Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 13, 2026

Optimized Sealing Process and Real-Time Monitoring of Glass-to-Metal Seal Structures
04:41

Optimized Sealing Process and Real-Time Monitoring of Glass-to-Metal Seal Structures

Published on: September 2, 2019

Benchmarking Multilayer Perceptron Configurations for Damage Classification in UAV Composite Wings Using Fiber Bragg

David O Briceño González1, Julian Sierra-Perez2, Maribel Anaya Vejar1

  • 1Departamento de Ingeniería Eléctrica y Electrónica, Universidad Nacional de Colombia, Bogotá 111321, Colombia.

Sensors (Basel, Switzerland)
|June 12, 2026
PubMed
Summary

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

Detection of Microplastics and Heavy Metals Using Electronic Tongues and Machine Learning.

Sensors (Basel, Switzerland)·2026
Same author

Electronic Tongues and Noses: A General Overview.

Biosensors·2024
Same author

New Electronic Tongue Sensor Array System for Accurate Liquor Beverage Classification.

Sensors (Basel, Switzerland)·2023
Same author

Performance Analysis and Architecture of a Clustering Hybrid Algorithm Called FA+GA-DBSCAN Using Artificial Datasets.

Entropy (Basel, Switzerland)·2022
Same author

Toward a Structural Health Monitoring Methodology for Concrete Structures under Dynamic Loads Using Embedded FBG Sensors and Strain Mapping Techniques.

Sensors (Basel, Switzerland)·2022
Same author

Attention-Based Deep Recurrent Neural Network to Forecast the Temperature Behavior of an Electric Arc Furnace Side-Wall.

Sensors (Basel, Switzerland)·2022

This study benchmarks lightweight neural networks for composite UAV wing damage classification using Fiber Bragg Grating (FBG) sensors. Compact Multilayer Perceptron models offer a balance of performance and efficiency for Structural Health Monitoring (SHM).

Area of Science:

  • Aerospace Engineering
  • Materials Science
  • Computational Mechanics

Background:

  • Structural Health Monitoring (SHM) of composite unmanned aerial vehicle (UAV) wings is critical.
  • Barely visible impact damage presents a significant challenge for SHM systems.
  • Fiber Bragg Grating (FBG) sensors offer high-resolution strain data but require robust analysis methods.

Purpose of the Study:

  • To systematically benchmark lightweight neural network architectures for damage classification in composite UAV wings.
  • To evaluate the performance of Multilayer Perceptron (MLP) configurations using real FBG sensor data.
  • To assess the robustness of these models under various sensor degradation scenarios.

Main Methods:

  • A four-phase experimental study using a composite UAV wing instrumented with 32 FBG sensors.
Keywords:
Fiber Bragg Grating (FBG) sensorsUAV composite wingsbenchmarkingdamage classificationmultilayer perceptron (MLP)structural health monitoring (SHM)

More Related Videos

Design, Instrumentation and Usage Protocols for Distributed In Situ Thermal Hot Spots Monitoring in Electric Coils using FBG Sensor Multiplexing
10:52

Design, Instrumentation and Usage Protocols for Distributed In Situ Thermal Hot Spots Monitoring in Electric Coils using FBG Sensor Multiplexing

Published on: March 8, 2020

A Random-displacement Measurement by Combining a Magnetic Scale and Two Fiber Bragg Gratings
08:23

A Random-displacement Measurement by Combining a Magnetic Scale and Two Fiber Bragg Gratings

Published on: September 30, 2019

Related Experiment Videos

Last Updated: Jun 13, 2026

Optimized Sealing Process and Real-Time Monitoring of Glass-to-Metal Seal Structures
04:41

Optimized Sealing Process and Real-Time Monitoring of Glass-to-Metal Seal Structures

Published on: September 2, 2019

Design, Instrumentation and Usage Protocols for Distributed In Situ Thermal Hot Spots Monitoring in Electric Coils using FBG Sensor Multiplexing
10:52

Design, Instrumentation and Usage Protocols for Distributed In Situ Thermal Hot Spots Monitoring in Electric Coils using FBG Sensor Multiplexing

Published on: March 8, 2020

A Random-displacement Measurement by Combining a Magnetic Scale and Two Fiber Bragg Gratings
08:23

A Random-displacement Measurement by Combining a Magnetic Scale and Two Fiber Bragg Gratings

Published on: September 30, 2019

  • Training and validation of MLP models across five damage states and 210 loading experiments.
  • Analysis of optimization strategies, hyperparameter sensitivity, architectural depth, and robustness to sensor dropout, noise, and wavelength drift.

    • Main Results:

    • Compact MLP architectures (256-128-64) with adaptive optimizers (AdamW, Nadam) achieved the best performance (macro-F1 up to 0.85).
    • These models demonstrated a favorable balance between performance, stability, and computational efficiency.
    • Performance degraded gradually with sensor loss, indicating potential for distributed strain-field learning.

    Conclusions:

    • Lightweight, compact MLP models are suitable for FBG-based SHM in aerospace.
    • Adaptive optimizers enhance model performance and stability.
    • Findings provide practical guidelines for deploying efficient and robust SHM systems.