{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T09:59:10Z","timestamp":1766138350141,"version":"build-2065373602"},"reference-count":53,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T00:00:00Z","timestamp":1686096000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62103364","LY23F030002"],"award-info":[{"award-number":["62103364","LY23F030002"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["62103364","LY23F030002"],"award-info":[{"award-number":["62103364","LY23F030002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/s23125415","type":"journal-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T02:02:28Z","timestamp":1686189748000},"page":"5415","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Real-Time Forecasting of Subsurface Inclusion Defects for Continuous Casting Slabs: A Data-Driven Comparative Study"],"prefix":"10.3390","volume":"23","author":[{"given":"Chihang","family":"Wei","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Hangzhou Normal University, Hangzhou 311121, China"}]},{"given":"Zhihuan","family":"Song","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,6,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1700312","DOI":"10.1002\/srin.201700312","article-title":"Review on modeling and simulation of continuous casting","volume":"89","author":"Thomas","year":"2018","journal-title":"Steel Res. Int."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.2355\/isijinternational.45.1291","article-title":"Mathematical heat transfer model research for the improvement of continuous casting slab temperature","volume":"45","author":"Wang","year":"2005","journal-title":"ISIJ Int."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"104258","DOI":"10.1016\/j.conengprac.2019.104258","article-title":"Prediction and causal analysis of defects in steel products: Handling nonnegative and highly overdispersed count data","volume":"95","author":"Zhang","year":"2020","journal-title":"Control Eng. Pract."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2233","DOI":"10.1016\/B978-0-444-64241-7.50367-0","article-title":"Defect data modeling and analysis for improving product quality and productivity in steel industry","volume":"44","author":"Zhang","year":"2018","journal-title":"Comput. Aided Chem. Eng."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1600068","DOI":"10.1002\/srin.201600068","article-title":"An end-to-end steel strip surface defects recognition system based on convolutional neural networks","volume":"88","author":"Yi","year":"2017","journal-title":"Steel Res. Int."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1179\/174328105X15814","article-title":"Precipitation and phase transformation modelling to predict surface cracks and slab quality","volume":"32","author":"Chimani","year":"2005","journal-title":"Ironmak. Steelmak."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"108920","DOI":"10.1016\/j.matdes.2020.108920","article-title":"Effect of slab charging temperature on reverse transformation behavior and induced crack sensitivity through experiments and micromechanical analysis","volume":"194","author":"Liu","year":"2020","journal-title":"Mater. Des."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1007\/s11668-019-00690-2","article-title":"Metallurgical analyses of surface defects in cold-rolled steel sheets","volume":"19","author":"Dhua","year":"2019","journal-title":"J. Fail. Anal. Prev."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"3092","DOI":"10.1002\/aic.14523","article-title":"Process data analytics in the era of big data","volume":"60","author":"Qin","year":"2014","journal-title":"AIChE J."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"20590","DOI":"10.1109\/ACCESS.2017.2756872","article-title":"Data mining and analytics in the process industry: The role of machine learning","volume":"5","author":"Ge","year":"2017","journal-title":"IEEE Access"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.chemolab.2017.09.021","article-title":"Review on data-driven modeling and monitoring for plant-wide industrial processes","volume":"171","author":"Ge","year":"2017","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_12","first-page":"1","article-title":"Block-wise parallel semisupervised linear dynamical system for massive and inconsecutive time-series data with application to soft sensing","volume":"71","author":"Shao","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1109\/MIE.2019.2938025","article-title":"Real-Time Monitoring and Control of Industrial Cyberphysical Systems: With Integrated Plant-Wide Monitoring and Control Framework","volume":"13","author":"Yin","year":"2019","journal-title":"IEEE Ind. Electron. Mag."