{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T14:31:09Z","timestamp":1786113069008,"version":"build-2736575974"},"reference-count":35,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the Science and Technology Project of State Grid Fujian Electric Power Co., LTD, China","award":["52130X250007"],"award-info":[{"award-number":["52130X250007"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Smart meter sensors in coastal environments suffer severe accuracy degradation due to salt fog corrosion, high humidity, and temperature cycling affecting current transformers, voltage dividers, and measurement circuits. This study proposes a reliability prediction framework addressing multi-stress degradation in harsh marine atmospheres. The framework integrates an enhanced Transformer with multi-scale attention, a Bidirectional Long Short-Term Memory (BiLSTM) network for local degradation patterns, and a standard Transformer, unified through particle swarm optimization for dynamic weight adjustment. Validation using six years of field data comprising 10.5 million records from 200 sensors on Meizhou Island, China, demonstrates superior performance, achieving a coefficient of determination of 0.944 and a root mean square error of 0.0121%, representing a 6.9% improvement over the best individual model. To capture coastal-specific effects, two novel indices are introduced: the Salt Fog Corrosion Index, quantifying cumulative chloride deposition, and the Electrochemical Activity Factor, modeling electrochemical corrosion potential. Feature analysis identifies load current-temperature interaction with correlation 0.76 as the dominant drift mechanism, consistent with Joule heating theory. Field deployment verifies the framework\u2019s ability to predict failures about 5 days in advance with 0.01 percentage point accuracy, enabling condition-based maintenance and reducing out-of-specification operation time by 85%. This research provides practical tools for sensor reliability in harsh environments beyond smart metering.<\/jats:p>","DOI":"10.1371\/journal.pone.0355304","type":"journal-article","created":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T17:36:12Z","timestamp":1785951372000},"page":"e0355304","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning framework for predicting measurement error drift in smart meter sensors under harsh coastal environments"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2774-4945","authenticated-orcid":true,"given":"Tianfu","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"issue":"4","key":"pone.0355304.ref001","doi-asserted-by":"crossref","first-page":"297","DOI":"10.3390\/en9040297","article-title":"Smart distribution systems","volume":"9","author":"Y Jiang","year":"2016","journal-title":"Energies"},{"key":"pone.0355304.ref002","doi-asserted-by":"crossref","first-page":"1217","DOI":"10.1016\/j.rser.2014.07.187","article-title":"An instrumentation engineer\u2019s review on smart grid: critical applications and parameters","volume":"40","author":"J Bhatt","year":"2014","journal-title":"Renew Sustain Energy Rev"},{"issue":"2","key":"pone.0355304.ref003","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TNSM.2021.3078381","article-title":"A unified deep learning anomaly detection and classification approach for smart grid environments","volume":"18","author":"I Siniosoglou","year":"2021","journal-title":"IEEE Trans Netw Serv Manage"},{"issue":"2","key":"pone.0355304.ref004","doi-asserted-by":"crossref","first-page":"1007","DOI":"10.1016\/j.enpol.2010.11.037","article-title":"Electricity theft: overview, issues, prevention and a smart meter based approach to control theft","volume":"39","author":"SSSR Depuru","year":"2011","journal-title":"Energy Policy"},{"key":"pone.0355304.ref005","first-page":"1009","volume-title":"Power line channel noise modeling algorithm based on IGA algorithm and BP neural network","author":"X Yang","year":"2024"},{"key":"pone.0355304.ref006","first-page":"108834","article-title":"Corrosion and interfacial contact resistance of AISI 316L stainless steel coated with conductive layers under salt spray environment","volume":"174","author":"P Yi","year":"2020","journal-title":"Corros