{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T21:06:29Z","timestamp":1790802389027,"version":"4.1.0"},"reference-count":47,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T00:00:00Z","timestamp":1786060800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science and Technology Council (NSTC), Taiwan","award":["NSTC 115-2222-E-031-002"],"award-info":[{"award-number":["NSTC 115-2222-E-031-002"]}]},{"award":["NSTC 115-2222-E-031-002"],"award-info":[{"award-number":["NSTC 115-2222-E-031-002"]}],"id":[{"id":"https:\/\/ror.org\/02kv4zf79","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Reliable Predictive Maintenance (PdM) in Industrial Internet of Things (IIoT) environments is challenged by severe class imbalance, heterogeneous sensor variables, inconsistent experimental protocols, and deployment constraints. This study proposes a Physics-Informed Benchmarking Framework that integrates engineering-guided feature construction, Mutual Information (MI)-based feature relevance analysis, standardized model development, and deployment-oriented evaluation within a unified and reproducible workflow. Using the AI4I 2020 Predictive Maintenance Dataset, Logistic Regression, Isolation Forest, Random Forest, and Extreme Gradient Boosting (XGBoost) were evaluated using identical feature representations, train\u2013test partitions, preprocessing procedures, and imbalance-handling strategies. The engineered feature space incorporates thermal, mechanical, interaction, and degradation-related information derived from the original sensor measurements. The results show that tree-based ensembles provide the strongest overall performance under severe class imbalance. Random Forest achieved an accuracy of 0.986, an F1-score of 0.722, and a ROC-AUC of 0.983, providing the best balance between failure detection and false-alarm control. XGBoost achieved an accuracy of 0.978, a recall of 0.853, and the lowest inference latency of 0.35 ms, indicating its suitability for latency-sensitive IIoT deployment. These findings demonstrate that combining engineering-guided feature representation with a standardized evaluation protocol enables fair comparison of representative learning paradigms while preserving engineering interpretability and deployment relevance.<\/jats:p>","DOI":"10.3390\/s26165026","type":"journal-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:00:43Z","timestamp":1786118443000},"page":"5026","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Physics-Informed Benchmarking Framework for Machine Learning and Tree-Based Ensembles in IIoT-Enabled Predictive Maintenance"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8942-7751","authenticated-orcid":false,"given":"Yi-Kai","family":"Su","sequence":"first","affiliation":[{"name":"Department of Financial Management, National Defense University, Taipei 112305, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1611-4259","authenticated-orcid":false,"given":"Chun-Jan","family":"Tseng","sequence":"additional","affiliation":[{"name":"Department of Data Science, Soochow University, Taipei 111002, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,7]]},"reference":[{"key":"ref_1","unstructured":"Prieto, M.D., and Mart\u00ednez, L.R. (2026). Industry 4.0: Transforming the Future beyond Manufacturing. Industry 4.0\u2014Transforming the Future Beyond Manufacturing\u2014Volume 1, Digital Technologies and Smart Industrial Systems, IntechOpen. Chapter 2."},{"key":"ref_2","first-page":"18","article-title":"A cyber-physical systems architecture for industry 4.0-based manufacturing systems","volume":"3","author":"Lee","year":"2015","journal-title":"Manuf. Lett."},{"key":"ref_3","first-page":"1","article-title":"Industry 4.0: A survey on technologies, applications and open research issues","volume":"6","author":"Lu","year":"2017","journal-title":"J. Ind. Inf. Integr."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1109\/JIOT.2016.2579198","article-title":"Edge computing: Vision and challenges","volume":"3","author":"Shi","year":"2016","journal-title":"IEEE Internet Things J."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Mobley, R.K. (2002). An Introduction to Predictive Maintenance, Elsevier.","DOI":"10.1016\/B978-075067531-4\/50006-3"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1109\/MIS.2022.3167561","article-title":"Data-driven predictive maintenance","volume":"37","author":"Gama","year":"2022","journal-title":"IEEE Intell. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1016\/j.ymssp.2017.11.016","article-title":"Machinery health prognostics: A systematic review from data acquisition to RUL prediction","volume":"104","author":"Lei","year":"2018","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Liu, C.L., Tseng, C.J., Hsaio, W.H., Wu, S.H., and Lu, S.R. (2022). Predicting the wafer material removal rate for semiconductor chemical mechanical polishing using a fusion network. Appl. Sci., 12.","DOI":"10.3390\/app122211478"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"106889","DOI":"10.1016\/j.cie.2020.106889","article-title":"Predictive maintenance in the Industry 4.0: A systematic literature review","volume":"150","author":"Zonta","year":"2020","journal-title":"Comput. Ind. