{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T18:12:15Z","timestamp":1778523135979,"version":"3.51.4"},"reference-count":24,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T00:00:00Z","timestamp":1778457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Accurate prediction of the Remaining Useful Life (RUL) of special gas cylinders is critical for industrial safety management. However, the nonlinear, strongly coupled degradation behaviors of these cylinders, combined with non-stationary and high-noise monitoring data, limit the performance of single deep learning models. Traditional hyperparameter tuning and signal processing methods often fail to meet the required prediction accuracy. To address these challenges, this study proposes a hybrid SSA\u2013PSO\u2013ResNet\u2013LSTM\u2013Attention framework for RUL prediction of special gas cylinders. The framework first applies Singular Spectrum Analysis (SSA) to decompose and reconstruct the 12-dimensional multi-source sensor signals, effectively suppressing noise while extracting core degradation trends. Subsequently, a ResNet\u2013LSTM\u2013Attention collaborative model is constructed, where ResNet ensures stable spatial feature propagation, LSTM captures long- and short-term temporal dependencies, and a multi-head attention mechanism emphasizes critical time steps associated with abrupt degradation. Furthermore, a Particle Swarm Optimization (PSO) algorithm is employed to globally optimize key hyperparameters, including the number of convolutional kernels, LSTM hidden units, and learning rate, mitigating the subjectivity of manual tuning. Experimental validation is conducted on 1000 real monitoring samples from 100 composite material gas cylinders, with a cylinder ID-based 7:1:2 train\u2013validation\u2013test split and stratified sampling covering four operating conditions. PSO optimizes hyperparameters using the validation set RMSE as the fitness function, and the test set is exclusively used for final performance evaluation. All results are reported as the mean \u00b1 standard deviation from grouped 5-fold cross-validation on the cylinder-wise partition. The proposed model achieves a test RMSE of 71.55, MAE of 50.63, and R2 of 0.9584, representing a 34.2% and 30.2% reduction in RMSE and MAE, respectively, compared with the second-best CNN-LSTM model, and significantly outperforming SVR, MLP, and other benchmark models. Ablation studies confirm the positive synergistic effect of each component, with the removal of either the attention mechanism or the ResNet module causing substantial performance degradation. By employing physically calibrated RUL labels and a balanced multi-condition dataset, the proposed framework achieves high predictive accuracy and good potential for industrial application, providing an effective solution for RUL prediction of special gas cylinders and similar high-pressure vessels, with potential applications in intelligent maintenance of complex industrial equipment.<\/jats:p>","DOI":"10.3390\/a19050376","type":"journal-article","created":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T17:17:42Z","timestamp":1778519862000},"page":"376","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Remaining Useful Life Prediction for Special Gas Cylinders Based on SSA\u2013PSO\u2013ResNet\u2013LSTM\u2013Attention Framework"],"prefix":"10.3390","volume":"19","author":[{"given":"Hao","family":"Hu","sequence":"first","affiliation":[{"name":"Demonstrative Software School, College of Computer Science and Cyber Security, Chengdu University of Technology, Chengdu 610059, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Oxford Brookes College, Chengdu University of Technology, Chengdu 610059, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojin","family":"Jin","sequence":"additional","affiliation":[{"name":"Oxford Brookes College, Chengdu University of Technology, Chengdu 610059, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3915-7921","authenticated-orcid":false,"given":"Bo","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Chengdu University of Technology, Chengdu 610059, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/j.jmsy.2018.04.008","article-title":"Bearing remaining useful life prediction based on deep autoencoder and deep neural networks","volume":"48","author":"Ren","year":"2018","journal-title":"J. Manuf. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1016\/j.ress.2018.11.011","article-title":"Deep learning-based remaining useful life estimation of bearings using multi-scale feature extraction","volume":"182","author":"Li","year":"2019","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"20786","DOI":"10.1109\/ACCESS.2020.2968939","article-title":"LSTM-based battery remaining useful life prediction with multi-channel charging profiles","volume":"8","author":"Park","year":"2020","journal-title":"IEEE Access"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Rezazadeh, N., Perfetto, D., De Luca, A., and Caputo, F. (2024). Ensemble learning for estimating remaining useful life: Incorporating linear, KNN, and Gaussian process regression. Advances in Remanufacturing, Springer. IWAR 2023; Lecture Notes in Mechanical Engineering.","DOI":"10.1007\/978-3-031-52649-7_16"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1007\/s44196-024-00639-w","article-title":"Prediction of remaining useful life of aero-engines based on CNN-LSTM-attention","volume":"17","author":"Deng","year":"2024","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"109642","DOI":"10.1016\/j.measurement.2021.109642","article-title":"A deep attention residual neural network-based remaining useful life prediction of machinery","volume":"181","author":"Zeng","year":"2021","journal-title":"Measurement"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.ymssp.2018.05.050","article-title":"Deep learning and its applications to machine health monitoring","volume":"115","author":"Zhao","year":"2019","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"398","DOI":"10.1016\/j.ins.2023.01.100","article-title":"Adaptive self-attention LSTM for RUL prediction of lithium-ion batteries","volume":"635","author":"Wang","year":"2023","journal-title":"Inf. Sci."