cs.CENov 9, 2026

Physics-Informed Sinusoidal Representation Networks for Damage Identification in Ultrasonic Guided Wave Structural Health Monitoring

Authors: Lukas Jilke, Caspar Wasle, Norbert Hosters, Florian Raddatz, Marek Behr, Gerko Wende

Organizations: German Aerospace Center (DLR), Institute of Maintenance, Repair and Overhaul, Aachen-Würselen, Germany · German Aerospace Center (DLR), Institute of Maintenance, Repair and Overhaul, Hamburg, Germany · RWTH Aachen University, Chair for Computational Analysis of Technical Systems, Aachen, Germany

Abstract

Ultrasonic guided wave (UGW) inspection has become an effective method in structural health monitoring (SHM). While machine learning has enhanced damage detection capabilities, purely data-driven models remain constrained by extensive labeled datasets and limited physical interpretability. Standard multi-layer perceptrons (MLPs) further suffer from spectral bias (F-Principle) in high-frequency regimes, prioritizing low-frequency components while failing to resolve the high-frequency oscillations critical for UGW reconstruction. Physics-Informed Sinusoidal Representation Networks (PI-SIRENs) address these limitations by embedding governing partial differential equations directly into the training process. Building upon SIRENs, which utilize periodic activation functions to inherently capture high-frequency spectral content, the proposed framework is designed to operate effectively in sparse ultrasonic measurement regimes. This work introduces a frequency-domain PI-SIREN framework tailored for the Mindlin-Reissner plate theory to reconstruct ultrasonic wavefields without temporal discretization. The model parameters are optimized using a hybrid strategy comprising three phases: first-order Adam, residual-adaptive refinement (RAR) and quasi-Newton L-BFGS. Numerical and experimental evaluations confirm that the model serves as a physics-consistent baseline derived from sparse data, functioning as a computationally efficient surrogate for damage identification in SHM and non-destructive testing (NDT). Integrating the surrogate into a damage identification pipeline detects and localizes a milled notch from sparse experimental measurements with a localization error of 1 % of the plate diagonal. In contrast, data-driven benchmarks and MLPs with hyperbolic tangent activation functions, with and without Fourier feature embedding, are unable to identify damage due to higher reconstruction errors.

Figures & tables

Explore similar work

CardsList
  1. A Multi-Fidelity Convolutional Autoencoder-Transfer Learning Framework for Guided-Wave-Based Damage Diagnosis Using Large Simulated and Limited Experimental Datasets

    Jun 25, 2026Santosh Kapuria, AbhishekConvolutional AutoencoderTransfer Learning

  2. WaveGraphNet: Physics-Consistent Guided-Wave Damage Localization through Coupled Inverse-Forward Graph Learning

    May 19, 2026Vinay Sharma, Aditya Bharade, Olga FinkGraph Neural NetworksInverse Problems

  3. Neural Surrogate Modeling of Ultrasonic Wave Propagation in Heterogeneous Media

    Oct 9, 2026Burla Nur Korkmaz, Petro Moilanen, Ari Salmi +2Neural Surrogate ModelingPDE Surrogate Modeling