文献类型：期刊文献

英文题名：A semi-supervised learning algorithm for high and low-frequency variable imbalances in industrial data

作者：Zhu, Jiannan[1,2];Fan, Chen[1];Yang, Minglei[1,3];Qian, Feng[1,3];Mahalec, Vladimir[2]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai, Peoples R China;[2]McMaster Univ, Dept Chem Engn, Hamilton, ON L8S 4L8, Canada;[3]East China Univ Sci & Technol, Engn Res Ctr Proc Syst Engn, Minist Educ, Shanghai, Peoples R China

年份：2025

卷号：193

外文期刊名：COMPUTERS & CHEMICAL ENGINEERING

收录：;EI(收录号：20244717408963);WOS:【SCI-EXPANDED(收录号:WOS:001363822300001)】；

基金：This work was supported by National Key Research & Development Program-Intergovernmental International Science and Technology Innovation Cooperation Project (2021YFE0112800), National Natural Science Foundation of China (Basic Science Center Program: 61988101), Fundamental Research Funds for the Central Universities (222202417006), the Programme of Introducing Talents of Discipline to Universities (the 111 Project) under Grant B17017.

语种：英文

外文关键词：Semi-supervised learning; Consistency regularization; Unbalanced data structure; Loss balancing methods

摘要：This work introduces a semi-supervised learning algorithm to estimate missing data for processes where measured data is comprised of variables that are measured at high frequency and low frequency. A semisupervised learning algorithm named "Weight-Adjusted Consistency Regularization Algorithm for SemiSupervised Learning" (WACR-SSL) based on consistency regularization is proposed. The algorithm splits the irregular unbalanced data set into three parts and processes them separately. To address the loss balancing problem, five loss balancing methods have been tested: Uncertainty Weights (UW), Random Loss Weighting (RLW), Dynamic Weight Average (DWA), Geometric Loss Strategy (GLS) and the logarithmic transformation (LogT). When applied to data from a hydrocracking process, the algorithm effectively leverages partially labeled data. With carefully chosen noise scales and the coefficient for the unsupervised loss, the uncertainty weight (UW) variant performs the best when compared to the other loss balancing methods.