{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T08:30:33Z","timestamp":1790670633084,"version":"4.1.0"},"reference-count":45,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2023,4,29]],"date-time":"2023-04-29T00:00:00Z","timestamp":1682726400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The material removal rate (MRR) is an important variable but difficult to measure in the chemical\u2013mechanical planarization (CMP) process. Most data-based virtual metrology (VM) methods ignore the large number of unlabeled samples, resulting in a waste of information. In this paper, the semi-supervised deep kernel active learning (SSDKAL) model is proposed. Clustering-based phase partition and phase-matching algorithms are used for the initial feature extraction, and a deep network is used to replace the kernel of Gaussian process regression so as to extract hidden deep features. Semi-supervised regression and active learning sample selection strategies are applied to make full use of information on the unlabeled samples. The experimental results of the CMP process dataset validate the effectiveness of the proposed method. Compared with supervised regression and co-training-based semi-supervised regression algorithms, the proposed model has a lower mean square error with different labeled sample proportions. Compared with other frameworks proposed in the literature, such as physics-based VM models, Gaussian-process-based regression models, and stacking models, the proposed method achieves better prediction results without using all the labeled samples.<\/jats:p>","DOI":"10.3390\/s23094392","type":"journal-article","created":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T12:12:11Z","timestamp":1682943131000},"page":"4392","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Semi-Supervised Deep Kernel Active Learning for Material Removal Rate Prediction in Chemical Mechanical Planarization"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9924-144X","authenticated-orcid":false,"given":"Chunpu","family":"Lv","sequence":"first","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing 100084, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingwei","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing 100084, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5202-5574","authenticated-orcid":false,"given":"Ming","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Engineering and Physical Sciences, Aston University, Birmingham B4 7ET, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7322-3446","authenticated-orcid":false,"given":"Huangang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing 100084, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2980-6281","authenticated-orcid":false,"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing 100084, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,4,29]]},"reference":[{"key":"ref_1","first-page":"214","article-title":"The theory and design of plate glass polishing machines","volume":"11","author":"Preston","year":"1927","journal-title":"J. Glass Technol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00170-009-2488-7","article-title":"Development of a pad conditioning simulation module with a diamond dresser for CMP applications","volume":"50","author":"Yeh","year":"2010","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1007\/s00170-018-1956-3","article-title":"Diamond structure-dependent pad and wafer polishing performance during chemical mechanical polishing","volume":"97","author":"Shin","year":"2018","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"3515","DOI":"10.1007\/s00170-016-9069-3","article-title":"Material removal model of chemical mechanical polishing for fused silica using soft nanoparticles","volume":"88","author":"Liu","year":"2017","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2407","DOI":"10.1007\/s00170-018-2578-5","article-title":"A stack fusion model for material removal rate prediction in chemical-mechanical planarization process","volume":"99","author":"Zhao","year":"2018","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"031003","DOI":"10.1115\/1.4042051","article-title":"Prediction of material removal rate for chemical mechanical planarization using decision tree-based ensemble learning","volume":"141","author":"Li","year":"2019","journal-title":"J. Manuf. Sci. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"103228","DOI":"10.1016\/j.compind.2020.103228","article-title":"A virtual metrology method with prediction uncertainty based on Gaussian process for chemical mechanical planarization","volume":"119","author":"Cai","year":"2020","journal-title":"Comput. Ind."