{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T02:06:41Z","timestamp":1781230001103,"version":"3.54.1"},"reference-count":59,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["767561"],"award-info":[{"award-number":["767561"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Condition monitoring of industrial equipment, combined with machine learning algorithms, may significantly improve maintenance activities on modern cyber-physical production systems. However, data of proper quality and of adequate quantity, modeling both good operational conditions as well as abnormal situations throughout the operational lifecycle, are required. Nevertheless, this is difficult to acquire in a non-destructive approach. In this context, this study investigates an approach to enable a transition from preventive maintenance activities, that are scheduled at predetermined time intervals, into predictive ones. In order to enable such approaches in a cyber-physical production system, a deep learning algorithm is used, allowing for maintenance activities to be planned according to the actual operational status of the machine and not in advance. An autoencoder-based methodology is employed for classifying real-world machine and sensor data, into a set of condition-related labels. Real-world data collected from manufacturing operations are used for training and testing a prototype implementation of Long Short-Term Memory autoencoders for estimating the remaining useful life of the monitored equipment. Finally, the proposed approach is evaluated in a use case related to a steel industry production process.<\/jats:p>","DOI":"10.3390\/s21030972","type":"journal-article","created":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T11:40:48Z","timestamp":1612179648000},"page":"972","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":140,"title":["A Deep Learning Model for Predictive Maintenance in Cyber-Physical Production Systems Using LSTM Autoencoders"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2830-8464","authenticated-orcid":false,"given":"Xanthi","family":"Bampoula","sequence":"first","affiliation":[{"name":"Laboratory for Manufacturing Systems and Automation, Department of Mechanical Engineering and Aeronautics, University of Patras, 26504 Patras, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8736-109X","authenticated-orcid":false,"given":"Georgios","family":"Siaterlis","sequence":"additional","affiliation":[{"name":"Laboratory for Manufacturing Systems and Automation, Department of Mechanical Engineering and Aeronautics, University of Patras, 26504 Patras, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4563-714X","authenticated-orcid":false,"given":"Nikolaos","family":"Nikolakis","sequence":"additional","affiliation":[{"name":"Laboratory for Manufacturing Systems and Automation, Department of Mechanical Engineering and Aeronautics, University of Patras, 26504 Patras, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3658-6838","authenticated-orcid":false,"given":"Kosmas","family":"Alexopoulos","sequence":"additional","affiliation":[{"name":"Laboratory for Manufacturing Systems and Automation, Department of Mechanical Engineering and Aeronautics, University of Patras, 26504 Patras, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,2,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1080\/0951192X.2015.1130257","article-title":"A concept for context-aware computing in manufacturing: the white goods case","volume":"29","author":"Alexopoulos","year":"2016","journal-title":"Int. J. Comput. Integr. Manuf."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1016\/j.engappai.2018.11.007","article-title":"Industry 4.0: A bibliometric analysis and detailed overview","volume":"78","author":"Muhuri","year":"2019","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_3","unstructured":"Lee, E.A., and Seshia, S.A. (2017). Introduction to Embedded Systems: A Cyber-Physical Systems Approach, MIT Press."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Biffl, S., Gerhard, D., and L\u00fcder, A. (2017). Introduction to the multi-disciplinary engineering for cyber-physical production systems. Multi-Disciplinary Engineering for Cyber-Physical Production Systems: Data Models and Software Solutions for Handling Complex Engineering Projects, Springer International Publishing.","DOI":"10.1007\/978-3-319-56345-9"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1109\/MIE.2014.2312079","article-title":"Industrie 4.0: Hit or hype? [Industry Forum]","volume":"8","author":"Drath","year":"2014","journal-title":"IEEE Ind. Electron. Mag."},{"key":"ref_6","unstructured":"ISA (2000). ISA-95.00. 