrowing the range of fluctuation of the iron content and basicity of the sinter. The chemical composition of sinter can be stabilized by carefully averaging the iron ores used to make the sinter. However, since such averaging is precluded by the limited storage space available at the sinter plant of ISPAT-Karmet, the combine has developed a technology to make sinter of stable chemical composition. The key elements of the technology: obtaining representative samples of the materials; forming piles of mixtures of ores; calculating the chemical composition of the planned piles; determining consumption factors for the components of the charge, in order to obtain sinter of the prescribed chemical composition; using an express method to determine the losses incurred during sintering; statistically analyzing the quality of the charge components and the sinter. The use of this technology for multicomponent charges in the sinter shop at ISPAT-Karmet has appreciably stabilized the chemical composition of the sinter – the standard deviation is now 0.295–0.311% for iron content and 0.031–0.037 for basicity.