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e36236","DOI":"10.1016\/j.heliyon.2024.e36236","article-title":"Remaining useful life prediction of Lithium-ion batteries using spatio-temporal multimodal attention networks","volume":"10","author":"Suh","year":"2024","journal-title":"Heliyon"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Yan, J., Xiao, X., and Li, H. (2023). Wind turbine gearbox condition monitoring using hybrid attentions and spatio-temporal BiConvLSTM network. Energies, 16.","DOI":"10.3390\/en16196786"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Golyandina, N., Nekrutkin, V., and Zhigljavsky, A. (2001). Analysis of Time Series Structure: SSA and Related Techniques, Chapman & Hall\/CRC.","DOI":"10.1201\/9781420035841"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"101118","DOI":"10.1016\/j.elerap.2022.101118","article-title":"LSTM with particle Swam optimization for sales forecasting","volume":"51","author":"He","year":"2022","journal-title":"Electron. Commer. Res. Appl."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Hafeez, F., Arfeen, Z.A., Ali, G., Masud, M.I., Hamid, M., Aman, M., Saeed, M.S., and Jumani, T.A. (2025). A Particle Swarm Optimized Multi-Model Framework for Remaining Useful Life Prediction of Lithium-Ion Batteries Using Domain-Driven Feature Engineering. World Electr. Veh. J., 16.","DOI":"10.3390\/wevj16110639"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Der, O. (2025). Multi-Output Prediction and Optimization of CO2 Laser Cutting Quality in FFF-Printed ASA Thermoplastics Using Machine Learning Approaches. Polymers, 17.","DOI":"10.3390\/polym17141910"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Basar, G. (2025). Experimental Evaluation and Machine Learning-Based Prediction of Laser Cutting Quality in FFF-Printed ABS Thermoplastics. Polymers, 17.","DOI":"10.3390\/polym17131728"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Elsner, J.B., and Tsonis, A.A. (1996). Singular Spectrum Analysis\u2014A New Tool in Time Series Analysis, Plenum Press.","DOI":"10.1007\/978-1-4757-2514-8"},{"key":"ref_17","first-page":"74","article-title":"Fault diagnosis of rolling bearing under adaptive attention LSTM-ResNet","volume":"52","author":"Jiang","year":"2024","journal-title":"Mach. Tool Hydraul."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"120063","DOI":"10.1016\/j.apenergy.2022.120063","article-title":"A deep model for short-term load forecasting applying a stacked autoencoder based on LSTM supported by a multi-stage attention mechanism","volume":"327","author":"Fazlipour","year":"2022","journal-title":"Appl. Energy"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.apenergy.2014.04.047","article-title":"An improved PSO-based charging strat-egy of electric vehicles in electrical distribution grid","volume":"128","author":"Yang","year":"2014","journal-title":"Appl. Energy"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2517011","DOI":"10.1109\/TIM.2021.3125108","article-title":"Remaining useful life prediction of lithium-ion batteries based on a mixture of ensemble empirical mode decomposition and GWO-SVR model","volume":"70","author":"Yang","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, H., Li, D., Li, D., Liu, C., Yang, X., and Zhu, G. (2023). Remaining useful life prediction of aircraft turbofan engine based on random forest feature selection and multi-layer perceptron. Appl. Sci., 13.","DOI":"10.3390\/app13127186"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"123622","DOI":"10.1016\/j.energy.2022.123622","article-title":"Remaining useful life prediction of lithium-ion batteries using a hybrid model","volume":"248","author":"Yao","year":"2022","journal-title":"Energy"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Rastegarpanah, A., Contreras, C., and Stolkin, R. (2023). Hyperparameter-optimized CNN and CNN-LSTM for predicting the remaining useful life of lithium-ion batteries. 2023 Eleventh International Conference on Intelligent Computing and Information Systems (ICICIS), IEEE.","DOI":"10.1109\/ICICIS58388.2023.10391176"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2266","DOI":"10.1007\/s11668-025-02247-y","article-title":"Remaining useful life prediction of rolling bearings based on optimized GRU and Transformer","volume":"25","author":"Yao","year":"2025","journal-title":"J. Fail. Anal. Prev."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/5\/376\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T17:31:23Z","timestamp":1778520683000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/5\/376"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,11]]},"references-count":24,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["a19050376"],"URL":"https:\/\/doi.org\/10.3390\/a19050376","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,11]]}}}