{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T22:16:12Z","timestamp":1785190572559,"version":"3.55.0"},"reference-count":38,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2022,7,11]],"date-time":"2022-07-11T00:00:00Z","timestamp":1657497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"African Center of Excellence in Internet of Things (ACEIoT), University of Rwandas"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>A precise prediction of the health status of industrial equipment is of significant importance to determine its reliability and lifespan. This prediction provides users information that is useful in determining when to service, repair, or replace the unhealthy equipment\u2019s components. In the last decades, many works have been conducted on data-driven prognostic models to estimate the asset\u2019s remaining useful life. These models require updates on the novel happenings from regular diagnostics, otherwise, failure may happen before the estimated time due to different facts that may oblige rapid maintenance actions, including unexpected replacement. Adding to offline prognostic models, the continuous monitoring and prediction of remaining useful life can prevent failures, increase the useful lifespan through on-time maintenance actions, and reduce the unnecessary preventive maintenance and associated costs. This paper presents the ability of the two real-time tiny predictive analytics models: tiny long short-term memory (TinyLSTM) and sequential dense neural network (DNN). The model (TinyModel) from Edge Impulse is used to predict the remaining useful life of the equipment by considering the status of its different components. The equipment degradation insights were assessed through the real-time data gathered from operating equipment. To label our dataset, fuzzy logic based on the maintainer\u2019s expertise is used to generate maintenance priorities, which are later used to compute the actual remaining useful life. The predictive analytic models were developed and performed well, with an evaluation loss of 0.01 and 0.11, respectively, for the LSTM and model from Edge Impulse. Both models were converted into TinyModels for on-device deployment. Unseen data were used to simulate the deployment of both TinyModels. Conferring to the evaluation and deployment results, both TinyLSTM and TinyModel from Edge Impulse are powerful in real-time predictive maintenance, but the model from Edge Impulse is much easier in terms of development, conversion to Tiny version, and deployment.<\/jats:p>","DOI":"10.3390\/s22145174","type":"journal-article","created":{"date-parts":[[2022,7,11]],"date-time":"2022-07-11T00:06:21Z","timestamp":1657497981000},"page":"5174","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":50,"title":["On-Device IoT-Based Predictive Maintenance Analytics Model: Comparing TinyLSTM and TinyModel from Edge Impulse"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6655-2893","authenticated-orcid":false,"given":"Irene Niyonambaza","family":"Mihigo","sequence":"first","affiliation":[{"name":"African Centre of Excellence in Internet of Things, College of Science and Technology, University of Rwanda, Kigali P.O. Box 4285, Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0578-0830","authenticated-orcid":false,"given":"Marco","family":"Zennaro","sequence":"additional","affiliation":[{"name":"Telecommunications\/ICT4D Laboratory, The Abdus Salam International Centre for Theoretical Physics, Strada Costiera, 34151 Trieste, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5687-5645","authenticated-orcid":false,"given":"Alfred","family":"Uwitonze","sequence":"additional","affiliation":[{"name":"College of Science and Technology, University of Rwanda, Kigali P.O. Box 4285, Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3217-9725","authenticated-orcid":false,"given":"James","family":"Rwigema","sequence":"additional","affiliation":[{"name":"College of Science and Technology, University of Rwanda, Kigali P.O. Box 4285, Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6810-3036","authenticated-orcid":false,"given":"Marcelo","family":"Rovai","sequence":"additional","affiliation":[{"name":"Instituto de Engenharia de Sistemas e Tecnologia da Informa\u00e7\u00e3o, Universidade Federal de Itajub\u00e1, Itajuba 37500-903, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,7,11]]},"reference":[{"key":"ref_1","unstructured":"Ran, Y., Zhou, X., Lin, P., Wen, Y., and Deng, R. (2019). A Survey of Predictive Maintenance: Systems, Purposes and Approaches. arXiv."