Research On Judging Method For FeO Content In Sinter Based On Machine Vision

In the process of modern iron-making,sinter is the main link in the production chain which provide material for iron-making.The quality of sinter has important effect on blast furnace result.Producing sinter with sinter method not only solves the problem of lean ore iron-making,but also improving the metallurgy property of iron-bearing materials,production indices and economic profit of blast furnaces are largely improved.The FeO content is related to the sinter reduction,which is the significant quality guideline of sinter.Judging FeO content has important implications to sinter product.This paper reviews the mechanism of the sintering process,analyze the mechanism of FeO in the sintering process and the factors affecting the FeO content.Introducing machine vision into judging FeO content has researched the methods of judging FeO content based upon machine vision,researched the collecting techniques of sinter tail section image,researched image preprocessing methods of sinter tail section image of expression,gray processing,image smoothing and partitioning.It focused research sinter tail section image feature information extraction method based on the color feature and shape feature.This paper proposes a basic idea about the sinter FeO content two stage judgment methods which is quantitative first grading after.In the case of just qualitative analysis of FeO content level,based on fuzzy reasoning,according to the sinter tail section image feature information,using brightness?area and central ordinate as fuzzy system input,using sinter FeO content as fuzzy system output.It can realize the fuzzy classification of FeO content.For the condition of high requirements for production quota and quantitative analysis,in view of the three different levels,we can respectively set up three FeO contents of neural network model according to the results of classification.We also can select the invariant moment of sinter tail section image and the thickness of the material?the ratio of fuel?mixed water?alkalinity which are the four sintering process parameters great influencing on FeO content as the input of neural network,while the output of neural network is the FeO content.Consequently we can achieve the accurate judgment of sinter FeO content.The simulation results that the two levels of sinter FeO content judgement have their feasibility,effectiveness and superiority.