Real-Time Forecasting of Subsurface Inclusion Defects for Continuous Casting Slabs: A Data-Driven Comparative Study
Subsurface inclusions are one of the most common defects that affect the inner quality of continuous casting slabs. This increases the defects in the final products and increases the complexity of the hot charge rolling process and may even cause breakout accidents. The defects are, however, hard to...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-06-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/12/5415 |
_version_ | 1797592729995182080 |
---|---|
author | Chihang Wei Zhihuan Song |
author_facet | Chihang Wei Zhihuan Song |
author_sort | Chihang Wei |
collection | DOAJ |
description | Subsurface inclusions are one of the most common defects that affect the inner quality of continuous casting slabs. This increases the defects in the final products and increases the complexity of the hot charge rolling process and may even cause breakout accidents. The defects are, however, hard to detect online by traditional mechanism-model-based and physics-based methods. In the present paper, a comparative study is carried out based on data-driven methods, which are only sporadically discussed in the literature. As a further contribution, a scatter-regularized kernel discriminative least squares (SR-KDLS) model and a stacked defect-related autoencoder back propagation neural network (SDAE-BPNN) model are developed to improve the forecasting performance. The scatter-regularized kernel discriminative least squares is designed as a coherent framework to directly provide forecasting information instead of low-dimensional embeddings. The stacked defect-related autoencoder back propagation neural network extracts deep defect-related features layer by layer for a higher feasibility and accuracy. The feasibility and efficiency of the data-driven methods are demonstrated through case studies based on a real-life continuous casting process, where the imbalance degree drastically vary in different categories, showing that the defects are timely (within 0.01 ms) and accurately forecasted. Moreover, experiments illustrate the merits of the developed scatter-regularized kernel discriminative least squares and stacked defect-related autoencoder back propagation neural network methods regarding the computational burden; the F1 scores of the developed methods are clearly higher than common methods. |
first_indexed | 2024-03-11T01:58:16Z |
format | Article |
id | doaj.art-b0ac11336b8f4932a82da3af929e9c51 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-11T01:58:16Z |
publishDate | 2023-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-b0ac11336b8f4932a82da3af929e9c512023-11-18T12:30:41ZengMDPI AGSensors1424-82202023-06-012312541510.3390/s23125415Real-Time Forecasting of Subsurface Inclusion Defects for Continuous Casting Slabs: A Data-Driven Comparative StudyChihang Wei0Zhihuan Song1School of Information Science and Technology, Hangzhou Normal University, Hangzhou 311121, ChinaState Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, ChinaSubsurface inclusions are one of the most common defects that affect the inner quality of continuous casting slabs. This increases the defects in the final products and increases the complexity of the hot charge rolling process and may even cause breakout accidents. The defects are, however, hard to detect online by traditional mechanism-model-based and physics-based methods. In the present paper, a comparative study is carried out based on data-driven methods, which are only sporadically discussed in the literature. As a further contribution, a scatter-regularized kernel discriminative least squares (SR-KDLS) model and a stacked defect-related autoencoder back propagation neural network (SDAE-BPNN) model are developed to improve the forecasting performance. The scatter-regularized kernel discriminative least squares is designed as a coherent framework to directly provide forecasting information instead of low-dimensional embeddings. The stacked defect-related autoencoder back propagation neural network extracts deep defect-related features layer by layer for a higher feasibility and accuracy. The feasibility and efficiency of the data-driven methods are demonstrated through case studies based on a real-life continuous casting process, where the imbalance degree drastically vary in different categories, showing that the defects are timely (within 0.01 ms) and accurately forecasted. Moreover, experiments illustrate the merits of the developed scatter-regularized kernel discriminative least squares and stacked defect-related autoencoder back propagation neural network methods regarding the computational burden; the F1 scores of the developed methods are clearly higher than common methods.https://www.mdpi.com/1424-8220/23/12/5415real-time forecastingsubsurface inclusion defectsdata-driven methodsdiscriminant analysisstack autoencoder |
spellingShingle | Chihang Wei Zhihuan Song Real-Time Forecasting of Subsurface Inclusion Defects for Continuous Casting Slabs: A Data-Driven Comparative Study Sensors real-time forecasting subsurface inclusion defects data-driven methods discriminant analysis stack autoencoder |
title | Real-Time Forecasting of Subsurface Inclusion Defects for Continuous Casting Slabs: A Data-Driven Comparative Study |
title_full | Real-Time Forecasting of Subsurface Inclusion Defects for Continuous Casting Slabs: A Data-Driven Comparative Study |
title_fullStr | Real-Time Forecasting of Subsurface Inclusion Defects for Continuous Casting Slabs: A Data-Driven Comparative Study |
title_full_unstemmed | Real-Time Forecasting of Subsurface Inclusion Defects for Continuous Casting Slabs: A Data-Driven Comparative Study |
title_short | Real-Time Forecasting of Subsurface Inclusion Defects for Continuous Casting Slabs: A Data-Driven Comparative Study |
title_sort | real time forecasting of subsurface inclusion defects for continuous casting slabs a data driven comparative study |
topic | real-time forecasting subsurface inclusion defects data-driven methods discriminant analysis stack autoencoder |
url | https://www.mdpi.com/1424-8220/23/12/5415 |
work_keys_str_mv | AT chihangwei realtimeforecastingofsubsurfaceinclusiondefectsforcontinuouscastingslabsadatadrivencomparativestudy AT zhihuansong realtimeforecastingofsubsurfaceinclusiondefectsforcontinuouscastingslabsadatadrivencomparativestudy |