A froth velocity measurement method based on improved U-Net++semantic segmentation in flotation process

作     者：Yiwei Chen Degang Xu Kun Wan Yiwei Chen;Degang Xu;Kun Wan

作者机构：School of AutomationCentral South UniversityChangsha 410083China 

出 版 物：《International Journal of Minerals,Metallurgy and Materials》 (矿物冶金与材料学报（英文版）)

年 卷 期：2024年第31卷第8期

页      面：1816-1827页

核心收录：

学科分类：081902[工学-矿物加工工程] 0819[工学-矿业工程] 08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：This work was financially supported by the National Natural Science Foundation of China(No.61973320) the Joint Fund of Liaoning Province State Key Laboratory of Robotics,China(No.2021KF2218) the Youth Program of the National Natural Science Foundation of China(No.61903138) the Key Research Innovation Project of Hunan Province,China(No.2022GK2059) 

主　　题：froth flotation froth segmentation froth image data augmentation velocity extraction image features 

摘      要：During flotation,the features of the froth image are highly correlated with the concentrate grade and the corresponding working *** static features such as color and size of the bubbles and the dynamic features such as velocity have obvious differences between different working *** extraction of these features is typically relied on the outcomes of image segmentation at the froth edge,making the segmentation of froth image the basis for studying its visual ***,the absence of scientifically reliable training data with label and the necessity to manually construct dataset and label make the study difficult in the mineral *** solve this problem,this paper constructs a tungsten concentrate froth image dataset,and proposes a data augmentation network based on Conditional Generative Adversarial Nets(cGAN)and a U-Net++-based edge segmentation *** performance of this algorithm is also evaluated and contrasted with other algorithms in this *** the results of semantic segmentation,a phase-correlationbased velocity extraction method is finally suggested.