Related Concept Videos
Convolution Properties II
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
Fatigue
Emission Spectra
Convolution Properties I
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
Protein Networks
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
Types of Non-structural Cracks in Concrete
Plastic shrinkage cracks typically form within hours after the concrete is poured. The concrete's surface dries faster than the bottom, creating tensile stress that the still-plastic concrete cannot withstand, leading to diagonal or randomly patterned cracks on the concrete surface.
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
New Method of Impact Localization on Plate-like Structures Using Deep Learning and Wavelet Transform.
Exploring Piezoelectric Actuation towards Its Applications in Laser Powder Bed Fusion Additive Manufacturing.
Piezoelectric Transducer-Based Structural Health Monitoring.
Related Experiment Video
Updated: Jan 29, 2026

Full-field Strain Measurements for Microstructurally Small Fatigue Crack Propagation Using Digital Image Correlation Method
Published on: January 16, 2019
Fatigue Crack Length Estimation Using Acoustic Emissions Technique-Based Convolutional Neural Networks.
Asaad Migot1,2, Ahmed Saaudi3,2, Roshan Joseph4
1Department of Petroleum and Gas Engineering, College of Engineering, University of Thi-Qar, Nasiriyah 64001, Iraq.
This study uses deep learning and acoustic emission (AE) signals to estimate fatigue crack length in metal plates. Transfer learning with convolutional neural networks (CNNs) achieved 99% accuracy, enhancing structural health monitoring.
Area of Science:
- Materials Science
- Mechanical Engineering
- Artificial Intelligence
Background:
- Fatigue crack propagation is a critical failure mechanism in engineering structures.
- Effective monitoring is essential for timely maintenance and preventing catastrophic failures.
- Acoustic emission (AE) signals offer a promising non-destructive method for detecting and analyzing crack growth.
Purpose of the Study:
- To develop a deep learning framework for estimating fatigue fracture length in metallic plates using AE signals.
- To investigate the effectiveness of convolutional neural networks (CNNs) and transfer learning for analyzing AE data.
- To enhance structural health monitoring capabilities through data-driven approaches.
Main Methods:
- AE waveforms were transformed into time-frequency images using the Choi-Williams distribution.
- A CNN-based model was used for feature extraction, and K-means clustering categorized fatigue lengths.
- Transfer learning models (ResNet50V2, VGG16) were compared against a custom CNN for fracture length classification.
Main Results:
- The AE dataset was successfully clustered, visualizing data point proximity using PCA.
- CNN models accurately categorized fracture lengths into three distinct ranges.
- Transfer learning models achieved significantly higher accuracy (approx. 99%) compared to the custom CNN (approx. 93%).
Conclusions:
- Deep learning, especially with transfer learning, is highly effective for analyzing AE data.
- CNNs demonstrate strong capabilities in understanding AE signals for fatigue crack monitoring.
- The proposed framework advances data-driven structural health monitoring for metallic components.