Sci"},{"issue":"1","key":"pone.0355304.ref007","first-page":"95","article-title":"National Energy Administration releases 2023 national statistical data on the electric power industry","volume":"40","author":"Energy Administration of China N","year":"2024","journal-title":"Electr Power Technol Environ Prot"},{"key":"pone.0355304.ref008","doi-asserted-by":"crossref","first-page":"109192","DOI":"10.1016\/j.epsr.2023.109192","article-title":"A measurement error prediction framework for smart meters under extreme natural environment stresses","volume":"218","author":"L Ma","year":"2023","journal-title":"Electr Power Syst Res"},{"issue":"23","key":"pone.0355304.ref009","doi-asserted-by":"crossref","first-page":"11457","DOI":"10.3390\/app112311457","article-title":"Effects of environmental and electrical factors on metering error and consistency of smart electricity meters","volume":"11","author":"S Xiong","year":"2021","journal-title":"Appl Sci"},{"issue":"3","key":"pone.0355304.ref010","first-page":"597","article-title":"Thermal cycling reliability and interfacial reaction of Sn-Cu solder joints with ENIG and ENEPIG surface finishes","volume":"31","author":"BI Noh","year":"2008","journal-title":"IEEE Trans Compon Packag Technol"},{"key":"pone.0355304.ref011","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/j.ijepes.2013.11.023","article-title":"Smart electricity meter reliability prediction based on accelerated degradation testing and modeling","volume":"56","author":"Z Yang","year":"2014","journal-title":"Int J Electr Power Energy Syst"},{"key":"pone.0355304.ref012","doi-asserted-by":"crossref","first-page":"109503","DOI":"10.1016\/j.engappai.2024.109503","article-title":"Explainable artificial intelligence of tree-based algorithms for fault detection and diagnosis in grid-connected photovoltaic systems","volume":"139","author":"HN Noura","year":"2025","journal-title":"Eng Appl Artif Intell"},{"key":"pone.0355304.ref013","volume-title":"Time series analysis: forecasting and control","author":"GE Box","year":"2015"},{"issue":"6","key":"pone.0355304.ref014","doi-asserted-by":"crossref","first-page":"3762","DOI":"10.1109\/TII.2020.3025314","article-title":"Probability analysis for failure assessment of electric energy metering equipment under multiple extreme stresses","volume":"17","author":"W Qiu","year":"2021","journal-title":"IEEE Trans Ind Inf"},{"key":"pone.0355304.ref015","volume-title":"The nature of statistical learning theory","author":"V Vapnik","year":"2013"},{"key":"pone.0355304.ref016","first-page":"1208","volume-title":"Forecasting smart meter energy usage using distributed systems and machine learning","author":"C Dong","year":"2018"},{"issue":"1","key":"pone.0355304.ref017","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1109\/TSG.2017.2753802","article-title":"Short-term residential load forecasting based on LSTM recurrent neural network","volume":"10","author":"W Kong","year":"2019","journal-title":"IEEE Trans Smart Grid"},{"key":"pone.0355304.ref018","article-title":"Attention is all you need","volume":"30","author":"A Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"issue":"12","key":"pone.0355304.ref019","doi-asserted-by":"crossref","first-page":"11106","DOI":"10.1609\/aaai.v35i12.17325","article-title":"Informer: beyond efficient transformer for long sequence time-series forecasting","volume":"35","author":"H Zhou","year":"2021","journal-title":"AAAI"},{"key":"pone.0355304.ref020","first-page":"22419","article-title":"Autoformer: decomposition transformers with auto-correlation for long-term series forecasting","volume":"34","author":"H Wu","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"issue":"7","key":"pone.0355304.ref021","doi-asserted-by":"crossref","first-page":"1711","DOI":"10.3390\/s19071711","article-title":"Internet of things in marine environment monitoring: a review","volume":"19","author":"G Xu","year":"2019","journal-title":"Sensors (Basel)"},{"issue":"15","key":"pone.0355304.ref022","doi-asserted-by":"crossref","first-page":"5200","DOI":"10.3390\/s21155200","article-title":"Explainable anomaly detection framework for maritime main engine sensor data","volume":"21","author":"D Kim","year":"2021","journal-title":"Sensors (Basel)"},{"issue":"4","key":"pone.0355304.ref023","doi-asserted-by":"crossref","first-page":"1470","DOI":"10.3390\/s21041470","article-title":"Predictive maintenance and intelligent sensors in smart factory: review","volume":"21","author":"M Pech","year":"2021","journal-title":"Sensors (Basel)"},{"issue":"23","key":"pone.0355304.ref024","doi-asserted-by":"crossref","first-page":"15667","DOI":"10.3390\/su142315667","article-title":"Multi-scale remaining useful life prediction using long short-term memory","volume":"14","author":"Y Wang","year":"2022","journal-title":"Sustainability"},{"key":"pone.0355304.ref025","doi-asserted-by":"crossref","first-page":"113410","DOI":"10.1016\/j.measurement.2023.113410","article-title":"Degradation trend evaluation for smart meters under high dry heat natural environments","volume":"220","author":"J Ma","year":"2023","journal-title":"Measurement"},{"key":"pone.0355304.ref026","doi-asserted-by":"crossref","first-page":"114481","DOI":"10.1016\/j.measurement.2024.114481","article-title":"Measurement error prediction-based reliability assessment framework for electric metering devices under harsh natural environments","volume":"232","author":"L Ma","year":"2024","journal-title":"Measurement"},{"key":"pone.0355304.ref027","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1016\/j.procs.2014.08.140","article-title":"Short term electricity forecasting using individual smart meter data","volume":"35","author":"K Gajowniczek","year":"2014","journal-title":"Procedia Comput Sci"},{"key":"pone.0355304.ref028","first-page":"1","volume-title":"Smart meter data analytics for load prediction using extreme learning machines and artificial neural networks","author":"P Chakraborty","year":"2020"},{"issue":"23","key":"pone.0355304.ref029","doi-asserted-by":"crossref","first-page":"8096","DOI":"10.3390\/s21238096","article-title":"Energy consumption forecasting for smart meters using extreme learning machine ensemble","volume":"21","author":"PSG de Mattos Neto","year":"2021","journal-title":"Sensors (Basel)"},{"issue":"21","key":"pone.0355304.ref030","doi-asserted-by":"crossref","first-page":"4794","DOI":"10.1049\/gtd2.12997","article-title":"Using machine learning ensemble method for detection of energy theft in smart meters","volume":"17","author":"AI Kawoosa","year":"2023","journal-title":"IET Gener Transm Distrib"},{"key":"pone.0355304.ref031","unstructured":"Hsu CW, Cheng YW. Deep learning detection of inaccurate smart electricity meters: a case study. arXiv:190711377 [Preprint]. 2019."},{"key":"pone.0355304.ref032","doi-asserted-by":"crossref","unstructured":"Asim M, Ming Z, Javed MY. CNN based spatio-temporal feature extraction for face anti-spoofing. 2017 2nd International Conference on Image, Vision and Computing (ICIVC); 2017. p. 234\u20138. Available from: https:\/\/api.semanticscholar.org\/CorpusID:25268360","DOI":"10.1109\/ICIVC.2017.7984552"},{"key":"pone.0355304.ref033","unstructured":"Nie Y, Nguyen NH, Sinthong P, Kalagnanam J. A time series is worth 64 words: long-term forecasting with transformers. International Conference on Learning Representations; 2023."},{"key":"pone.0355304.ref034","first-page":"27268","volume-title":"Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting","author":"T Zhou","year":"2022"},{"key":"pone.0355304.ref035","doi-asserted-by":"crossref","unstructured":"Jacob B, Kligys S, Chen B, Zhu M, Tang M, Howard A, et al. Quantization and training of neural networks for efficient integer-arithmetic-only inference. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2018. p. 2704\u201313. https:\/\/doi.org\/10.1109\/cvpr.2018.00286","DOI":"10.1109\/CVPR.2018.00286"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0355304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T17:36:23Z","timestamp":1785951383000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0355304"}},"subtitle":[],"editor":[{"given":"Massimo","family":"Mariello","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"references-count":35,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,5]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0355304","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]}}}