Dynamic Feature Extraction and Semi-Supervised Soft Sensor Model Based on SCINet for Industrial and Transportation Processes

In industrial processes, dynamic changes are one of the factors restricting the performance of soft sensor models. Meanwhile, the inconsistency of sensor sampling rates often leads to the problem of mismatch between process variables and quality variables. This paper proposes a semi-supervised soft...

Full description

Saved in:
Bibliographic Details
Main Authors: Jun Wang, Changjian Qi, Xing Luo, Shihao Deng, Qi Lei
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied System Innovation
Subjects:
Online Access:https://www.mdpi.com/2571-5577/8/3/73
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849418175206129664
author Jun Wang
Changjian Qi
Xing Luo
Shihao Deng
Qi Lei
author_facet Jun Wang
Changjian Qi
Xing Luo
Shihao Deng
Qi Lei
author_sort Jun Wang
collection DOAJ
description In industrial processes, dynamic changes are one of the factors restricting the performance of soft sensor models. Meanwhile, the inconsistency of sensor sampling rates often leads to the problem of mismatch between process variables and quality variables. This paper proposes a semi-supervised soft sensor modeling method based on sample convolution and interactive networks (SCINet). To extract the dynamic information of industrial processes more fully, an unsupervised time series dynamic feature extractor was designed based on SCINet and an autoencoder, and the feature extractor was trained using complete data. The dynamic features encoded by the dynamic feature extractor were transferred to the eXtreme Gradient Boosting (XGBoost) ensemble model with strong generalization ability. The semi-supervised soft measurement model SSCI-XGBoost was established. The effectiveness of dynamic feature transfer and model performance improvement was verified on the industrial process dataset.
format Article
id doaj-art-dca81dfb1b824704a31a32f5613ea026
institution Kabale University
issn 2571-5577
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Applied System Innovation
spelling doaj-art-dca81dfb1b824704a31a32f5613ea0262025-08-20T03:32:31ZengMDPI AGApplied System Innovation2571-55772025-05-01837310.3390/asi8030073Dynamic Feature Extraction and Semi-Supervised Soft Sensor Model Based on SCINet for Industrial and Transportation ProcessesJun Wang0Changjian Qi1Xing Luo2Shihao Deng3Qi Lei4CRRC Nanjing Puzhen Vehicle Co., Ltd., Nanjing 210031, ChinaCRRC Nanjing Puzhen Vehicle Co., Ltd., Nanjing 210031, ChinaMain Campus, School of Automation, Electrical EngineeringCentral South University, Changsha 410083, ChinaMain Campus, School of Automation, Electrical EngineeringCentral South University, Changsha 410083, ChinaMain Campus, School of Automation, Electrical EngineeringCentral South University, Changsha 410083, ChinaIn industrial processes, dynamic changes are one of the factors restricting the performance of soft sensor models. Meanwhile, the inconsistency of sensor sampling rates often leads to the problem of mismatch between process variables and quality variables. This paper proposes a semi-supervised soft sensor modeling method based on sample convolution and interactive networks (SCINet). To extract the dynamic information of industrial processes more fully, an unsupervised time series dynamic feature extractor was designed based on SCINet and an autoencoder, and the feature extractor was trained using complete data. The dynamic features encoded by the dynamic feature extractor were transferred to the eXtreme Gradient Boosting (XGBoost) ensemble model with strong generalization ability. The semi-supervised soft measurement model SSCI-XGBoost was established. The effectiveness of dynamic feature transfer and model performance improvement was verified on the industrial process dataset.https://www.mdpi.com/2571-5577/8/3/73soft sensorsample convolution and interactive networks (SCINet)dynamic feature extractor
spellingShingle Jun Wang
Changjian Qi
Xing Luo
Shihao Deng
Qi Lei
Dynamic Feature Extraction and Semi-Supervised Soft Sensor Model Based on SCINet for Industrial and Transportation Processes
Applied System Innovation
soft sensor
sample convolution and interactive networks (SCINet)
dynamic feature extractor
title Dynamic Feature Extraction and Semi-Supervised Soft Sensor Model Based on SCINet for Industrial and Transportation Processes
title_full Dynamic Feature Extraction and Semi-Supervised Soft Sensor Model Based on SCINet for Industrial and Transportation Processes
title_fullStr Dynamic Feature Extraction and Semi-Supervised Soft Sensor Model Based on SCINet for Industrial and Transportation Processes
title_full_unstemmed Dynamic Feature Extraction and Semi-Supervised Soft Sensor Model Based on SCINet for Industrial and Transportation Processes
title_short Dynamic Feature Extraction and Semi-Supervised Soft Sensor Model Based on SCINet for Industrial and Transportation Processes
title_sort dynamic feature extraction and semi supervised soft sensor model based on scinet for industrial and transportation processes
topic soft sensor
sample convolution and interactive networks (SCINet)
dynamic feature extractor
url https://www.mdpi.com/2571-5577/8/3/73
work_keys_str_mv AT junwang dynamicfeatureextractionandsemisupervisedsoftsensormodelbasedonscinetforindustrialandtransportationprocesses
AT changjianqi dynamicfeatureextractionandsemisupervisedsoftsensormodelbasedonscinetforindustrialandtransportationprocesses
AT xingluo dynamicfeatureextractionandsemisupervisedsoftsensormodelbasedonscinetforindustrialandtransportationprocesses
AT shihaodeng dynamicfeatureextractionandsemisupervisedsoftsensormodelbasedonscinetforindustrialandtransportationprocesses
AT qilei dynamicfeatureextractionandsemisupervisedsoftsensormodelbasedonscinetforindustrialandtransportationprocesses