{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:37:35Z","timestamp":1783438655324,"version":"3.54.6"},"reference-count":44,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T00:00:00Z","timestamp":1692316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The prediction of system degradation is very important as it serves as an important basis for the formulation of condition-based maintenance strategies. An effective health indicator (HI) plays a key role in the prediction of system degradation as it enables vital information for critical tasks ranging from fault diagnosis to remaining useful life prediction. To address this issue, a method for monitoring data fusion and health indicator construction based on an autoencoder (AE) and a long short-term memory (LSTM) network is proposed in this study to improve the predictability and effectiveness of health indicators. Firstly, an unsupervised method and overall framework for HI construction is built based on a deep autoencoder and an LSTM neural network. The neural network is trained fully based on the normal operating monitoring data and then the construction error of the AE model is adopted as the health indicator of the system. Secondly, we propose related machine learning techniques for monitoring data processing to overcome the issue of data fusion, such as mutual information for sensor selection and t-distributed stochastic neighbor embedding (T-SNE) for operating condition identification. Thirdly, in order to verify the performance of the proposed method, experiments are conducted based on the CMAPSS dataset and results are compared with algorithms of principal component analysis (PCA) and a vanilla autoencoder model. Result shows that the LSTM-AE model outperforms the PCA and Vanilla-AE model in the metrics of monotonicity, trendability, prognosability, and fitness. Fourthly, in order to analyze the impact of the time step of the LSMT-AE model on HI construction, we construct and analyze the system HI curve under different time steps of 5, 10, 15, 20, and 25 cycles. Finally, the results demonstrate that the proposed method for HI construction can effectively characterize the health state of a system, which is helpful for the development of further failure prognostics and converting the scheduled maintenance into condition-based maintenance.<\/jats:p>","DOI":"10.3390\/s23167239","type":"journal-article","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T10:28:48Z","timestamp":1692354528000},"page":"7239","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["An Unsupervised Machine Learning Approach for Monitoring Data Fusion and Health Indicator Construction"],"prefix":"10.3390","volume":"23","author":[{"given":"Lin","family":"Huang","sequence":"first","affiliation":[{"name":"Ship Comprehensive Test and Training Base, Naval University of Engineering, Wuhan 430033, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Naval University of Engineering, Wuhan 430033, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yajie","family":"Liu","sequence":"additional","affiliation":[{"name":"Ship Comprehensive Test and Training Base, Naval University of Engineering, Wuhan 430033, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Gong","sequence":"additional","affiliation":[{"name":"Ship Comprehensive Test and Training Base, Naval University of Engineering, Wuhan 430033, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,8,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"108063","DOI":"10.1016\/j.ress.2021.108063","article-title":"Prognostics and health management: A review from the perspectives of design, development and decision","volume":"217","author":"Hu","year":"2022","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Quatrini, E., Costantino, F., Di Gravio, G., and Patriarca, R. (2020). Condition-Based Maintenance\u2014An Extensive Literature Review. Machines, 8.","DOI":"10.3390\/machines8020031"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"793161","DOI":"10.1155\/2015\/793161","article-title":"Prognostics and Health Management: A Review on Data Driven Approaches","volume":"2015","author":"Tsui","year":"2015","journal-title":"Math. Probl. Eng."},{"key":"ref_4","first-page":"41","article-title":"Autoencoder based Semi-Supervised Anomaly Detection in Turbofan Engines","volume":"11","author":"Bataineh","year":"2020","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.isatra.2020.03.017","article-title":"An automated health indicator construction methodology for prognostics based on multi-criteria optimization","volume":"113","author":"Nguyen","year":"2021","journal-title":"ISA Trans."