Reliable prognosis for complex systems based on spatial-temporal representation modeling and uncertainty-aware dynamic Fusion

Xu, Z, Bashir, M, Zhang, Q, Beer, M, Wang, J ORCID: 0000-0003-4646-9106 and Yang, Z ORCID: 0000-0003-1385-493X (2026) Reliable prognosis for complex systems based on spatial-temporal representation modeling and uncertainty-aware dynamic Fusion. Measurement Science and Technology, 37 (24). ISSN 0957-0233

Preview

Text Reliable prognosis for complex systems based on spatial temporal representation modeling and uncertainty aware dynamic Fusion.pdf - Published Version Available under License Creative Commons Attribution. Download (10MB) | Preview

Abstract

Remaining useful life (RUL) prediction for complex systems is essential for ensuring their reliability and operational safety. Deep neural networks have demonstrated strong capabilities in prognostic modeling by learning degradation patterns from multivariate sensor data. However, their performance remains limited due to two key challenges: the difficulty of jointly capturing temporal degradation dynamics and cross-sensor dependencies, and the effective fusion of information from multiple variables. To overcome these challenges, this study develops an intelligent prognostic framework composed of three main modules: (i) a spatial–temporal feature embedding module for multivariable feature encoding; (ii) a Bayesian event-triggered dynamic graph update mechanism to robustly characterize evolving spatial relationships during degradation; and (iii) an uncertainty-aware fusion module for decision-level RUL prediction. Experiments on complex system RUL prediction tasks show that the proposed spatial–temporal network significantly improves prediction accuracy. The Bayesian event-triggered graph update further makes graph evolution more robust and better aligned with degradation progression. In addition, the uncertainty-aware fusion strategy improves uncertainty calibration and interval coverage, allowing a greater proporsion of true RUL values to fall within the predicted confidence bounds. The proposed framework make significant contribution on the provition of increased more reliable RUL prediction and improved support for predictive maintenance.

Item Type:	Article
Uncontrolled Keywords:	prognostics and health management; uncertainty quantification; information fusion; decision-making; Bayesian neural network; 40 Engineering; 51 Physical Sciences; Networking and Information Technology R&D (NITRD); Bioengineering; Generic health relevance; 02 Physical Sciences; 09 Engineering; Optics; 40 Engineering; 51 Physical sciences
Subjects:	T Technology > T Technology (General) T Technology > TA Engineering (General). Civil engineering (General)
Divisions:	Engineering and Built Environment
Publisher:	IOP Publishing
Date of acceptance:	28 May 2026
Date of first compliant Open Access:	28 August 2026
Date Deposited:	28 Aug 2026 10:48
Last Modified:	28 Aug 2026 10:48
DOI or ID number:	10.1088/1361-6501/ae7463
URI:	https://researchonline.ljmu.ac.uk/id/eprint/29217

View Item