Bayesian Physics Informed Neural Networks for Reliable Transformer Prognostics

• URL: http://arxiv.org/abs/2509.15933v1
• Date: Fri, 19 Sep 2025 12:39:15 GMT
• Title: Bayesian Physics Informed Neural Networks for Reliable Transformer Prognostics
• Authors: Ibai Ramirez, Jokin Alcibar, Joel Pino, Mikel Sanz, David Pardo, Jose I. Aizpurua,
• Abstract summary: This work introduces a Bayesian Physics-Informed Neural Network (B-PINN) framework for probabilistic prognostics estimation.<n>The framework is validated against a finite element model developed and tested with real measurements from a solar power plant.<n>Results, benchmarked against a dropout-PINN baseline, show that the proposed B-PINN delivers more reliable prognostic predictions by accurately quantifying predictive uncertainty.
• Score: 1.53934570513443
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scientific Machine Learning (SciML) integrates physics and data into the learning process, offering improved generalization compared with purely data-driven models. Despite its potential, applications of SciML in prognostics remain limited, partly due to the complexity of incorporating partial differential equations (PDEs) for ageing physics and the scarcity of robust uncertainty quantification methods. This work introduces a Bayesian Physics-Informed Neural Network (B-PINN) framework for probabilistic prognostics estimation. By embedding Bayesian Neural Networks into the PINN architecture, the proposed approach produces principled, uncertainty-aware predictions. The method is applied to a transformer ageing case study, where insulation degradation is primarily driven by thermal stress. The heat diffusion PDE is used as the physical residual, and different prior distributions are investigated to examine their impact on predictive posterior distributions and their ability to encode a priori physical knowledge. The framework is validated against a finite element model developed and tested with real measurements from a solar power plant. Results, benchmarked against a dropout-PINN baseline, show that the proposed B-PINN delivers more reliable prognostic predictions by accurately quantifying predictive uncertainty. This capability is crucial for supporting robust and informed maintenance decision-making in critical power assets.

Related papers

• Disentangling Aleatoric and Epistemic Uncertainty in Physics-Informed Neural Networks. Application to Insulation Material Degradation Prognostics [1.1417805445492082]
  Most existing PIN-based prognostics approaches are deterministic or account only for uncertainty, limiting their suitability for risk-aware decision-making.<n>This work introduces a heteroscedastic Bayesian Physics-Informed Neural Network (B-PINN) framework that integrates BNNs with physics-based residual enforcement and prior distributions.<n>Results show that the proposed B-PINN provides improved predictive accuracy and better systematic uncertainty estimates than competing approaches.
  arXiv  Detail & Related papers  (2026-01-07T07:54:09Z)
• Bridging the Gap Between Bayesian Deep Learning and Ensemble Weather Forecasts [100.26854618129039]
  Weather forecasting is fundamentally challenged by the chaotic nature of the atmosphere.<n>Recent advances in Bayesian Deep Learning (BDL) offer a promising but often disconnected alternative.<n>We bridge these paradigms through a unified hybrid BDL framework for ensemble weather forecasting.
  arXiv  Detail & Related papers  (2025-11-18T07:49:52Z)
• Uncertainty Quantification for Physics-Informed Neural Networks with Extended Fiducial Inference [6.80557541703437]
  Uncertainty quantification in scientific machine learning is increasingly critical.<n>For physics-informed neural networks (PINNs), uncertainty is typically quantified using Bayesian or dropout methods.<n>We propose a novel method within the framework of extended fiducial inference (EFI) to provide rigorous uncertainty quantification for PINNs.
  arXiv  Detail & Related papers  (2025-05-25T13:18:13Z)
• Plug-and-Play Physics-informed Learning using Uncertainty Quantified Port-Hamiltonian Models [5.1732651331429516]
  We introduce a Plug-and-Play Physics-In Machine Learning (PIML) framework to address this challenge.<n>Our method employs conformal prediction to identify outlier dynamics and switches from a nominal predictor to a physics-consistent model.<n>In this way, the proposed framework produces reliable physics-informed predictions even for the out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-04-24T22:25:51Z)
• Calibrated Physics-Informed Uncertainty Quantification [16.985414812517252]
  We introduce a model-agnostic, physics-informed conformal prediction framework.<n>This framework provides guaranteed uncertainty estimates without requiring labelled data.<n>We further validate our method on neural PDE models for plasma modelling and shot design in fusion reactors.
  arXiv  Detail & Related papers  (2025-02-06T09:23:06Z)
• Tractable Function-Space Variational Inference in Bayesian Neural Networks [72.97620734290139]
  A popular approach for estimating the predictive uncertainty of neural networks is to define a prior distribution over the network parameters. We propose a scalable function-space variational inference method that allows incorporating prior information. We show that the proposed method leads to state-of-the-art uncertainty estimation and predictive performance on a range of prediction tasks.
  arXiv  Detail & Related papers  (2023-12-28T18:33:26Z)
• PICProp: Physics-Informed Confidence Propagation for Uncertainty Quantification [30.66285259412019]
  This paper introduces and studies confidence interval estimation for deterministic partial differential equations as a novel problem. That is, to propagate confidence, in the form of CIs, from data locations to the entire domain with probabilistic guarantees. We propose a method, termed Physics-Informed Confidence propagation (PICProp), based on bi-level optimization to compute a valid CI without making heavy assumptions.
  arXiv  Detail & Related papers  (2023-10-10T18:24:50Z)
• Dense Uncertainty Estimation [62.23555922631451]
  In this paper, we investigate neural networks and uncertainty estimation techniques to achieve both accurate deterministic prediction and reliable uncertainty estimation. We work on two types of uncertainty estimations solutions, namely ensemble based methods and generative model based methods, and explain their pros and cons while using them in fully/semi/weakly-supervised framework.
  arXiv  Detail & Related papers  (2021-10-13T01:23:48Z)
• Hessian-based toolbox for reliable and interpretable machine learning in physics [58.720142291102135]
  We present a toolbox for interpretability and reliability, extrapolation of the model architecture. It provides a notion of the influence of the input data on the prediction at a given test point, an estimation of the uncertainty of the model predictions, and an agnostic score for the model predictions. Our work opens the road to the systematic use of interpretability and reliability methods in ML applied to physics and, more generally, science.
  arXiv  Detail & Related papers  (2021-08-04T16:32:59Z)
• When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting [70.54920804222031]
  Most existing forecasting models disregard uncertainty quantification, resulting in mis-calibrated predictions. Recent works in deep neural models for uncertainty-aware time-series forecasting also have several limitations. We model the forecasting task as a probabilistic generative process and propose a functional neural process model called EPIFNP.
  arXiv  Detail & Related papers  (2021-06-07T18:31:47Z)
• Probabilistic electric load forecasting through Bayesian Mixture Density Networks [70.50488907591463]
  Probabilistic load forecasting (PLF) is a key component in the extended tool-chain required for efficient management of smart energy grids. We propose a novel PLF approach, framed on Bayesian Mixture Density Networks. To achieve reliable and computationally scalable estimators of the posterior distributions, both Mean Field variational inference and deep ensembles are integrated.
  arXiv  Detail & Related papers  (2020-12-23T16:21:34Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.