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"107241","DOI":"10.1016\/j.ress.2020.107241","article-title":"A generalized remaining useful life prediction method for complex systems based on composite health indicator","volume":"205","author":"Wen","year":"2021","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"107871","DOI":"10.1016\/j.ress.2021.107871","article-title":"Remaining useful life prediction based on intentional noise injection and feature reconstruction","volume":"215","author":"Xiao","year":"2021","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2483","DOI":"10.1109\/TII.2019.2905295","article-title":"A Survey on Model-Based Distributed Control and Filtering for Industrial Cyber-Physical Systems","volume":"15","author":"Ding","year":"2019","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Cofre-Martel, S., Droguett, E.L., and Modarres, M. (2021). Big Machinery Data Preprocessing Methodology for Data-Driven Models in Prognostics and Health Management. Sensors, 21.","DOI":"10.3390\/s21206841"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"105140","DOI":"10.1016\/j.engappai.2022.105140","article-title":"A robust model selection framework for fault detection and system health monitoring with limited failure examples: Heterogeneous data fusion and formal sensitivity bounds","volume":"114","author":"Rocchetta","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"110044","DOI":"10.1016\/j.measurement.2021.110044","article-title":"Research on a rolling bearing health monitoring algorithm oriented to industrial big data","volume":"185","author":"Zhu","year":"2021","journal-title":"Measurement"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"108263","DOI":"10.1016\/j.ress.2021.108263","article-title":"Health status assessment and remaining useful life prediction of aero-engine based on BiGRU and MMoE","volume":"220","author":"Zhang","year":"2022","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"108573","DOI":"10.1016\/j.ymssp.2021.108573","article-title":"An unsupervised feature learning based health indicator construction method for performance assessment of machines","volume":"167","author":"Guo","year":"2022","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"107853","DOI":"10.1016\/j.ymssp.2021.107853","article-title":"Data-driven prognostic scheme for rolling-element bearings using a new health index and variants of least-square support vector machines","volume":"160","author":"Islam","year":"2021","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1016\/j.measurement.2019.06.038","article-title":"Degradation evaluation of slewing bearing using HMM and improved GRU","volume":"146","author":"Wang","year":"2019","journal-title":"Measurement"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"114500","DOI":"10.1016\/j.microrel.2022.114500","article-title":"A novel Bayesian multivariate linear regression model for online state-of-health estimation of Lithium-ion battery using multiple health indicators","volume":"131","author":"Lyu","year":"2022","journal-title":"Microelectron. Reliab."},{"key":"ref_17","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_18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jmsy.2019.11.008","article-title":"Health indicator construction of machinery based on end-to-end trainable convolution recurrent neural networks","volume":"54","author":"Chen","year":"2020","journal-title":"J. Manuf. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"101247","DOI":"10.1016\/j.aei.2021.101247","article-title":"A convolutional neural network based degradation indicator construction and health prognosis using bidirectional long short-term memory network for rolling bearings","volume":"48","author":"Cheng","year":"2021","journal-title":"Adv. Eng. Inform."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"107379","DOI":"10.1016\/j.asoc.2021.107379","article-title":"Health condition monitoring of machines based on long short-term memory convolutional autoencoder","volume":"107","author":"Ye","year":"2021","journal-title":"Appl. Soft Comput."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"111843","DOI":"10.1016\/j.rser.2021.111843","article-title":"An end-to-end neural network framework for state-of-health estimation and remaining useful life prediction of electric vehicle lithium batteries","volume":"156","author":"Li","year":"2022","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"102145","DOI":"10.1016\/j.rcim.2021.102145","article-title":"Transfer learning enabled convolutional neural networks for estimating health state of cutting tools","volume":"71","author":"Marei","year":"2021","journal-title":"Robot. Comput.-Integr. Manuf."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"107195","DOI":"10.1016\/j.compeleceng.2021.107195","article-title":"Generative adversarial networks based remaining useful life estimation for IIoT","volume":"92","author":"Behera","year":"2021","journal-title":"Comput. Electr. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"110176","DOI":"10.1016\/j.asoc.2023.110176","article-title":"A comprehensive survey on design and application of autoencoder in deep learning","volume":"138","author":"Li","year":"2023","journal-title":"Appl. Soft Comput."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., and Manzagol, P.A. (2008, January 5\u20139). Extracting and Composing Robust Features with Denoising Autoencoders. Proceedings of the Twenty-Fifth International Conference (ICML 2008) on Machine Learning, Helsinki, Finland.","DOI":"10.1145\/1390156.1390294"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"105005","DOI":"10.1088\/1361-6501\/ab8c0f","article-title":"Sparse auto-encoder with regularization method for health indicator construction and remaining useful life prediction of rolling bearing","volume":"31","author":"She","year":"2020","journal-title":"Meas. Sci. Technol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"106119","DOI":"10.1016\/j.asoc.2020.106119","article-title":"Constructing a health indicator for roller bearings by using a stacked auto-encoder with an exponential function to eliminate concussion","volume":"89","author":"Xu","year":"2020","journal-title":"Appl. Soft Comput."