Active label-denoising algorithm based on broad learning for annotation of machine health status

作     者：LIU GuoKai SHEN WeiMing GAO Liang KUSIAK Andrew 

作者机构：State Key Laboratory of Digital Manufacturing Equipment and TechnologyHuazhong University of Science and TechnologyWuhan 430074China Department of Industrial and System EngineeringThe University of IowaSeamans CenterIowa CityIA 52242USA 

出 版 物：《Science China(Technological Sciences)》 (中国科学（技术科学英文版）)

年 卷 期：2022年第65卷第9期

页      面：2089-2104页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0802[工学-机械工程] 0811[工学-控制科学与工程] 080201[工学-机械制造及其自动化] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the China Scholarship Council during a research visit of Guokai Liu to the University of Iowa(Grant No.201906160078) the Fundamental Research Funds for the Central Universities(Grant No.HUST:2021GCRC058) 

主　　题：data annotation broad learning deep learning domain adaptation fault diagnosis noisy label 

摘      要：Deep learning has led to tremendous success in machine maintenance and fault ***,this success is predicated on the correctly annotated *** in large industrial datasets can be noisy and thus degrade the performance of fault diagnosis *** emerging concept of broad learning shows the potential to address the label noise *** with existing deep learning algorithms,broad learning has a simple architecture and high training *** active label denoising algorithm based on broad learning(ALDBL)is ***,ALDBL captures the embedded representation from the time-frequency features by a recurrent memory ***,it augments wide features with a sparse autoencoder and projects the sparse features into an orthogonal space.A proposed corrector then iteratively changes the weights of source examples during the training and corrects the labels by using a label adaptation ***,ALDBL finetunes the model parameters with actively sampled target data with reliable pseudo *** performance of ALDBL is validated with three benchmark datasets,including 30 label denoising *** results demonstrate the effectiveness and advantages of the proposed algorithm over the other label denoising algorithms.