Videos de Conceptos Relacionados
01:17Convolution Properties II
583
The important convolution properties include width, area, differentiation, and integration properties.
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...
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...
583
01:21Fatigue
831
Fatigue occurs when materials rupture under repeated or fluctuating loads, even at stress levels far below their static breaking strength. It typically results in brittle failure, even for ductile materials. It is a critical consideration in designing machines and structural components subjected to repetitive or varying loads. The nature of these loadings can range from fluctuating loads like unbalanced pump impellers causing vibrations to repeatedly bending a thin steel rod wire back and forth...
831
02:39Emission Spectra
76.2K
When solids, liquids, or condensed gases are heated sufficiently, they radiate some of the excess energy as light. Photons produced in this manner have a range of energies, and thereby produce a continuous spectrum in which an unbroken series of wavelengths is present.
76.2K
01:20Convolution Properties I
584
Convolution computations can be simplified by utilizing their inherent properties.
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:
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:
584
02:26Protein Networks
4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
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,...
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,...
4.5K
01:28Types of Non-structural Cracks in Concrete
498
Non-structural cracks are primarily of three types: plastic, early-age thermal, and drying shrinkage cracks. Plastic cracks are further classified into plastic shrinkage cracks and plastic settlement cracks.
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.
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.
498
También podría leer
Artículos Relacionados
Artículos vinculados a este trabajo por autores compartidos, revista y gráfico de citas.
Ordenar por
Same author
New Method of Impact Localization on Plate-like Structures Using Deep Learning and Wavelet Transform.
Sensors (Basel, Switzerland)·2025
Same author
Exploring Piezoelectric Actuation towards Its Applications in Laser Powder Bed Fusion Additive Manufacturing.
Sensors (Basel, Switzerland)·2024
Same author
Piezoelectric Transducer-Based Structural Health Monitoring.
Sensors (Basel, Switzerland)·2024
Video Experimental Relacionado
Updated: Jan 29, 2026
07:37
Full-field Strain Measurements for Microstructurally Small Fatigue Crack Propagation Using Digital Image Correlation Method
Published on: January 16, 2019
10.1K
Estimación de la longitud de grietas de fatiga utilizando redes neuronales convolucionales basadas en la técnica de
Asaad Migot1,2, Ahmed Saaudi3,2, Roshan Joseph4
1Department of Petroleum and Gas Engineering, College of Engineering, University of Thi-Qar, Nasiriyah 64001, Iraq.
Sensors (Basel, Switzerland)
|January 28, 2026
Resumen
Este estudio utiliza aprendizaje profundo y señales de emisión acústica (AE) para estimar la longitud de grietas de fatiga en placas metálicas. El aprendizaje por transferencia con redes neuronales convolucionales (CNN) logró una precisión del 99 %, mejorando la monitorización de la salud estructural.
Área de la Ciencia:
- Ciencia de Materiales
- Ingeniería Mecánica
- Inteligencia Artificial
Sus antecedentes:
- La propagación de grietas por fatiga es un mecanismo de falla crítico en las estructuras de ingeniería.
- La monitorización eficaz es esencial para el mantenimiento oportuno y la prevención de fallos catastróficos.
- Las señales de emisión acústica (AE) ofrecen un método no destructivo prometedor para detectar y analizar el crecimiento de grietas.
Objetivo del estudio:
- Desarrollar un marco de aprendizaje profundo para estimar la longitud de fractura por fatiga en placas metálicas utilizando señales de AE.
- Investigar la efectividad de las redes neuronales convolucionales (CNN) y el aprendizaje por transferencia para analizar datos de AE.
- Mejorar las capacidades de monitorización de la salud estructural a través de enfoques basados en datos.
Principales métodos:
- Las formas de onda de AE se transformaron en imágenes tiempo-frecuencia utilizando la distribución de Choi-Williams.
- Se utilizó un modelo basado en CNN para la extracción de características y la agrupación K-means para categorizar las longitudes de fractura.
- Se compararon modelos de aprendizaje por transferencia (ResNet50V2, VGG16) con una CNN personalizada para la clasificación de la longitud de fractura.
Principales resultados:
- El conjunto de datos de AE se agrupó con éxito, visualizando la proximidad de los puntos de datos utilizando PCA.
- Los modelos CNN clasificaron con precisión las longitudes de fractura en tres rangos distintos.
- Los modelos de aprendizaje por transferencia lograron una precisión significativamente mayor (aproximadamente 99 %) en comparación con la CNN personalizada (aproximadamente 93 %).
Conclusiones:
- El aprendizaje profundo, especialmente con aprendizaje por transferencia, es muy eficaz para analizar datos de AE.
- Las CNN demuestran sólidas capacidades para comprender las señales de AE para la monitorización de grietas de fatiga.
- El marco propuesto avanza la monitorización de la salud estructural basada en datos para componentes metálicos.