A Novel Progressive Fusion Approach for Remaining Useful Life Prediction Using Temporal-Sensor Data
Received: 6 March 2025 | Revised: 13 May 2025 | Accepted: 1 June 2025 | Online: 6 October 2025
Corresponding author: Aparna Joshi
Abstract
Accurate prediction of Remaining Useful Life (RUL) is vital for proactive maintenance and failure prevention in industrial systems. This paper introduces the Spatiotemporal Homogeneous Feature Extractor (STSF) to address limitations in existing RUL prediction methods. STSF employs a flexible, layer-wise progressive feature fusion technique that harmonizes spatial and temporal features, enhancing the model's ability to capture complex degradation patterns. To further improve prediction accuracy, the Feature Space Global Relationship Invariance (FSGRI) training method is used, grounded in supervised contrastive learning. FSGRI maintains consistent relationships between sample features and degradation trajectories during training, simplifying subsequent regression tasks. Evaluations on a C-MAPSS dataset demonstrate that STSF outperforms baseline models across multiple metrics, highlighting its effectiveness in RUL prediction.
Keywords:
remaining useful life prediction, spatiotemporal homogeneous feature extractor, feature space, global relationship invariance, feature fusionDownloads
References
M. Compare, L. Bellani, and E. Zio, "Reliability model of a component equipped with PHM capabilities," Reliability Engineering & System Safety, vol. 168, pp. 4–11, Dec. 2017.
S. Wang, Y. Lei, B. Yang, X. Li, Y. Shu, and N. Lu, "A graph neural network-based data cleaning method to prevent intelligent fault diagnosis from data contamination," Engineering Applications of Artificial Intelligence, vol. 126, Nov. 2023, Art. no. 107071.
M. Wang, X. Ma, Y. Hu, and Y. Wang, "Gear Fault Diagnosis Based on Variational Modal Decomposition and Wide+Narrow Visual Field Neural Networks," IEEE Transactions on Automation Science and Engineering, vol. 19, no. 4, pp. 3288–3299, Jul. 2022.
X. Han, Z. Wang, M. Xie, Y. He, Y. Li, and W. Wang, “Remaining useful life prediction and predictive maintenance strategies for multi-state manufacturing systems considering functional dependence,” Reliability Engineering & System Safety, vol. 210, Jun. 2021, Art. no. 107560.
X. Li et al., "A spectral self-focusing fault diagnosis method for automotive transmissions under gear-shifting conditions," Mechanical Systems and Signal Processing, vol. 200, Oct. 2023, Art. no. 110499.
J. Zhang, Y. Jiang, S. Wu, X. Li, H. Luo, and S. Yin, "Prediction of remaining useful life based on bidirectional gated recurrent unit with temporal self-attention mechanism," Reliability Engineering & System Safety, vol. 221, May 2022, Art. no. 108297.
J. Zhang, X. Li, J. Tian, H. Luo, and S. Yin, "An integrated multi-head dual sparse self-attention network for remaining useful life prediction," Reliability Engineering & System Safety, vol. 233, May 2023, Art. no. 109096.
J. Zhang et al., "A Parallel Hybrid Neural Network With Integration of Spatial and Temporal Features for Remaining Useful Life Prediction in Prognostics," IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1–12, 2023.
W. Xu, Q. Jiang, Y. Shen, Q. Zhu, and F. Xu, "New RUL Prediction Method for Rotating Machinery via Data Feature Distribution and Spatial Attention Residual Network," IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1–9, 2023.
J. Wang, S. Zhang, C. Li, L. Wu, and Y. Wang, "A Data-Driven Method With Mode Decomposition Mechanism for Remaining Useful Life Prediction of Lithium-Ion Batteries," IEEE Transactions on Power Electronics, vol. 37, no. 11, pp. 13684–13695, Aug. 2022.
G. S. Babu, P. Zhao, and X. L. Li, "Deep Convolutional Neural Network Based Regression Approach for Estimation of Remaining Useful Life," in Database Systems for Advanced Applications, 2016, pp. 214–228.
L. Ren, J. Dong, X. Wang, Z. Meng, L. Zhao, and M. J. Deen, "A Data-Driven Auto-CNN-LSTM Prediction Model for Lithium-Ion Battery Remaining Useful Life," IEEE Transactions on Industrial Informatics, vol. 17, no. 5, pp. 3478–3487, Feb. 2021.
X. Li, Y. Lei, X. Li, and B. Yang, "A Robust Wavelet-integrated Residual Network for Fault Diagnosis of Machines with Adversarial Training," in 2023 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), Seattle, WA, USA, Jun. 2023, pp. 847–851.
H. Pei, X. Si, T. Li, Z. Zhang, and Y. Lei, "Interactive Prognosis Framework Between Deep Learning and a Stochastic Process Model for Remaining Useful Life Prediction," IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 12, pp. 18000–18012, Sep. 2024.
M. Sreenatha and P. B. Mallikarjuna, "A Fault Diagnosis Technique for Wind Turbine Gearbox: An Approach using Optimized BLSTM Neural Network with Undercomplete Autoencoder," Engineering, Technology & Applied Science Research, vol. 13, no. 1, pp. 10170–10174, Feb. 2023.
A. Saxena and K. Goebel, “Turbofan Engine Degradation Simulation.” Prognostics Center of Excellence Data Set Repository - NASA, 2008, [Online]. Available: https://www.nasa.gov/intelligent-systems-division/discovery-and-systems-health/pcoe/pcoe-data-set-repository/.
Downloads
How to Cite
License
Copyright (c) 2025 Gajanan Walunjkar, Aparna Joshi, Rahul Desai, Yuvraj Gholap, Sachin Korde
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
