Physics-Informed Machine Learning for Transformer Condition Monitoring -- Part II: Physics-Informed Neural Networks and Uncertainty Quantification

• URL: http://arxiv.org/abs/2512.22189v1
• Date: Sat, 20 Dec 2025 10:09:21 GMT
• Title: Physics-Informed Machine Learning for Transformer Condition Monitoring -- Part II: Physics-Informed Neural Networks and Uncertainty Quantification
• Authors: Jose I. Aizpurua,
• Abstract summary: integration of physics-based knowledge with machine learning models is increasingly shaping monitoring, diagnostics, and prognostics of electrical transformers.<n>This paper introduces the foundations of Neural Networks (NNs) and their variants for health assessment tasks.<n>We present PINs as a principled framework to quantify uncertainty and deliver robust predictions under sparse data.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The integration of physics-based knowledge with machine learning models is increasingly shaping the monitoring, diagnostics, and prognostics of electrical transformers. In this two-part series, the first paper introduced the foundations of Neural Networks (NNs) and their variants for health assessment tasks. This second paper focuses on integrating physics and uncertainty into the learning process. We begin with the fundamentals of Physics-Informed Neural Networks (PINNs), applied to spatiotemporal thermal modeling and solid insulation ageing. Building on this, we present Bayesian PINNs as a principled framework to quantify epistemic uncertainty and deliver robust predictions under sparse data. Finally, we outline emerging research directions that highlight the potential of physics-aware and trustworthy machine learning for critical power assets.

Related papers

• Adapting Vision-Language Models for Neutrino Event Classification in High-Energy Physics [41.33501105382656]
  This work explores the applications of Vision Language Models (VLMs) to the task of identifying neutrino interactions in pixelated detector data from high-energy physics experiments.<n>We benchmark this model against a state-of-the-art convolutional neural network (CNN) architecture, similar to those used in the NOvA and DUNE experiments.<n>We find that VLMs can outperform CNNs, while also providing greater flexibility in integrating auxiliary textual or semantic information and offering more interpretable, reasoning-based predictions.
  arXiv  Detail & Related papers  (2025-09-10T10:07:27Z)
• Physics-informed machine learning: A mathematical framework with applications to time series forecasting [0.0]
  We study the properties of physics-informed neural networks (PINNs) in terms of approximation, consistency, overfitting, and convergence.<n>The second part explores industrial applications in forecasting energy signals during atypical periods.<n>We introduce a physics-constrained framework for designing and enforcing constraints in time series.
  arXiv  Detail & Related papers  (2025-07-11T11:47:09Z)
• Mechanical in-sensor computing: a programmable meta-sensor for structural damage classification without external electronic power [41.70275766820096]
  We introduce a programmable metamaterial-based sensor (termed as MM-sensor) for physically processing structural vibration information.<n>We take advantage of the bandgap properties of LRMP to physically differentiate the dynamic behavior of structures before and after damage.<n>This is effective for engineering systems with a first natural frequency ranging from 9.54 Hz to 81.86 Hz.
  arXiv  Detail & Related papers  (2025-05-24T08:08:02Z)
• Advancing Physics Data Analysis through Machine Learning and Physics-Informed Neural Networks [0.0]
  This project evaluates various machine learning (ML) algorithms for physics data analysis.<n>We apply these techniques to a binary classification task that distinguishes the experimental viability of simulated scenarios.<n>XGBoost emerged as the preferred choice among the evaluated machine learning algorithms for its speed and effectiveness.
  arXiv  Detail & Related papers  (2024-10-18T11:05:52Z)
• Physics-Informed Neural Networks with Hard Linear Equality Constraints [9.101849365688905]
  This work proposes a novel physics-informed neural network, KKT-hPINN, which rigorously guarantees hard linear equality constraints. Experiments on Aspen models of a stirred-tank reactor unit, an extractive distillation subsystem, and a chemical plant demonstrate that this model can further enhance the prediction accuracy.
  arXiv  Detail & Related papers  (2024-02-11T17:40:26Z)
• Privacy-preserving machine learning with tensor networks [37.01494003138908]
  We show that tensor network architectures have especially prospective properties for privacy-preserving machine learning. First, we describe a new privacy vulnerability that is present in feedforward neural networks, illustrating it in synthetic and real-world datasets. We rigorously prove that such conditions are satisfied by tensor-network architectures.
  arXiv  Detail & Related papers  (2022-02-24T19:04:35Z)
• Physics-informed ConvNet: Learning Physical Field from a Shallow Neural Network [0.180476943513092]
  Modelling and forecasting multi-physical systems remain a challenge due to unavoidable data scarcity and noise. New framework named physics-informed convolutional network (PICN) is recommended from a CNN perspective. PICN may become an alternative neural network solver in physics-informed machine learning.
  arXiv  Detail & Related papers  (2022-01-26T14:35:58Z)
• Physically Explainable CNN for SAR Image Classification [59.63879146724284]
  In this paper, we propose a novel physics guided and injected neural network for SAR image classification. The proposed framework comprises three parts: (1) generating physics guided signals using existing explainable models, (2) learning physics-aware features with physics guided network, and (3) injecting the physics-aware features adaptively to the conventional classification deep learning model for prediction. The experimental results show that our proposed method substantially improve the classification performance compared with the counterpart data-driven CNN.
  arXiv  Detail & Related papers  (2021-10-27T03:30:18Z)
• Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling [86.9726984929758]
  We focus on the integration of incomplete physics models into deep generative models. We propose a VAE architecture in which a part of the latent space is grounded by physics. We demonstrate generative performance improvements over a set of synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2021-02-25T20:28:52Z)
• Thermodynamics-based Artificial Neural Networks for constitutive modeling [0.0]
  We propose a new class of data-driven, physics-based, neural networks for modeling of strain rate independent processes at the material point level. The two basic principles of thermodynamics are encoded in the network's architecture by taking advantage of automatic differentiation. We demonstrate the wide applicability of TANNs for modeling elasto-plastic materials, with strain hardening and softening strain.
  arXiv  Detail & Related papers  (2020-05-25T15:56:34Z)
• Parsimonious neural networks learn interpretable physical laws [77.34726150561087]
  We propose parsimonious neural networks (PNNs) that combine neural networks with evolutionary optimization to find models that balance accuracy with parsimony. The power and versatility of the approach is demonstrated by developing models for classical mechanics and to predict the melting temperature of materials from fundamental properties.
  arXiv  Detail & Related papers  (2020-05-08T16:15:47Z)
• Learning to Simulate Complex Physics with Graph Networks [68.43901833812448]
  We present a machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains. Our framework---which we term "Graph Network-based Simulators" (GNS)--represents the state of a physical system with particles, expressed as nodes in a graph, and computes dynamics via learned message-passing. Our results show that our model can generalize from single-timestep predictions with thousands of particles during training, to different initial conditions, thousands of timesteps, and at least an order of magnitude more particles at test time.
  arXiv  Detail & Related papers  (2020-02-21T16:44:28Z)

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.