The Detecting Method Of Blast Furnace Burden Surface Temperature Field Based On Multi-source Information

As the foundation of our national economy, steel industry plays an important role in the economic and social development. Blast furnace, the most critical equipment in steel industry and the major energy-consumer as well as the great producer of environmental pollution, has a great influence on the economic benefits of the steel company and even the whole country.Blast furnace process is very complex, in high-temperature, high-pressure and multiphase flow condition, furnace temperature is difficult to measure, This article is based on energy saving of the blast, proposed to a blast furnace surface temperature detection method using multi-source information for the blast furnace, including infrared image,material surface temperature, mineral coke rate, hot air pressure, air temperature, radar lines, and etc. The integrated use of information fusion technology, image processing technology, the mechanism of derivation and data-driven method to establish the distribution model of the material surface temperature, the model of temperature can used to monitor the smelting process effective in real-time and even guide the operation of burden distribution. The innovation and contribution of this thesis are as follows:(1) The correlation analysis of multi-source detection information and material surface temperature characteristics has discussed form the viewpoint of BF production process. So as to obtained the parameters of process detection and characteristic quantity which are closely related to the BF furnace temperature. In order to fully use multi-source detecting information, a on-line data-driven temperature detecting model for BF is settled with the course of multi-source information collected in the process of BF production.(2) In order to calculate the BF material surface temperature, a mapping model based on the crossing temperature material surface temperature is estimated. This model make using of the Cross thermocouple measurement value based on the thermodynamic theory. and take advantage of Newton interpolation method to establish crossing temperature curve model.(3) Infrared image processing and feature extraction Because the infrared images have a variety of interference and detecting distortion. Firstly, take advantage of Distribution method to eliminate the distortion of the image. Then take using of Gaussian filtering and tilt correction for further processing, finally, do gradation correction and recalibration for the infrared image.(4) Using the above calculation and direct measurement of multi-source detection information to effectively integrate the use of multi-source detection information, establish the temperature distribution of the material surface model using the method of least squares support vector machine, As a result, this method has better optimizing performance than using the course of single-source information, more comprehensive, more accurate reflection of the actual temperature of the material surface BF.