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"8862","DOI":"10.1109\/TCYB.2021.3062058","article-title":"Hessian Semisupervised Scatter Regularized Classification Model With Geometric and Discriminative Information for Nonlinear Process","volume":"52","author":"Wei","year":"2021","journal-title":"IEEE Trans. Cybern."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.engappai.2019.04.013","article-title":"Process monitoring using variational autoencoder for high-dimensional nonlinear processes","volume":"83","author":"Lee","year":"2019","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"10876","DOI":"10.1109\/TIE.2019.2962468","article-title":"Generalized Semisupervised Self-Optimizing Kernel Model for Quality-Related Industrial Process Monitoring","volume":"67","author":"Wei","year":"2020","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.arcontrol.2022.09.005","article-title":"Latent variable models in the era of industrial big data: Extension and beyond","volume":"54","author":"Kong","year":"2022","journal-title":"Annu. Rev. Control"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1178","DOI":"10.1177\/00405175221129654","article-title":"Attention-based Feature Fusion Generative Adversarial Network for yarn-dyed fabric defect detection","volume":"93","author":"Zhang","year":"2023","journal-title":"Text. Res. J."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1007\/BF02985802","article-title":"The elements of statistical learning: Data mining, inference, and prediction","volume":"27","author":"Hastie","year":"2005","journal-title":"Math. Intell."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.engappai.2015.03.006","article-title":"On the linear discriminant analysis for large number of classes","volume":"43","author":"Huang","year":"2015","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1016\/j.engappai.2018.04.024","article-title":"Leukemia diagnosis in blood slides using transfer learning in CNNs and SVM for classification","volume":"72","author":"Vogado","year":"2018","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"103637","DOI":"10.1016\/j.engappai.2020.103637","article-title":"An accelerator for online SVM based on the fixed-size KKT window","volume":"92","author":"Guo","year":"2020","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lukauskas, M., and Ruzgas, T. (2023). Reduced Clustering Method Based on the Inversion Formula Density Estimation. Mathematics, 11.","DOI":"10.3390\/math11030661"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"108331","DOI":"10.1016\/j.patcog.2021.108331","article-title":"Multinomial random forest","volume":"122","author":"Bai","year":"2022","journal-title":"Pattern Recognit."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1007\/s42519-023-00325-8","article-title":"An Algorithm of Nonparametric Quantile Regression","volume":"17","author":"Huang","year":"2023","journal-title":"J. Stat. Theory Pract."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"108989","DOI":"10.1016\/j.patcog.2022.108989","article-title":"A new algorithm for support vector regression with automatic selection of hyperparameters","volume":"133","author":"Wang","year":"2023","journal-title":"Pattern Recognit."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1541880.1541882","article-title":"Anomaly detection: A survey","volume":"41","author":"Chandola","year":"2009","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1016\/j.neucom.2021.12.093","article-title":"GAN-based anomaly detection: A review","volume":"493","author":"Xia","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"10801","DOI":"10.1109\/JSEN.2023.3266104","article-title":"A Multi-Step Sequence-to-Sequence Model with Attention LSTM Neural Networks for Industrial Soft Sensor Application","volume":"23","author":"Ma","year":"2023","journal-title":"IEEE Sen. J."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Bocu, R., Bocu, D., and Iavich, M. (2022). An Extended Review Concerning the Relevance of Deep Learning and Privacy Techniques for Data-Driven Soft Sensors. Sensors, 23.","DOI":"10.3390\/s23010294"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"108525","DOI":"10.1016\/j.ress.2022.108525","article-title":"Towards trustworthy machine fault diagnosis: A probabilistic Bayesian deep learning framework","volume":"224","author":"Zhou","year":"2022","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_33","first-page":"1","article-title":"The multiclass fault diagnosis of wind turbine bearing based on multisource signal fusion and deep learning generative model","volume":"71","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"6859","DOI":"10.1109\/TII.2022.3181692","article-title":"A Self-Interpretable Soft Sensor Based On Deep Learning and Multiple Attention Mechanism: From Data Selection to Sensor Modeling","volume":"19","author":"Guo","year":"2022","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"104676","DOI":"10.1016\/j.jtice.2023.104676","article-title":"A novel integrated fault diagnosis method of chemical processes based on deep learning and information propagation hysteresis analysis","volume":"142","author":"Zhang","year":"2023","journal-title":"J. Taiwan Inst. Chem. Eng."