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1016\/j.ymssp.2013.06.004","article-title":"Prognostics and health management design for rotary machinery systems\u2014Reviews, methodology and applications","volume":"42","author":"Lee","year":"2014","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1016\/j.jmsy.2020.06.014","article-title":"Anomaly monitoring improves remaining useful life estimation of industrial machinery","volume":"56","author":"Aydemir","year":"2020","journal-title":"J. Manuf. Syst."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"103182","DOI":"10.1016\/j.compind.2019.103182","article-title":"An ensemble framework based on convolutional bi-directional LSTM with multiple time windows for remaining useful life estimation","volume":"115","author":"Xia","year":"2020","journal-title":"Comput. Ind."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"106330","DOI":"10.1016\/j.ymssp.2019.106330","article-title":"Deep separable convolutional network for remaining useful life prediction of machinery","volume":"134","author":"Wang","year":"2019","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.neucom.2017.05.063","article-title":"Remaining useful life estimation of engineered systems using vanilla LSTM neural networks","volume":"275","author":"Wu","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"106113","DOI":"10.1016\/j.asoc.2020.106113","article-title":"Remaining useful life prediction using multi-scale deep convolutional neural network","volume":"89","author":"Li","year":"2020","journal-title":"Appl. Soft Comput. J."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1803","DOI":"10.1016\/j.ymssp.2010.11.018","article-title":"Prognostic modelling options for remaining useful life estimation by industry","volume":"25","author":"Sikorska","year":"2011","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"114598","DOI":"10.1016\/j.eswa.2021.114598","article-title":"Predictive maintenance system for production lines in manufacturing: A machine learning approach using IoT data in real-time","volume":"173","author":"Ayvaz","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1049","DOI":"10.1109\/TII.2015.2462296","article-title":"Stochastic Scheduling of Renewable and CHP-Based Microgrids","volume":"11","author":"Alipour","year":"2015","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ress.2017.11.021","article-title":"Remaining useful life estimation in prognostics using deep convolution neural networks","volume":"172","author":"Li","year":"2018","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1751","DOI":"10.1016\/j.engappai.2013.02.006","article-title":"Remaining useful life estimation based on nonlinear feature reduction and support vector regression","volume":"26","author":"Benkedjouh","year":"2013","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_13","first-page":"8616039","article-title":"Failure prediction of aircraft equipment using machine learning with a hybrid data preparation method","volume":"2020","author":"Celikmih","year":"2020","journal-title":"Sci. Program."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhang, X.H., and Kang, J.S. (2010, January 13\u201314). Hidden Markov models in bearing fault diagnosis and prognosis. Proceedings of the 2010 Second International Conference on Computational Intelligence and Natural Computing, Wuhan, China.","DOI":"10.1109\/CINC.2010.5643712"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"100341","DOI":"10.1016\/j.cosrev.2020.100341","article-title":"Machine Learning and Deep Learning in smart manufacturing: The Smart Grid paradigm","volume":"40","author":"Kotsiopoulos","year":"2021","journal-title":"Comput. Sci. Rev."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1016\/j.jmsy.2018.01.003","article-title":"Deep learning for smart manufacturing: Methods and applications","volume":"48","author":"Thanasis","year":"2018","journal-title":"J. Manuf. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1007\/978-3-030-67667-4_28","article-title":"Automatic Remaining Useful Life Estimation Framework with Embedded Convolutional LSTM as the Backbone","volume":"12460","author":"Zhou","year":"2021","journal-title":"Lect. Notes Comput. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"75464","DOI":"10.1109\/ACCESS.2019.2919566","article-title":"A Directed Acyclic Graph Network Combined With CNN and LSTM for Remaining Useful Life Prediction","volume":"7","author":"Li","year":"2019","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.neucom.2018.09.076","article-title":"Bidirectional handshaking LSTM for remaining useful life prediction","volume":"323","author":"Elsheikh","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1016\/j.neucom.2020.03.041","article-title":"Averaged Bi-LSTM networks for RUL prognostics with non-life-cycle labeled dataset","volume":"402","author":"Yu","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"4585","DOI":"10.1109\/JIOT.2019.2957029","article-title":"Challenges to IoT-Enabled Predictive Maintenance for Industry 4.0","volume":"7","author":"Compare","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_22","unstructured":"(2022, May 30). Advanced ML for Every Solution. Available online: https:\/\/www.edgeimpulse.com."