{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T17:09:51Z","timestamp":1780506591410,"version":"3.54.1"},"reference-count":26,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T00:00:00Z","timestamp":1745452800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>This study proposes an advanced elevator fault precursor prediction method integrating Variational Mode Decomposition (VMD), Bidirectional Long Short-Term Memory (BILSTM), and an Autoencoder with an Attention Mechanism (AEAM), collectively referred to as the VMD-BILSTM-AEAM algorithm. This model addresses the challenges of feature redundancy and noise interference in elevator operation data, improving the stability and accuracy of fault predictions. Using a dataset of elevator operation parameters, including current, voltage, and running speed, the model utilizes the Attribute Correlation Density Ranking (ACDR) method for feature selection and the TSO-optimized VMD for denoising, enhancing data quality. Cross-validation and statistical analyses, including confidence interval calculations, were employed to validate the robustness of the model. The results demonstrate that the VMD-BILSTM-AEAM algorithm achieves a mean True Positive Rate (TPR) of 0.919 with a 95% confidence interval of 0.915 to 0.924, a mean False Positive Rate (FPR) of 0.090 with a 95% confidence interval of 0.087 to 0.092, and a mean Area Under the Curve (AUC) of 0.919 with a 95% confidence interval of 0.915 to 0.923. These performance metrics indicate a significant improvement over traditional and other deep learning models, confirming the model\u2019s superiority in predictive maintenance of elevators. The robust capability of the VMD-BILSTM-AEAM algorithm to accurately process and analyze time-series data, even in the presence of noise, highlights its potential for broader applications in predictive maintenance and fault detection across various domains.<\/jats:p>","DOI":"10.1371\/journal.pone.0320566","type":"journal-article","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T17:32:18Z","timestamp":1745515938000},"page":"e0320566","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["Elevator fault precursor prediction based on improved LSTM-AE algorithm and TSO-VMD denoising technique"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9113-882X","authenticated-orcid":true,"given":"Hao","family":"Cao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyan","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,4,24]]},"reference":[{"issue":"1","key":"pone.0320566.ref001","first-page":"012026","article-title":"Building elevator safety monitoring system based on the BIM technology","volume":"1939","author":"Z An","year":"2021","journal-title":"J Phys: Conf Ser"},{"issue":"15","key":"pone.0320566.ref002","doi-asserted-by":"crossref","first-page":"2990","DOI":"10.3390\/app9152990","article-title":"Elevator fault detection using profile extraction and deep autoencoder feature extraction for acceleration and magnetic signals","volume":"9","author":"KM Mishra","year":"2019","journal-title":"Applied Sciences"},{"key":"pone.0320566.ref003","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2022\/2517077","article-title":"Study and application of an elevator failure monitoring system based on the internet of things technology","volume":"2022","author":"W Yao","year":"2022","journal-title":"Scientific Programming"},{"key":"pone.0320566.ref004","doi-asserted-by":"crossref","first-page":"7207","DOI":"10.1109\/ACCESS.2022.3141074","article-title":"Fault diagnosis of elevator doors using control state information","volume":"10","author":"H Chae","year":"2022","journal-title":"IEEE Access"},{"issue":"1","key":"pone.0320566.ref005","doi-asserted-by":"crossref","first-page":"113","DOI":"10.3390\/math12010113","article-title":"Risk evaluation of elevators based on fuzzy theory and machine learning algorithms","volume":"12","author":"W Pan","year":"2023","journal-title":"Mathematics"},{"key":"pone.0320566.ref006","article-title":"Fault Prediction of Elevator Door Lock Based on MPGA-BP Algorithm","author":"J Qiu","year":"2022","journal-title":"Journal of Physics Conference Series"},{"issue":"11","key":"pone.0320566.ref007","doi-asserted-by":"crossref","first-page":"761","DOI":"10.4236\/eng.2016.811068","article-title":"Fault prediction of elevator door system based on PSO-BP neural network","volume":"2016","author":"P Wen","year":"2016","journal-title":"Engineering"},{"key":"pone.0320566.ref008","article-title":"Fault diagnosis of Elevator Door Machines Based on Deep Convolutional Forest","author":"A Zhang","year":"2022","journal-title":"International Conference on Automation & Computing"},{"key":"pone.0320566.ref009","first-page":"696","article-title":"Elevator breakdown prediction using LSTM analysis of monitoring data","author":"G Iuculano","year":"2024","journal-title":"2024 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)"},{"key":"pone.0320566.ref010","first-page":"3079","article-title":"Semi-supervised sequence learning","volume":"2015","author":"A Dai","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pone.0320566.ref011","doi-asserted-by":"crossref","first-page":"106926","DOI":"10.1016\/j.ress.2020.106926","article-title":"An improved similarity-based prognostic algorithm for RUL estimation using an RNN autoencoder scheme","volume":"199","author":"W Yu","year":"2020","journal-title":"Reliability Engineering & System Safety"},{"issue":"12","key":"pone.0320566.ref012","first-page":"195","article-title":"Travel demand prediction based on 3D convolution and LSTM encoding and decoding","volume":"48","author":"J Teng","year":"2021","journal-title":"Computer Science"},{"issue":"1","key":"pone.0320566.ref013","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1007\/s10994-014-5460-1","article-title":"Using causal discovery for feature selection in multivariate numerical time series","volume":"101","author":"Y Sun","year":"2015","journal-title":"Machine Learning"},{"issue":"5","key":"pone.0320566.ref014","doi-asserted-by":"crossref","first-page":"1077","DOI":"10.1007\/s00521-015-1924-x","article-title":"Unsupervised feature selection for sensor time-series in pervasive computing applications","volume":"27","author":"D Bacciu","year":"2016","journal-title":"Neural Computing and Applications"},{"issue":"9","key":"pone.0320566.ref015","doi-asserted-by":"crossref","first-page":"1535","DOI":"10.3390\/app8091535","article-title":"A filter feature selection algorithm based on mutual information for intrusion detection","volume":"8","author":"F Zhao","year":"2018","journal-title":"Applied Sciences"},{"issue":"12","key":"pone.0320566.ref016","first-page":"273","article-title":"Attribute selection of multivariate time series based on correlation density","volume":"34","author":"K Zhang","year":"2017","journal-title":"Computer Applications and Software"},{"issue":"2","key":"pone.0320566.ref017","article-title":"Prediction of concrete compressive strength based on tuna swarm algorithm optimization extreme learning machine","volume":"41","author":"B Zhang","year":"2023","journal-title":"Application Research of Computers"},{"key":"pone.0320566.ref018","unstructured":"Prashar K, Talwar R, Kant C. Robust automatic cotton crop disease recognition (ACDR) method using the hybrid feature descriptor with SVM[C] 4th 2016 International Conference on Computing on sustainable Global Development. 2017:01\u20133."},{"key":"pone.0320566.ref019","first-page":"289","article-title":"A robust glaucoma screening method for fundus images using deep learning technique","author":"F Maadi","year":"2020","journal-title":"2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME)"},{"issue":"4","key":"pone.0320566.ref020","doi-asserted-by":"crossref","DOI":"10.1016\/j.acme.2017.03.005","article-title":"The flow line evolution of hot open ACDR process for titanium alloy discs","volume":"17","author":"Y Zheng","year":"2017","journal-title":"Archives of Civil and Mechanical Engineering"},{"key":"pone.0320566.ref021","doi-asserted-by":"crossref","first-page":"169379","DOI":"10.1016\/j.ijleo.2022.169379","article-title":"A novel chaotic-driven Tuna Swarm Optimizer with Newton-Raphson method for parameter identification of three-diode equivalent circuit model of solar photovoltaic cells\/modules","volume":"264","author":"C Kumar","year":"2022","journal-title":"Optik"},{"key":"pone.0320566.ref022","doi-asserted-by":"crossref","first-page":"111087","DOI":"10.1016\/j.asoc.2023.111087","article-title":"Active distribution network operational optimization problem: A multi-objective tuna swarm optimization model","volume":"150","author":"L Li","year":"2024","journal-title":"Applied Soft Computing"},{"issue":"2","key":"pone.0320566.ref023","doi-asserted-by":"crossref","first-page":"424","DOI":"10.55546\/jmm.1291032","article-title":"Improved tuna swarm optimization algorithm for engineering design problems","volume":"4","author":"H Gezici","year":"2023","journal-title":"Journal of Materials and Mechatronics"},{"key":"pone.0320566.ref024","doi-asserted-by":"crossref","first-page":"115417","DOI":"10.1016\/j.measurement.2024.115417","article-title":"RTSMFFDE-HKRR: a fault diagnosis method for train bearing in noise environment","volume":"239","author":"D He","year":"2025","journal-title":"Measurement"},{"key":"pone.0320566.ref025","doi-asserted-by":"crossref","first-page":"103123","DOI":"10.1016\/j.aei.2025.103123","article-title":"Prediction of bearing remaining useful life based on a two-stage updated digital twin","volume":"65","author":"D He","year":"2025","journal-title":"Advanced Engineering Informatics"},{"key":"pone.0320566.ref026","doi-asserted-by":"crossref","first-page":"110563","DOI":"10.1016\/j.apacoust.2025.110563","article-title":"A zero-shot model for diagnosing unknown composite faults in train bearings based on label feature vector generated fault features","volume":"232","author":"D He","year":"2025","journal-title":"Applied Acoustics"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0320566","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T17:32:30Z","timestamp":1745515950000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0320566"}},"subtitle":[],"editor":[{"given":"J.N.Chandra","family":"Sekhar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,4,24]]},"references-count":26,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4,24]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0320566","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,24]]}}}