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Ou, C., Zhu, H., Shardt, Y.A., Ye, L., Yuan, X., Wang, Y., and Yang, C. (2022). Quality-driven regularization for deep learning networks and its application to industrial soft sensors. IEEE Trans. Neural Netw. Learn. Syst.","DOI":"10.1109\/TNNLS.2022.3144162"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Gao, H., Huang, W., Gao, X., and Han, H. (2023). Decentralized adaptively weighted stacked autoencoder-based incipient fault detection for nonlinear industrial processes. ISA Trans.","DOI":"10.1016\/j.isatra.2023.04.035"},{"key":"ref_38","first-page":"2399","article-title":"Manifold regularization: A geometric framework for learning from labeled and unlabeled examples","volume":"7","author":"Belkin","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.jprocont.2019.06.011","article-title":"K-means Bayes algorithm for imbalanced fault classification and big data application","volume":"81","author":"Chen","year":"2019","journal-title":"J. Process. Control"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1109\/TPWRS.2006.888990","article-title":"Power distribution fault cause identification with imbalanced data using the data mining-based fuzzy classification E-algorithm","volume":"22","author":"Xu","year":"2007","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1016\/j.ymssp.2018.03.025","article-title":"Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization","volume":"110","author":"Jia","year":"2018","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Weiss, G.M. (1995). Learning with Rare Cases and Small Disjuncts, Elsevier.","DOI":"10.1016\/B978-1-55860-377-6.50075-X"},{"key":"ref_43","first-page":"665","article-title":"A quantitative study of small disjuncts","volume":"2000","author":"Weiss","year":"2000","journal-title":"AAAI\/IAAI"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Wallace, B.C., Small, K., Brodley, C.E., and Trikalinos, T.A. (2011, January 11\u201314). Class imbalance, redux. Proceedings of the 2011 IEEE 11th International Conference on Data Mining, Vancouver, BC, Canada.","DOI":"10.1109\/ICDM.2011.33"},{"key":"ref_45","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_46","first-page":"559","article-title":"Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning","volume":"18","author":"Nogueira","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/j.ces.2003.09.012","article-title":"Nonlinear process monitoring using kernel principal component analysis","volume":"59","author":"Lee","year":"2004","journal-title":"Chem. Eng. Sci."},{"key":"ref_48","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1007\/s10443-012-9286-3","article-title":"Prediction of damage factor in end milling of glass fibre reinforced plastic composites using artificial neural network","volume":"20","author":"Erkan","year":"2013","journal-title":"Appl. Compos. Mater."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Rasamoelina, A.D., Adjailia, F., and Sin\u010d\u00e1k, P. (2020, January 23\u201325). A review of activation function for artificial neural network. Proceedings of the 2020 IEEE 18th World Symposium on Applied Machine Intelligence and Informatics (SAMI), Herl\u2019any, Slovakia.","DOI":"10.1109\/SAMI48414.2020.9108717"},{"key":"ref_51","unstructured":"Ramachandran, P., Zoph, B., and Le, Q.V. (2017). Searching for activation functions. arXiv."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"022030","DOI":"10.1088\/1742-6596\/1237\/2\/022030","article-title":"Performance analysis of various activation functions in artificial neural networks","volume":"1237","author":"Feng","year":"2019","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_53","unstructured":"Agostinelli, F., Hoffman, M., Sadowski, P., and Baldi, P. (2014). Learning activation functions to improve deep neural networks. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/12\/5415\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:50:18Z","timestamp":1760125818000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/12\/5415"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,7]]},"references-count":53,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2023,6]]}},"alternative-id":["s23125415"],"URL":"https:\/\/doi.org\/10.3390\/s23125415","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2023,6,7]]}}}