Apparatus for learning tissue composition of sintered ore, method for learning organization composition and learning program for organization composition

摘要

Problem to be solved: to provide an assembly structure learning device capable of generating a learning model capable of accurately estimating the composition of sintered ore.The tissue composition learning apparatus 1 of the sintered oreAn image data acquisition section 21 for acquiring a plurality of image data showing a plurality of sectional images obtained by imaging a cross-section of a sintered ore, andFor each of the multiple regions of the sectional imageA learning data generator 23 for generating a plurality of learning data in association with the mineral phases contained in the sinter andA learning processing unit 24 for learning the relationship between a plurality of cross sectional images and the composition of sinter using a plurality of learning data is learned.Based on the relationship between multiple cross-sectional images learned and the composition of sinterA learning model output part 25 which outputs a learning model for estimating the composition of sinter from the cross section image obtained by imaging the cross section of sinter, andAndMultiple learning dataHematiteMagnetiteIn at least three mineral phases of calcium ferrite and silicate slagGenerated by associating multiple regions.Diagram