01-2000: Enterprise-Control System Integration Part 1: Models and Terminology, ISA, The Instrumentation, Systems, and Automation Society. Technical Report."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"101919","DOI":"10.1016\/j.rcim.2019.101919","article-title":"On a containerized approach for the dynamic planning and control of a cyber\u2013physical production system","volume":"64","author":"Nikolakis","year":"2020","journal-title":"Robot. Comput. Integr. Manuf."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"102173","DOI":"10.1016\/j.technovation.2020.102173","article-title":"Internet of Things and Big Data as enablers for business digitalization strategies","volume":"98","author":"Sestino","year":"2020","journal-title":"Technovation"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2328","DOI":"10.3390\/s20082328","article-title":"Big Data Analytics and Structural Health Monitoring: A Statistical Pattern Recognition-Based Approach","volume":"20","author":"Entezami","year":"2020","journal-title":"Sensors"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3884","DOI":"10.3390\/s19183884","article-title":"Predictive maintenance with sensor data analytics on a Raspberry Pi-based experimental platform","volume":"19","author":"Chuang","year":"2019","journal-title":"Sensors"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Cakir, M., Guvenc, M.A., and Mistikoglu, S. (2020). The experimental application of popular machine learning algorithms on predictive maintenance and the design of IIoT based condition monitoring system. Comput. Ind. Eng.","DOI":"10.1016\/j.cie.2020.106948"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2524","DOI":"10.3390\/s17112524","article-title":"Remaining useful life estimation of insulated gate biploar transistors (IGBTS) based on a novel volterra K-nearest neighbor optimally pruned extreme learning machine (VKOPP) model using degradation data","volume":"17","author":"Liu","year":"2017","journal-title":"Sensors"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"795","DOI":"10.3390\/s16060795","article-title":"Tool condition monitoring and remaining useful life prognostic based on awireless sensor in dry milling operations","volume":"16","author":"Zhang","year":"2016","journal-title":"Sensors"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1067","DOI":"10.1080\/0951192X.2019.1686173","article-title":"The use of Digital Twin for predictive maintenance in manufacturing","volume":"32","author":"Aivaliotis","year":"2019","journal-title":"Int. J. Comput. Integr. Manuf."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1007\/s00170-015-7317-6","article-title":"Tool wear predictability estimation in milling based on multi-sensorial data","volume":"82","author":"Stavropoulos","year":"2016","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_16","unstructured":"Oo, M.C.M., and Thein, T. (2019). An efficient predictive analytics system for high dimensional big data. J. King Saud Univ.\u2014Comput. Inf. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1038\/nmeth.4642","article-title":"Points of Significance: Statistics versus machine learning","volume":"15","author":"Bzdok","year":"2018","journal-title":"Nat. Methods"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1016\/j.cirp.2015.05.011","article-title":"Cloud-enabled prognosis for manufacturing","volume":"64","author":"Gao","year":"2015","journal-title":"CIRP Ann.\u2014Manuf. Technol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"8792","DOI":"10.1109\/TIE.2019.2891463","article-title":"A Bidirectional LSTM Prognostics Method Under Multiple Operational Conditions","volume":"66","author":"Huang","year":"2019","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_20","first-page":"489","article-title":"Attention based Echo state Network: A novel approach for fault prognosis","volume":"F148150","author":"Liu","year":"2019","journal-title":"ACM Int. Conf. Proc. Ser."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"106024","DOI":"10.1016\/j.cie.2019.106024","article-title":"A systematic literature review of machine learning methods applied to predictive maintenance","volume":"137","author":"Carvalho","year":"2019","journal-title":"Comput. Ind. Eng."},{"key":"ref_22","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_23","doi-asserted-by":"crossref","first-page":"3454","DOI":"10.3390\/en12183454","article-title":"A Process to Implement an Artificial Neural Network and Association Rules Techniques to Improve Asset Performance and Energy Efficiency","volume":"12","author":"Antomarioni","year":"2019","journal-title":"Energies"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Carbery, C.M., Woods, R., and Marshall, A.H. (2018, January 20\u201322). A Bayesian network based learning system for modelling faults in large-scale manufacturing. Proceedings of the IEEE International Conference on Industrial Technology, Lyon, France.","DOI":"10.1109\/ICIT.2018.8352377"},{"key":"ref_25","unstructured":"Wu, N., Green, B., Ben, X., and O\u2019Banion, S. (2020). Deep transformer models for time series forecasting: The influenza prevalence case. arXiv."