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Matzka, S. (2020, January 21\u201323). Explainable artificial intelligence for predictive maintenance applications. Proceedings of the 2020 Third International Conference on Artificial Intelligence For Industries (AI4I), Irvine, CA, USA.","DOI":"10.1109\/AI4I49448.2020.00023"},{"key":"ref_11","first-page":"1","article-title":"Resource management in fog\/edge computing: A survey on architectures, infrastructure, and algorithms","volume":"52","author":"Hong","year":"2019","journal-title":"ACM Comput. Surv."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"28573","DOI":"10.1109\/ACCESS.2018.2831228","article-title":"Multi-agent systems: A survey","volume":"6","author":"Dorri","year":"2018","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from imbalanced data","volume":"21","author":"He","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Saito, T., and Rehmsmeier, M. (2015). The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0118432"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","article-title":"An introduction to ROC analysis","volume":"27","author":"Fawcett","year":"2006","journal-title":"Pattern Recognit. Lett."},{"key":"ref_16","first-page":"31","article-title":"Machine learning and deep learning based methods toward industry 4.0 predictive maintenance in induction motors: State of the art survey","volume":"15","author":"Drakaki","year":"2022","journal-title":"J. Ind. Eng. Manag."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_18","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_19","doi-asserted-by":"crossref","unstructured":"Carvalho, D.V., Pereira, E.M., and Cardoso, J.S. (2019). Machine learning interpretability: A survey on methods and metrics. Electronics, 8.","DOI":"10.3390\/electronics8080832"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.ymssp.2018.05.050","article-title":"Deep learning and its applications to machine health monitoring","volume":"115","author":"Zhao","year":"2019","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"10934","DOI":"10.1007\/s10489-021-03004-y","article-title":"Deep learning models for predictive maintenance: A survey, comparison, challenges and prospects","volume":"52","author":"Serradilla","year":"2022","journal-title":"Appl. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"4597","DOI":"10.1109\/ACCESS.2023.3347989","article-title":"Physics-informed machine learning for data anomaly detection, classification, localization, and mitigation: A review, challenges, and path forward","volume":"12","author":"Zideh","year":"2023","journal-title":"IEEE Access"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2692","DOI":"10.1109\/TPEL.2023.3328438","article-title":"Toward physics-informed machine-learning-based predictive maintenance for power converters\u2014A review","volume":"39","author":"Fassi","year":"2023","journal-title":"IEEE Trans. Power Electron."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"119191","DOI":"10.1016\/j.measurement.2025.119191","article-title":"A novel physics-informed model for tool wear monitoring under multi-machining conditions","volume":"258","author":"Li","year":"2025","journal-title":"Measurement"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.arcontrol.2018.09.003","article-title":"Review and big data perspectives on robust data mining approaches for industrial process modeling with outliers and missing data","volume":"46","author":"Zhu","year":"2018","journal-title":"Annu. Rev. Control"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"23484","DOI":"10.1109\/ACCESS.2017.2765544","article-title":"Industrial big data in an industry 4.0 environment: Challenges, schemes, and applications for predictive maintenance","volume":"5","author":"Yan","year":"2017","journal-title":"IEEE Access"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Tsallis, C., Papageorgas, P., Piromalis, D., and Munteanu, R.A. (2025). Application-wise review of Machine Learning-based predictive maintenance: Trends, challenges, and future directions. Appl. Sci., 15.","DOI":"10.3390\/app15094898"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Kaur, N. (2025). Intelligent manufacturing in Industry 4.0. Intelligent Manufacturing, CRC Press.","DOI":"10.1201\/9781032655758-2"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"4861","DOI":"10.1007\/s00170-026-17531-w","article-title":"AI-driven predictive maintenance for industry 4.0: A systematic review of models, methods, and challenges","volume":"143","author":"Meddaoui","year":"2026","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"79","DOI":"10.58471\/jds.v3i2.7267","article-title":"Feature Engineering for Predictive Maintenance: Identifying Key Predictors of Machine Defects Using Machine Learning","volume":"3","author":"Ani","year":"2025","journal-title":"J. Data Sci."