Study On Diagnose And Forecast Of Blast Furnace Condition Based On Neural Network

The puddling of blast furnace plays an important part in iron and steel industry which is stanchion industry of country economic. Long-term,stable and smooth status of the blast furnace is not only the precondition of high yield and low consumption,but also the prerequisite to extend the life of blast furnace. Reducing energy consumption in the blast furnace smelting process and achieving the stability and optimization of iron making production demand timely and accurate judgment and forecast to the status of blast furnace,adopt various adjustment measures in a timely and appropriate manner。 Therefore,at present,the judgment and handling of Blast Furnace Operation is still mainly based on the rich experience of the operator,so which results in subjectivity in operation,poor succession. Therefore,the exceptional situation prediction have been a hot research at home and abroad.On the background of Tianjin Iron&Steel Group Co.,Ltd.and based on a quantity of relevant bibliographies, this paper summarizes the development of judgment and forecast to the status of blast furnace，and empirically analyses the organizing methods of Condition parameters of blast furnace.The paper mainly completes the following aspects:(1) Describes the status of diagnostic system of blast furnace iron and steel enterprises in the important role, introduced the development and research at home and abroad.(2) The application of BP neural network model to determine the three-forward network structure, with additional momentum method to adjust the weights of BP neural network, effectively overcome the slow convergence of BP neural network, easily falling into local minimum shortcomings and improve the the computing speed, filter the numerical stability and accuracy of neural network output.(3) Through the blast furnace process and principles of analysis and research on a variety of measured parameters from the blast furnace, through correlation analysis to determine the impact of blast furnace condition of various abnormal parameters. In the blast furnace, based on data analysis, established to determine the blast furnace heat, to cool, pipe schedule, suspended material, collapse material, accumulation of abnormal hearth furnace conditions forecast.Compared with other method,this skill has the advantages as follow:(1) Determine the mode from global considerations, ideas meet the foreman of the logic of the operator’s experience, this method model parameters used are all readily available in the daily work of blast furnace basic parameters, easy to blast furnace operators to accept.(2) Judged to meet the requirements of real-time blast furnace can be used as a tool for online analysis.