Impact-damage reconstruction from elastic-wave measurements using multitask deep learning

Abstract Impact-induced subsurface damage is challenging to characterize because transient wave measurements contain spatially distributed and strongly coupled information associated with damage location, extent, and intensity. This study presents a physics-based wave–deep-learning framework for simultaneous three-dimensional reconstruction and quantitative characterization of impact damage. Random surface impacts with varying impactor properties and contact locations were applied to a homogeneous solid. Rather than prescribing artificial damage geometries, a Hertzian-contact-based surrogate was used to map the impact conditions to continuous subsurface damage fields. Transient elastic-wave responses were then simulated using distributed excitation and sensing, and differential signals between the damaged and intact states were used as inputs to the inverse model. A multitask convolutional neural network was developed with a receiver–time feature encoder, a volumetric damage decoder, and separate regression branches for damage volume and severity. To address the strong spatial sparsity of subsurface damage, the decoder explicitly separated damage occupancy from continuous damage intensity. The proposed framework successfully reconstructed damage location, spatial extent, morphology, and intensity distribution while simultaneously estimating damage volume and severity. Systematic studies of training-data size, model components, damage characteristics, impact surface, measurement noise, receiver loss, wave-speed mismatch, and damage-identification threshold further demonstrated the robustness and sensitivity characteristics of the learned inverse mapping. The results demonstrate the potential of combining physically conditioned data generation, transient elastic-wave measurements, and multitask deep learning for volumetric nondestructive characterization of subsurface impact damage. Additional frozen-model tests with alternative numerical damage surrogates revealed nonuniform out-of-distribution performance, emphasizing the importance of model-form uncertainty and independent physical validation. Independent baseline comparisons showed competitive spatial and damage-volume accuracy relative to alternative convolutional architectures, with some task-dependent trade-offs in severity and localization.

Authors

Institutions

Publication Details

Journal
Smart Materials and Structures
Published
2026-11-16
DOI
https://doi.org/10.1088/1361-665x/aec297
Primary Topic
Ultrasonics and Acoustic Wave Propagation
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Impact-damage reconstruction from elastic-wave measurements using multitask deep learning

Sheng Sang, Ziping Wang, Jiadi Fan, Braden Greenberger
2 links
Smart Materials and Structures
Ultrasonics and Acoustic Wave Propagation
article

Impact-damage reconstruction from elastic-wave measurements using multitask deep learning

Sheng Sang, Ziping Wang, Jiadi Fan, Braden Greenberger
article en

Abstract

Abstract Impact-induced subsurface damage is challenging to characterize because transient wave measurements contain spatially distributed and strongly coupled information associated with damage location, extent, and intensity. This study presents a physics-based wave–deep-learning framework for simultaneous three-dimensional reconstruction and quantitative characterization of impact damage. Random surface impacts with varying impactor properties and contact locations were applied to a homogeneous solid. Rather than prescribing artificial damage geometries, a Hertzian-contact-based surrogate was used to map the impact conditions to continuous subsurface damage fields. Transient elastic-wave responses were then simulated using distributed excitation and sensing, and differential signals between the damaged and intact states were used as inputs to the inverse model. A multitask convolutional neural network was developed with a receiver–time feature encoder, a volumetric damage decoder, and separate regression branches for damage volume and severity. To address the strong spatial sparsity of subsurface damage, the decoder explicitly separated damage occupancy from continuous damage intensity. The proposed framework successfully reconstructed damage location, spatial extent, morphology, and intensity distribution while simultaneously estimating damage volume and severity. Systematic studies of training-data size, model components, damage characteristics, impact surface, measurement noise, receiver loss, wave-speed mismatch, and damage-identification threshold further demonstrated the robustness and sensitivity characteristics of the learned inverse mapping. The results demonstrate the potential of combining physically conditioned data generation, transient elastic-wave measurements, and multitask deep learning for volumetric nondestructive characterization of subsurface impact damage. Additional frozen-model tests with alternative numerical damage surrogates revealed nonuniform out-of-distribution performance, emphasizing the importance of model-form uncertainty and independent physical validation. Independent baseline comparisons showed competitive spatial and damage-volume accuracy relative to alternative convolutional architectures, with some task-dependent trade-offs in severity and localization.

Smart Materials and Structures
Jiangsu University (CN), University of Minnesota (US), North Carolina Agricultural and Technical State University (US)
North Carolina Agricultural and Technical State University
Ultrasonics and Acoustic Wave Propagation
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon