Semi-supervised soft sensor development based on dynamic dimensionality reduction-assisted large-scale pseudo label optimization and sample-weighted quality-relevant deep learning
Huaiping Jin , Guangkun Liu , Bin Qian , Bin Wang , Biao Yang , Xiangguang Chen
{"title":"Semi-supervised soft sensor development based on dynamic dimensionality reduction-assisted large-scale pseudo label optimization and sample-weighted quality-relevant deep learning","authors":"Huaiping Jin , Guangkun Liu , Bin Qian , Bin Wang , Biao Yang , Xiangguang Chen","doi":"10.1016/j.ces.2024.120387","DOIUrl":null,"url":null,"abstract":"<div><p>Data-driven soft sensors have become popular tools for estimating critical quality variables in the process industry. However, in practical applications, it is very common that the unlabeled data are abundant but the labeled data are scarce, which poses a great challenge for developing high-performance data-based soft sensors. Thus, a dynamic dimensionality reduction-assisted large-scale pseudo label optimization method (DDR-LSPLO) is proposed for achieving sample expansion. This method repeatedly converts the LSPLO issue into a reduced-dimension pseudo label optimization problem with the low-confidence pseudo labels as new decision variables during the evolutionary optimization process. Meanwhile, to tackle the sample imbalance problem resulting from the inclusion of large-scale pseudo-labeled samples, a sample expansion and weighting-based quality-relevant autoencoder (SEWQAE) is developed for semi-supervised soft sensor modeling. The effectiveness and superiority of the proposed DDR-LSPLO and SEWQAE methods are verified through an industrial chlortetracycline (CTC) fermentation process and a simulated Tennessee Eastman (TE) chemical process.</p></div>","PeriodicalId":271,"journal":{"name":"Chemical Engineering Science","volume":null,"pages":null},"PeriodicalIF":4.1000,"publicationDate":"2024-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Chemical Engineering Science","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0009250924006870","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}
引用次数: 0
Abstract
Data-driven soft sensors have become popular tools for estimating critical quality variables in the process industry. However, in practical applications, it is very common that the unlabeled data are abundant but the labeled data are scarce, which poses a great challenge for developing high-performance data-based soft sensors. Thus, a dynamic dimensionality reduction-assisted large-scale pseudo label optimization method (DDR-LSPLO) is proposed for achieving sample expansion. This method repeatedly converts the LSPLO issue into a reduced-dimension pseudo label optimization problem with the low-confidence pseudo labels as new decision variables during the evolutionary optimization process. Meanwhile, to tackle the sample imbalance problem resulting from the inclusion of large-scale pseudo-labeled samples, a sample expansion and weighting-based quality-relevant autoencoder (SEWQAE) is developed for semi-supervised soft sensor modeling. The effectiveness and superiority of the proposed DDR-LSPLO and SEWQAE methods are verified through an industrial chlortetracycline (CTC) fermentation process and a simulated Tennessee Eastman (TE) chemical process.
期刊介绍:
Chemical engineering enables the transformation of natural resources and energy into useful products for society. It draws on and applies natural sciences, mathematics and economics, and has developed fundamental engineering science that underpins the discipline.
Chemical Engineering Science (CES) has been publishing papers on the fundamentals of chemical engineering since 1951. CES is the platform where the most significant advances in the discipline have ever since been published. Chemical Engineering Science has accompanied and sustained chemical engineering through its development into the vibrant and broad scientific discipline it is today.