},{"key":"ref_23","unstructured":"(2022, May 30). About Keras. Available online: https:\/\/keras.io\/about\/."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Niyonambaza, I., Zennaro, M., and Uwitonze, A. (2020). Predictive maintenance (Pdm) structure using internet of things (iot) for mechanical equipment used into hospitals in Rwanda. Futur. Internet, 12.","DOI":"10.3390\/fi12120224"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1177\/1687814020919207","article-title":"An intelligent approach for data pre-processing and analysis in predictive maintenance with an industrial case study","volume":"12","author":"Bekar","year":"2020","journal-title":"Adv. Mech. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1016\/S0019-9958(65)90241-X","article-title":"Fuzzy sets","volume":"8","author":"Zadeh","year":"1965","journal-title":"Inf. Control"},{"key":"ref_27","unstructured":"Mihigo, I.N., Zennaro, M., and Uwitonze, A. (2021, January 1\u20133). Enhancing the Priority for the Maintenance Activities of the Hospitals\u2019 Mechanical Equipment Using the Fuzzy Expert System. Proceedings of the 13th EAI International Conference, AFRICOMM 2021, Zanzibar, Tanzania."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Baban, M., Baban, C.F., and Moisi, B. (2018, January 27\u201330). A Fuzzy Logic-Based Approach for Predictive Maintenance of Grinding Wheels of Automated Grinding Lines. Proceedings of the 23rd International Conference on Methods and Models in Automation and Robotics MMAR, Miedzyzdroje, Poland.","DOI":"10.1109\/MMAR.2018.8486144"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"83504","DOI":"10.1109\/ACCESS.2019.2923791","article-title":"Maintenance Decision-Making Support for Textile Machines: A Knowledge-Based Approach Using Fuzzy Logic and Vibration Monitoring","volume":"7","author":"Baban","year":"2019","journal-title":"IEEE Access"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1108\/02656711111097571","article-title":"Prioritization of maintenance tasks on industrial equipment for reliability: A fuzzy approach","volume":"28","author":"Kumar","year":"2011","journal-title":"Int. J. Qual. Reliab. Manag."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1177\/1847979018776172","article-title":"Optimal maintenance strategy selection based on a fuzzy analytical network process: A case study on a 5-MW powerhouse","volume":"10","author":"Borjalilu","year":"2018","journal-title":"Int. J. Eng. Bus. Manag."},{"key":"ref_32","first-page":"27","article-title":"Development of an intelligent decision making tool for maintenance planning using fuzzy logic and dynamic scheduling","volume":"12","author":"Andrew","year":"2020","journal-title":"Int. J. Inf. Technol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/j.procs.2019.01.065","article-title":"Risk Assessment of Maintenance activities using Fuzzy Logic","volume":"148","author":"Gallab","year":"2019","journal-title":"Procedia Comput. Sci."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1109\/21.256541","article-title":"ANFIS: Adaptive Network-Based Fuzzy Inference System","volume":"23","author":"Jang","year":"1993","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"ref_35","unstructured":"(2022, May 30). Fuzzy Logic\u2014Controls, Concepts, Theories and Application: A Mamdani Type Fuzzy Logic Controller. Available online: www.intechopen.com."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_37","unstructured":"(2022, May 30). TensoFlow Home Page. Available online: https:\/\/www.tensorflow.org\/."},{"key":"ref_38","unstructured":"Arduino (2022, May 30). Nano Sense Ble. Available online: https:\/\/docs.arduino.cc\/hardware\/nano-33-ble-sense\/."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/14\/5174\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:47:44Z","timestamp":1760140064000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/14\/5174"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,11]]},"references-count":38,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2022,7]]}},"alternative-id":["s22145174"],"URL":"https:\/\/doi.org\/10.3390\/s22145174","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,11]]}}}