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"108338","DOI":"10.1016\/j.measurement.2020.108338","article-title":"Adaptive virtual metrology method based on Just-in-time reference and particle filter for semiconductor manufacturing","volume":"168","author":"Cai","year":"2021","journal-title":"Measurement"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1007\/s10845-018-1437-4","article-title":"Recurrent feature-incorporated convolutional neural network for virtual metrology of the chemical mechanical planarization process","volume":"31","author":"Lee","year":"2020","journal-title":"J. Intell. Manuf."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/OJIM.2022.3205649","article-title":"A Distributional Perspective on Remaining Useful Life Prediction With Deep Learning and Quantile Regression","volume":"1","author":"Zhang","year":"2022","journal-title":"IEEE Open J. Instrum. Meas."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1430","DOI":"10.1016\/j.wear.2019.02.012","article-title":"Predictive modeling of material removal rate in chemical mechanical planarization with physics-informed machine learning","volume":"426","author":"Yu","year":"2019","journal-title":"Wear"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Lim, K.L., and Dutta, R. (2020, January 2\u20134). Material removal rate prediction using the classification-regression approach. Proceedings of the 2020 IEEE 22nd Electronics Packaging Technology Conference (EPTC), Singapore.","DOI":"10.1109\/EPTC50525.2020.9315140"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhang, M., Amaitik, N., Wang, Z., Xu, Y., Maisuradze, A., Peschl, M., and Tzovaras, D. (2022). Predictive maintenance for remanufacturing based on hybrid-driven remaining useful life prediction. Appl. Sci., 12.","DOI":"10.3390\/app12073218"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Ma, Q., Zhang, M., Xu, Y., Song, J., and Zhang, T. (2021, January 2\u20134). Remaining Useful Life Estimation for Turbofan Engine with Transformer-based Deep Architecture. Proceedings of the 2021 26th International Conference on Automation and Computing (ICAC), Portsmouth, UK.","DOI":"10.23919\/ICAC50006.2021.9594150"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Lim, K.L., and Dutta, R. (2021, January 7\u20139). Prognostics and Health Management of Wafer Chemical-Mechanical Polishing System using Autoencoder. Proceedings of the 2021 IEEE International Conference on Prognostics and Health Management (ICPHM), Detroit, MI, USA.","DOI":"10.1109\/ICPHM51084.2021.9486471"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2295","DOI":"10.1007\/s10845-021-01784-1","article-title":"A novel hypergraph convolution network-based approach for predicting the material removal rate in chemical mechanical planarization","volume":"33","author":"Xia","year":"2022","journal-title":"J. Intell. Manuf."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1109\/TSM.2018.2849206","article-title":"A computer vision-inspired deep learning architecture for virtual metrology modeling with 2-dimensional data","volume":"31","author":"Maggipinto","year":"2018","journal-title":"IEEE Trans. Semicond. Manuf."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"104262","DOI":"10.1016\/j.conengprac.2019.104262","article-title":"Development of convolutional neural network based Gaussian process regression to construct a novel probabilistic virtual metrology in multi-stage semiconductor processes","volume":"96","author":"Wu","year":"2020","journal-title":"Control. Eng. Pract."},{"key":"ref_19","unstructured":"Rasmussen, C.E. (2003, January 4\u201316). Gaussian processes in machine learning. Proceedings of the Summer School on Machine Learning, Tubingen, Germany."},{"key":"ref_20","unstructured":"Rasmussen, C., and Ghahramani, Z. (2001, January 3\u20138). Infinite mixtures of Gaussian process experts. Proceedings of the Advances in Neural Information Processing Systems 14 (NIPS 2001), Vancouver, BC, Canada."},{"key":"ref_21","unstructured":"Wilson, A.G., Hu, Z., Salakhutdinov, R., and Xing, E.P. (2016, January 9\u201311). Deep kernel learning. Proceedings of the Artificial Intelligence and Statistics, Cadiz, Spain."},{"key":"ref_22","unstructured":"Settles, B. (2023, March 10). Active Learning Literature Survey. Available online: http:\/\/digital.library.wisc.edu\/1793\/60660."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1348","DOI":"10.1109\/TNNLS.2018.2868649","article-title":"Pool-based sequential active learning for regression","volume":"30","author":"Wu","year":"2018","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Seung, H.S., Opper, M., and Sompolinsky, H. (1992, January 27\u201329). Query by committee. Proceedings of the fifth annual workshop on Computational learning theory, Pittsburgh, Pennsylvania.","DOI":"10.1145\/130385.130417"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1023\/A:1007330508534","article-title":"Selective sampling using the query by committee algorithm","volume":"28","author":"Freund","year":"1997","journal-title":"Mach. Learn."},{"key":"ref_26","unstructured":"Krogh, A., and Vedelsby, J. (1994). Advances in Neural Information Processing Systems 7, MIT Press."