Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Non-canonical ATR signaling mediates direct and bystander cold atmospheric plasma-induced stress responses in A549 lung adenocarcinoma cells.

Scientific reports·2026

Same author

Cascade Reaction of α, β-Unsaturated Keto-carboxylic Acid for the Formation of 5-Substituted Isoxazole using NaN<sub>3</sub>/I<sub>2</sub>/TBHP.

Organic letters·2026

Same author

Parametrically upscaled model-based predictive platform for fatigue with location-specific microstructural linkages.

Nature communications·2026

Same author

Eye Movements and Visual Perception in Children With Autism Spectrum Disorder.

Journal of pediatric ophthalmology and strabismus·2026

Same author

Safety and Effectiveness of Routine Tenecteplase Use in a Large Telestroke Network.

The neurologist·2026

Same author

Recent Advances in Bioactive Flavonoids-based Nanotherapeutics as Promising Neuroprotectants in Epilepsy.

Current aging science·2026

Search research articles

Related Experiment Video

Updated: May 26, 2025

Strain Sensing Based on Multiscale Composite Materials Reinforced with Graphene Nanoplatelets

Strain Sensing Based on Multiscale Composite Materials Reinforced with Graphene Nanoplatelets

Published on: November 7, 2016

Machine learning-enabled multiscale modeling platform for damage sensing digital twin in piezoelectric composite

Somnath Ghosh¹, Saikat Dan², Preetam Tarafder²

¹Civil & Systems Engineering, Johns Hopkins University, Baltimore, MD, 21218, USA. sghosh20@jhu.edu.

Scientific Reports

|February 24, 2025

Summary

This study introduces a novel digital twin (DT) for real-time damage detection in piezoelectric composites. The advanced DT integrates microscale details and machine learning to predict structural damage using electrical signals.

Keywords:

ConvLSTM Electromechanical-damage coupling Multiscale PUCCDM model Piezoelectric composite Representative aggregated microstructural parameters (RAMPs)

More Related Videos

Data Acquisition Protocol for Determining Embedded Sensitivity Functions

Data Acquisition Protocol for Determining Embedded Sensitivity Functions

Published on: April 20, 2016

A Polymer-based Piezoelectric Vibration Energy Harvester with a 3D Meshed-Core Structure

A Polymer-based Piezoelectric Vibration Energy Harvester with a 3D Meshed-Core Structure

Published on: February 20, 2019

Related Experiment Videos

Last Updated: May 26, 2025

Strain Sensing Based on Multiscale Composite Materials Reinforced with Graphene Nanoplatelets

Strain Sensing Based on Multiscale Composite Materials Reinforced with Graphene Nanoplatelets

Published on: November 7, 2016

Data Acquisition Protocol for Determining Embedded Sensitivity Functions

Data Acquisition Protocol for Determining Embedded Sensitivity Functions

Published on: April 20, 2016

A Polymer-based Piezoelectric Vibration Energy Harvester with a 3D Meshed-Core Structure

A Polymer-based Piezoelectric Vibration Energy Harvester with a 3D Meshed-Core Structure

Published on: February 20, 2019

Area of Science:

Materials Science and Engineering
Mechanical Engineering
Aerospace Engineering

Background:

Nondestructive evaluation (NDE) is vital for aerospace structures but often lacks real-time damage prediction.
Existing NDE methods are typically post-mortem, failing to capture evolving damage in situ.
Piezoelectric composite structures require advanced monitoring due to harsh operating conditions.

Purpose of the Study:

To develop a damage-sensing digital twin (DT) for piezoelectric composite structures.
To enable real-time, in-situ prediction of structural damage progression.
To integrate microscale morphology and mechanisms into structural damage assessment.

Main Methods:

A two-step computational process combining multiscale-multiphysics modeling and machine learning (ML).
Development of a parametrically upscaled coupled constitutive damage mechanics (PUCCDM) model.
Utilizing artificial neural networks (ANN) and convolutional long-short-term memory (ConvLSTM) networks for damage prediction from electrical signals.

Main Results:

The DT successfully integrated microstructural details into macroscopic constitutive relations via the PUCCDM model.
ANN derived PUCCDM coefficients based on microstructural parameters (RAMPs).
ConvLSTM learned correlations between electrical signals, damage fields, and microstructural features, enabling accurate damage prediction.

Conclusions:

The proposed damage-sensing digital twin provides real-time, in-situ predictive capabilities for evolving damage in piezoelectric composites.
The framework effectively predicts location-specific damage using limited surface electrical signal measurements.
This approach enhances the operational safety and maintenance of aerospace structures.