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Jakubowski, J., Stanisz, P., Bobek, S., and Nalepa, G.J. (2022). Anomaly Detection in Asset Degradation Process Using Variational Autoencoder and Explanations. Sensors, 22.","DOI":"10.3390\/s22010291"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"102282","DOI":"10.1016\/j.ijinfomgt.2020.102282","article-title":"Forecasting and Anomaly Detection approaches using LSTM and LSTM Autoencoder techniques with the applications in supply chain management","volume":"57","author":"Nguyen","year":"2021","journal-title":"Int. J. Inf. Manag."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"576","DOI":"10.1016\/j.jmsy.2021.10.011","article-title":"Remaining useful life prediction of bearing based on stacked autoencoder and recurrent neural network","volume":"61","author":"Han","year":"2021","journal-title":"J. Manuf. Syst."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"110460","DOI":"10.1016\/j.measurement.2021.110460","article-title":"Autoencoder-based representation learning and its application in intelligent fault diagnosis: A review","volume":"189","author":"Yang","year":"2022","journal-title":"Measurement"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"107327","DOI":"10.1016\/j.ymssp.2020.107327","article-title":"A hybrid classification autoencoder for semi-supervised fault diagnosis in rotating machinery","volume":"149","author":"Wu","year":"2021","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"3235","DOI":"10.1007\/s00521-020-05186-x","article-title":"Data-driven system health monitoring technique using autoencoder for the safety management of commercial aircraft","volume":"33","author":"Lee","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"2255005","DOI":"10.1142\/S0218001422550059","article-title":"Mutual Information Variational Autoencoders and Its Application to Feature Extraction of Multivariate Time Series","volume":"36","author":"Li","year":"2022","journal-title":"Int. J. Pattern Recognit. Artif. Intell."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"066138","DOI":"10.1103\/PhysRevE.69.066138","article-title":"Estimating mutual information","volume":"69","author":"Grassberger","year":"2004","journal-title":"Phys. Rev. E"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1016\/j.neucom.2016.11.047","article-title":"Theoretical evaluation of feature selection methods based on mutual information","volume":"226","author":"Pascoal","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"120652","DOI":"10.1016\/j.saa.2021.120652","article-title":"A variable selection method based on mutual information and variance inflation factor","volume":"268","author":"Cheng","year":"2022","journal-title":"Spectrochim. Acta Part A Mol. Biomol. Spectrosc."},{"key":"ref_38","unstructured":"Zaremba, W., Sutskever, I., and Vinyals, O. (2014). Recurrent neural network regularization. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"105582","DOI":"10.1016\/j.engappai.2022.105582","article-title":"Developing health indicators and RUL prognostics for systems with few failure instances and varying operating conditions using a LSTM autoencoder","volume":"117","author":"Mitici","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Saxena, A., Goebel, K., Simon, D., and Eklund, N. (2008, January 6\u20139). Damage propagation modeling for aircraft engine run-to-failure simulation. Proceedings of the 2008 International Conference on Prognostics and Health Management, Denver, CO, USA.","DOI":"10.1109\/PHM.2008.4711414"},{"key":"ref_41","first-page":"1060","article-title":"Stability of feature selection algorithm: A review","volume":"34","author":"Khaire","year":"2022","journal-title":"J. King Saud Univ.-Comput. Inf. Sci."},{"key":"ref_42","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_43","doi-asserted-by":"crossref","first-page":"107890","DOI":"10.1016\/j.measurement.2020.107890","article-title":"Complex engineered system health indexes extraction using low frequency raw time-series data based on deep learning methods","volume":"161","author":"Liu","year":"2020","journal-title":"Measurement"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"103667","DOI":"10.1016\/j.artint.2022.103667","article-title":"Relation between prognostics predictor evaluation metrics and local interpretability SHAP values","volume":"306","author":"Baptista","year":"2022","journal-title":"Artif. Intell."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/16\/7239\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:36:19Z","timestamp":1760128579000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/16\/7239"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,18]]},"references-count":44,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2023,8]]}},"alternative-id":["s23167239"],"URL":"https:\/\/doi.org\/10.3390\/s23167239","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,18]]}}}