},{"key":"ref_27","unstructured":"RayChaudhuri, T., and Hamey, L. (December, January 27). Minimisation of data collection by active learning. Proceedings of the ICNN\u201995-International Conference on Neural Networks, Perth, WA, Australia."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Cai, W., Zhang, Y., and Zhou, J. (2013, January 7\u201310). Maximizing expected model change for active learning in regression. Proceedings of the 2013 IEEE 13th International Conference on Data Mining, Dallas, TX, USA.","DOI":"10.1109\/ICDM.2013.104"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Yu, H., and Kim, S. (2010, January 13\u201317). Passive sampling for regression. Proceedings of the 2010 IEEE International Conference on Data Mining, Sydney, NSW, Australia.","DOI":"10.1109\/ICDM.2010.9"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.ins.2018.09.060","article-title":"Active learning for regression using greedy sampling","volume":"474","author":"Wu","year":"2019","journal-title":"Inf. Sci."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1021","DOI":"10.1016\/j.jprocont.2006.07.005","article-title":"Online monitoring of batch processes using multi-phase principal component analysis","volume":"16","author":"Camacho","year":"2006","journal-title":"J. Process. Control"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.chemolab.2013.03.017","article-title":"Step-wise sequential phase partition (SSPP) algorithm based statistical modeling and online process monitoring","volume":"125","author":"Zhao","year":"2013","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1016\/j.ins.2013.02.042","article-title":"Warped k-means: An algorithm to cluster sequentially-distributed data","volume":"237","author":"Leiva","year":"2013","journal-title":"Inf. Sci."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1483","DOI":"10.3233\/JIFS-169689","article-title":"Semi-supervised regression: A recent review","volume":"35","author":"Kostopoulos","year":"2018","journal-title":"J. Intell. Fuzzy Syst."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1002\/aic.14270","article-title":"Mixture semisupervised principal component regression model and soft sensor application","volume":"60","author":"Ge","year":"2014","journal-title":"AIChE J."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/j.jprocont.2018.01.008","article-title":"Semisupervised learning for probabilistic partial least squares regression model and soft sensor application","volume":"64","author":"Zheng","year":"2018","journal-title":"J. Process. Control"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.conengprac.2018.11.008","article-title":"Semi-supervised mixture of latent factor analysis models with application to online key variable estimation","volume":"84","author":"Shao","year":"2019","journal-title":"Control Eng. Pract."},{"key":"ref_38","unstructured":"Jean, N., Xie, S.M., and Ermon, S. (2018, January 3\u20138). Semi-supervised deep kernel learning: Regression with unlabeled data by minimizing predictive variance. Proceedings of the Neural Information Processing Systems (NeurIPS), Montreal, QC, Canada."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1016\/j.ins.2015.06.021","article-title":"Learning from normalized local and global discriminative information for semi-supervised regression and dimensionality reduction","volume":"324","author":"Zhao","year":"2015","journal-title":"Inf. Sci."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","article-title":"Nearest neighbor pattern classification","volume":"13","author":"Cover","year":"1967","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","article-title":"Extremely randomized trees","volume":"63","author":"Geurts","year":"2006","journal-title":"Mach. Learn."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1479","DOI":"10.1109\/TKDE.2007.190644","article-title":"Semisupervised regression with cotraining-style algorithms","volume":"19","author":"Zhou","year":"2007","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_44","unstructured":"Gardner, J., Pleiss, G., Weinberger, K.Q., Bindel, D., and Wilson, A.G. (2018, January 3\u20138). Gpytorch: Blackbox matrix-matrix gaussian process inference with gpu acceleration. Proceedings of the Neural Information Processing Systems (NeurIPS), Montreal, QC, Canada."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1016\/j.cirp.2017.04.013","article-title":"A deep learning-based approach to material removal rate prediction in polishing","volume":"66","author":"Wang","year":"2017","journal-title":"CIRP Ann."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/9\/4392\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:26:40Z","timestamp":1760124400000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/9\/4392"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,29]]},"references-count":45,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2023,5]]}},"alternative-id":["s23094392"],"URL":"https:\/\/doi.org\/10.3390\/s23094392","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,29]]}}}