},{"key":"ref_26","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141, and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"108513","DOI":"10.1016\/j.measurement.2020.108513","article-title":"Fault Diagnosis of Multi-channel Data by the CNN with the Multilinear Principal Component Analysis","volume":"171","author":"Guo","year":"2020","journal-title":"Measurement"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"144","DOI":"10.3390\/info10040144","article-title":"Double deep autoencoder for heterogeneous distributed clustering","volume":"10","author":"Chen","year":"2019","journal-title":"Information"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"107478","DOI":"10.1016\/j.oceaneng.2020.107478","article-title":"A dual linear autoencoder approach for vessel trajectory prediction using historical AIS data","volume":"209","author":"Murray","year":"2020","journal-title":"Ocean Eng."},{"key":"ref_30","first-page":"536","article-title":"Forecasting financial time series using a low complexity recurrent neural network and evolutionary learning approach","volume":"29","author":"Rout","year":"2017","journal-title":"J. King Saud Univ.\u2014Comput. Inf. Sci."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1033","DOI":"10.1016\/j.procir.2018.03.262","article-title":"Deep Learning for Improved System Remaining Life Prediction","volume":"72","author":"Zhang","year":"2018","journal-title":"Procedia CIRP"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1109\/TIM.2010.2078296","article-title":"Prognosis of defect propagation based on recurrent neural networks","volume":"60","author":"Malhi","year":"2011","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"107929","DOI":"10.1016\/j.measurement.2020.107929","article-title":"Deep learning for prognostics and health management: State of the art, challenges, and opportunities","volume":"163","author":"Rezaeianjouybari","year":"2020","journal-title":"Meas. J. Int. Meas. Confed."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"125188","DOI":"10.1016\/j.jhydrol.2020.125188","article-title":"Short-term runoff prediction with GRU and LSTM networks without requiring time step optimization during sample generation","volume":"589","author":"Gao","year":"2020","journal-title":"J. Hydrol."},{"key":"ref_35","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.promfg.2020.06.015","article-title":"Remaining useful life prediction using deep learning approaches: A review","volume":"49","author":"Wang","year":"2020","journal-title":"Procedia Manuf."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"108205","DOI":"10.1016\/j.measurement.2020.108205","article-title":"Long-term gear life prediction based on ordered neurons LSTM neural networks","volume":"165","author":"Yan","year":"2020","journal-title":"Measurement"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Fang, Z., Wang, Y., Peng, L., and Hong, H. (2020). Predicting flood susceptibility using long short-term memory (LSTM) neural network model. J. Hydrol.","DOI":"10.1016\/j.jhydrol.2020.125734"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"110212","DOI":"10.1016\/j.chaos.2020.110212","article-title":"Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM","volume":"140","author":"Shahid","year":"2020","journal-title":"Chaos Solitons Fractals"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1016\/j.procs.2020.01.020","article-title":"Embedded Bi-directional GRU and LSTMLearning Models to Predict Disasterson Twitter Data","volume":"165","author":"Bhuvaneswari","year":"2019","journal-title":"Procedia Comput. Sci."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Sayah, M., Guebli, D., Al Masry, Z., and Zerhouni, N. (2020). Robustness testing framework for RUL prediction Deep LSTM networks. ISA Trans., 1\u201311.","DOI":"10.1016\/j.isatra.2020.07.003"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-019-55320-6","article-title":"Unsupervised Pre-training of a Deep LSTM-based Stacked Autoencoder for Multivariate Time Series Forecasting Problems","volume":"9","author":"Sagheer","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.neucom.2017.02.045","article-title":"A recurrent neural network based health indicator for remaining useful life prediction of bearings","volume":"240","author":"Guo","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"2946","DOI":"10.3390\/s19132946","article-title":"An autoencoder and LSTM-based traffic flow prediction method","volume":"19","author":"Wei","year":"2019","journal-title":"Sensors"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Bao, W., Yue, J., and Rao, Y. (2017). A deep learning framework for financial time series using stacked autoencoders and long-short term memory. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0180944"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Gensler, A., Henze, J., Sick, B., and Raabe, N. (2016, January 9\u201312). Deep Learning for solar power forecasting\u2014An approach using AutoEncoder and LSTM Neural Networks. Proceedings of the 2016 IEEE International Conference on Systems, Man and Cybernetics (SMC),  Budapest, Hungary.","DOI":"10.1109\/SMC.2016.7844673"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep Learning in neural networks: An overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Netw."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"101057","DOI":"10.1016\/j.phycom.2020.101057","article-title":"Novel suboptimal approaches for hyperparameter tuning of deep neural network [under the shelf of optical communication]","volume":"41","author":"Amirabadi","year":"2020","journal-title":"Phys. Commun."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"106895","DOI":"10.1016\/j.compchemeng.2020.106895","article-title":"Hidden Representations in Deep Neural Networks: Part 2. Regression Problems","volume":"139","author":"Das","year":"2020","journal-title":"Comput. Chem. Eng."},{"key":"ref_50","unstructured":"Srivastava, N., Mansimov, E., and Salakhutdinov, R. (2015, January 6\u201311). Unsupervised learning of video representations using LSTMs. Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"101058","DOI":"10.1016\/j.aei.2020.101058","article-title":"Deep neural network based framework for complex correlations in engineering metrics","volume":"44","author":"Asghari","year":"2020","journal-title":"Adv. Eng. Inf."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.knosys.2019.04.019","article-title":"Hyperparameter optimization of deep neural network using univariate dynamic encoding algorithm for searches","volume":"178","author":"Yoo","year":"2019","journal-title":"Knowl.-Based Syst."},{"key":"ref_53","unstructured":"(2021, January 29). Python Language Reference, Version 3.7. Available online: https:\/\/docs.python.org\/3.7\/reference\/."},{"key":"ref_54","first-page":"2620","article-title":"Online data preprocessing: A case study approach","volume":"9","author":"Kadry","year":"2019","journal-title":"Int. J. Electr. Comput. Eng."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1016\/0043-1648(94)90155-4","article-title":"Wear of hot rolling mill rolls: An overview","volume":"176","author":"Spuzic","year":"1994","journal-title":"Wear"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"1669","DOI":"10.1007\/s00231-015-1525-3","article-title":"Understanding thermo-fluidic characteristics of a glass tube closed loop pulsating heat pipe: flow patterns and fluid oscillations","volume":"51","author":"Karthikeyan","year":"2015","journal-title":"Heat Mass-Transf.-Und Stoffuebertragung"},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Rajapaksha, N., Rajatheva, N., and Latva-Aho, M. (2019). Low complexity autoencoder based end-to-end learning of coded communications systems. arXiv.","DOI":"10.1109\/VTC2020-Spring48590.2020.9128456"},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"2408","DOI":"10.1016\/j.ifacol.2019.11.567","article-title":"Anomaly detection using Long Short Term Memory Networks and its applications in Supply Chain Management","volume":"52","author":"Tran","year":"2019","journal-title":"IFAC-PapersOnLine"},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Nguyen, H.D., Tran, K.P., Thomassey, S., and Hamad, M. (2020). Forecasting and Anomaly Detection approaches using LSTM and LSTM Autoencoder techniques with the applications in supply chain management. Int. J. Inf. Manag., 102282.","DOI":"10.1016\/j.ijinfomgt.2020.102282"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/3\/972\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:18:26Z","timestamp":1760159906000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/3\/972"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,1]]},"references-count":59,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,2]]}},"alternative-id":["s21030972"],"URL":"https:\/\/doi.org\/10.3390\/s21030972","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,1]]}}}