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"2213","DOI":"10.1109\/JSYST.2019.2905565","article-title":"Data-driven methods for predictive maintenance of industrial equipment: A survey","volume":"13","author":"Zhang","year":"2019","journal-title":"IEEE Syst. J."},{"key":"ref_32","first-page":"5167","article-title":"Predictive maintenance using machine learning for engineering systems through real-time sensor data and anomaly detection models","volume":"5","author":"Nsor","year":"2024","journal-title":"Intl. J. Res. Publ. Rev."},{"key":"ref_33","first-page":"1157","article-title":"An introduction to variable and feature selection","volume":"3","author":"Guyon","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.1109\/TPAMI.2005.159","article-title":"Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy","volume":"27","author":"Peng","year":"2005","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/j.asoc.2016.03.013","article-title":"A hybrid framework combining data-driven and model-based methods for system remaining useful life prediction","volume":"44","author":"Liao","year":"2016","journal-title":"Appl. Soft Comput."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"e2016","DOI":"10.7717\/peerj-cs.2016","article-title":"Predictive maintenance in Industry 4.0: A survey of planning models and machine learning techniques","volume":"10","author":"Hector","year":"2024","journal-title":"PeerJ Comput. Sci."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zaidi, S.H.H., Shenfield, A., Zhang, H., and Ikpehai, A. (2026). A Systematic Review of Anomaly and Fault Detection Using Machine Learning for Industrial Machinery. Algorithms, 19.","DOI":"10.3390\/a19020108"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/s41060-024-00509-w","article-title":"A review of random forest-based feature selection methods for data science education and applications","volume":"20","author":"Iranzad","year":"2025","journal-title":"Int. J. Data Sci. Anal."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Zeng, B., Wu, S., and Yao, S. (2025). Machine Learning-Driven Paradigm for Polymer Aging Lifetime Prediction: Integrating Multi-Mechanism Coupling and Cross-Scale Modeling. Polymers, 17.","DOI":"10.3390\/polym17222991"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Liu, F.T., Ting, K.M., and Zhou, Z.H. (2008, January 15\u201319). Isolation forest. Proceedings of the 2008 Eighth IEEE International Conference on Data Mining, Pisa, Italy.","DOI":"10.1109\/ICDM.2008.17"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2907070","article-title":"A survey of predictive modeling on imbalanced domains","volume":"49","author":"Branco","year":"2016","journal-title":"ACM Comput. Surv."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"111236","DOI":"10.1016\/j.cie.2025.111236","article-title":"AI-based real-time anomaly detection in industrial engineering: A structured literature review, taxonomy, and research agenda","volume":"207","author":"Stahmann","year":"2025","journal-title":"Comput. Ind. Eng."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3732287","article-title":"A comprehensive survey on deep learning-based predictive maintenance","volume":"25","author":"Khan","year":"2026","journal-title":"ACM Trans. Embed. Comput. Syst."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Yang, Y., and Wang, H. (2025). Random forest-based machine failure prediction: A performance comparison. Appl. Sci., 15.","DOI":"10.3390\/app15168841"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1007\/s42452-025-06827-3","article-title":"Enhancing predictive maintenance in automotive industry: Addressing class imbalance using advanced machine learning techniques","volume":"7","author":"Mahale","year":"2025","journal-title":"Discov. Appl. Sci."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"112601","DOI":"10.1016\/j.enbuild.2022.112601","article-title":"A multi-task learning model for building electrical load prediction","volume":"278","author":"Liu","year":"2023","journal-title":"Energy Build."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5026\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:02:04Z","timestamp":1786118524000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5026"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,7]]},"references-count":47,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26165026"],"URL":"https:\/\/doi.org\/10.3390\/s26165026","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,7]]}}}