DATA MINING APPLIED TO IDENTIFYING FACTORS AFFECTING BLAST FURNACE STAVE HEAT LOADS (original) (raw)
Related papers
2009
In the last few years, the use of computers has made it possible to achieve a better image of blast furnace performance, allowing the establishment of models, the comparison of variables and the construction of powerful databases to store the variables and their evolution during the process. Nevertheless, part of the investment made in blast furnace equipment is not properly utilized and a considerable part of the information collected could be put to much better use. The application of modern data mining techniques has overcome these problems. This work shows ways to apply these techniques to data from probes located in the throat or shaft of the blast furnace, as well as how to extract useful information by defining and classifying a set of patterns in classes from temperature profiles that have been linked to the stability of the process in steelworks with blast furnaces.
Application of symbolic regression on blast furnace and temper mill datasets
2012
In this paper a data mining approach for variable selection and knowledge extraction from datasets is presented. The approach is based on unguided symbolic regression (every variable present in the dataset is treated as the target variable in multiple regression runs) and a novel variable relevance metric for genetic programming. The relevance of each input variable is calculated and a model approximating the target variable is created. The genetic programming configurations with different target variables are executed multiple times to reduce stochastic effects and the aggregated results are displayed as a variable interaction network. This interaction network highlights important system components and implicit relations between the variables. The whole approach is tested on a blast furnace dataset, because of the complexity of the blast furnace and the many interrelations between the variables. Finally the achieved results are discussed with respect to existing knowledge about the blast furnace process.
Data Mining Using Unguided Symbolic Regression on a Blast Furnace Dataset
Lecture Notes in Computer Science, 2011
In this paper a data mining approach for variable selection and knowledge extraction from datasets is presented. The approach is based on unguided symbolic regression (every variable present in the dataset is treated as the target variable in multiple regression runs) and a novel variable relevance metric for genetic programming. The relevance of each input variable is calculated and a model approximating the target variable is created. The genetic programming configurations with different target variables are executed multiple times to reduce stochastic effects and the aggregated results are displayed as a variable interaction network. This interaction network highlights important system components and implicit relations between the variables. The whole approach is tested on a blast furnace dataset, because of the complexity of the blast furnace and the many interrelations between the variables. Finally the achieved results are discussed with respect to existing knowledge about the blast furnace process.
ISIJ International, 2010
The adaptation of blast furnaces to the new technologies has increased the operation information so that the sensor information can be known at every moment. However this often results in the supply of excessive data volume to the plant operators. This paper describes an industrial application for self-organized maps (SOM) in order to help them make decisions regarding blast furnace control by means of pattern recognition and the matching of temperature profiles supplied by the thermocouples placed on the above burden. The classification of patterns via easy color coding indicates to the operator what the blast furnace operational situation is, thus making the necessary corrections easier. KEY WORDS: ironmaking; blast furnace; neural networks; self-organized maps (SOM); forecasting. Fig. 1. Data statistics of the top gas temperature profiles in a blast furnace.
Statistical modeling of charcoal consumption of blast furnaces based on historical data
Journal of Materials Research and Technology, 2013
This paper describes the development of statistical models to predict charcoal consumption in blast furnaces based on Response Surface Models (RSM) and Linear Regression Models (LRM). The statistical approach used provides a high level of confidence and allows the company to act preemptively fostering innovative business and in the action plan to reduce hot metal production cost, to improve raw materials processing and other actions in order to provide the blast furnaces with raw materials at minimal cost. It is a special particularity and represents a great step in V & M do Brasil blast furnaces' operation which no longer uses standard ferrous load and started to operate with greater flexibility and variability concerning the types of ferrous load applied to achieve better economic results.
Decision-Making Support in Blast-Furnace Operation
Steel in Translation, 2019
A model system for decision-making support (a model of the blast-furnace process developed at Yeltsin Ural Federal University and PAO MMK) is considered. The basic model modules permit calculation of the material and thermal balances, simulation of the thermal, slag, and gas-dynamic conditions in the blast furnace, and selection of the batch composition. The model system, embodied as software, is integrated into the PAO MMK information system. The model for calculating the material and thermal balances permits determination of the Fe, S, Mn, and Ti balances. Introduction of the Slag Conditions software permits identification of the most important slag property to ensure normal slag conditions; determination of the ratio of the iron-ore materials so that the slag has the best viscosity and viscosity gradient; and the production of hot metal of the required quality. The introduction of Blast-Furnace Gas Dynamics software permits calculation and visual mapping of the gas-dynamic characteristics of the batch bed and assessment of the change in pressure difference and equilibration of the batch within individual zones of the furnace in the design period, with variation in the batch parameters and properties. The results obtained in practical use of this system are outlined. Recommendations are made regarding the solution of industrial problems.
Ann based prediction of blast furnace parameters
2007
The paper presents a method to predict blast furnace parameters based on ar tificial neural network (ANN). The pr ediction is important as the parameters cause the degradation of the pr oduction process. The productivity as well as quality can be improved by knowing these parameters in advance. In this context, the ir on making process in the modern blast furnace is briefly illustrated. Characterisation of the input and the output parameters as well as the design of a feed for ward neural network (FFNN) is outlined. The implementation issues ar e discussed to predict the parameters like hot metal temperatur e (HMT) and percentage of impurity of silicon content in molten ir on. The simulation and plant trial r esults are compar ed to show the effectiveness of the approach.
A Model Predictive Approach to Blast Furnace Operational Management Automation
Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics
Blast furnace operational management automation using modelling and real-time predictive solutions for the object control are considered. Main features of the proposed control are: using of an operational data mining software to identify effective clusters of the furnace regime parameters values; real-time software for identification of the furnace cohesion zone parameters for the operational management correction; dynamics forecasting of the furnace thermal state indicators when charge load and blast parameters change. Usage of the software permits to achieve effective values of the furnace regime parameters with high productivity and reduced coke consumption. It is effective in conditions of the significant charge parameters changes, due to using of source materials from different suppliers. Therewith, forecasting of parameters dynamics allows supervisor to stabilize the blast furnace process in the effective regime. The system is based a joint development of the
Expert system of diagnostics blast furnace process
IOP Conference Series: Materials Science and Engineering, 2020
The expert system of diagnostics blast furnace process is presented. It is based on a logical-mathematical model for assessing the progress of blast furnace smelting. The model provides an opportunity to evaluate the normal operation mode of blast furnace and further deviations from this mode such as overdeveloped gas flows (peripheral and central), violation of thermal melting conditions (hot and cold course of melt), violation of smooth descent of burned materials in the furnace (tight furnace operation, higher and lower suspension of burden). The functional capabilities of developed software are represented.