基于多源异构信息融合的浮选精煤灰分智能预测

打开文本图片集

中图分类号：TD94 文献标志码：A

Abstract：To address the issue that X-raydetectionalone is insuficient to fully capture the complex material changes during the flotation clean coal process，an inteligent flotation system based on multi-source heterogeneous information fusion，integrating X-raydetection and machine vision technologies，was designed.A prediction model for cleancoal ash content was established using Federated Learning （FED）and Convolutional Neural Networks （CNN）.Elemental analysisofflotation cleancoal slurry wasconducted usingan X-ray ash analyzer.1D-CNN wasapplied to process the elemental contentdata to extract temporal features.Meanwhile， the ash content of flotationclean coal was detected using flotation froth vision technology，and 2D-CNN was used to process tailings image information to extract spatial features.An atention mechanism was adopted to fuse the temporalandspatial features derived frommulti-source heterogeneous information，and throughafullyconnected layer toconductregressionpredictionofashcontent inflotationcleancoal.TheFEDmodelefectively addressed privacy protection and collaborative modeling in multi-source heterogeneous information fusion through a modular aggregation method and a dynamic weighting strategy.Experimental results showed that the FED-CNN model achieved a maximum error of 4.44% and a coefficient of determination （R2） ）of0.94.Theprediction accuracywas higher than thatof the2D-CNN model basedontailingsimagesandthe1D-CNNmodelbasedon X-ray data.

Key words： intelligent flotation; clean coal ash prediction; multi-source heterogeneous information fusion： X-ray fluorescence spectroscopy; machine vision; federated learning; convolutional neural network

0引言

煤泥浮选是选煤厂生产过程中的关键环节，直接影响企业的经济效益[1-2]。（剩余10312字）