Automatic defect depth estimation for ultrasonic testing in carbon fiber reinforced composites using deep learning

Cheng, Xiaoying; Ma, Gaoshen; Wu, Zhenyu; Zu, Hongfei; Hu, Xudong

doi:10.1016/j.ndteint.2023.102804

Cited by 27 publications

(6 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Signal extraction Deep learning methods have gained significant attention with the increasing volume of data and the growing complexity of ultrasonic signals. Common deep learning networks include convolutional neural networks (CNN) [104], graph neural networks (GNNs) [98], recurrent neural networks (RNN) [105], long short-term memory (LSTM) [106], and Au-toEncoder [107]. It is evident that data-driven techniques dominated by machine learning (ML) methods have demonstrated significant advantages in ultrasonic in-line inspection compared to physical models [108].…”

Section: Potential Challenges and Opportunitiesmentioning

confidence: 99%

Systematic Evaluation of Ultrasonic In-Line Inspection Techniques for Oil and Gas Pipeline Defects Based on Bibliometric Analysis

Huang,

Chen,

et al. 2024

Sensors

View full text Add to dashboard Cite

The global reliance on oil and gas pipelines for energy transportation is increasing. As the pioneering review in the field of ultrasonic defect detection for oil and gas pipelines based on bibliometric methods, this study employs visual analysis to identify the most influential countries, academic institutions, and journals in this domain. Through cluster analysis, it determines the primary trends, research hotspots, and future directions in this critical field. Starting from the current global industrial ultrasonic in-line inspection (ILI) detection level, this paper provides a flowchart for selecting detection methods and a table for defect comparison, detailing the comparative performance limits of different detection devices. It offers a comprehensive perspective on the latest ultrasonic pipeline detection technology from laboratory experiments to industrial practice.

show abstract

Section: Potential Challenges and Opportunitiesmentioning

confidence: 99%

Systematic Evaluation of Ultrasonic In-Line Inspection Techniques for Oil and Gas Pipeline Defects Based on Bibliometric Analysis

Huang,

Chen,

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…[19] Instead of the typical TSR algorithm, further operations have been done with the implementation of the data clusters. This machine learning based approach is recently explored to make fully automatic damage evaluation systems [20][21][22][23]. There is a wide variety of data clustering methods presented by Jane et al [24] In general, clustering can be divided into two categories -hierarchical and partitional.…”

Section: Thermal Signal Reconstruction -Signal Processing Proceduresmentioning

confidence: 99%

Laser spot thermography and Pulse thermography – comparison of performance for non-destructive testing of composite structures

2023

IJM

View full text Add to dashboard Cite

Laser spot thermography (LST) is a sub-domain method in active thermography that uses a laser as the heat source. The method allows for precise control of the beam shape, pulse duration, and delivered energy. Therefore, this technique can be applied, especially for delicate structures where testing conditions must be maintained precisely. The following work includes the introduction of a laser spot thermography technology demonstrator that was designed and constructed at AGH UST. The paper presents laser thermography laboratory experiments along with the developed procedure for automatic defect identification. The measurements were used to establish an automatic procedure and algorithm for automatic defect identification based on regression methods.

show abstract

“…Unidirectional (UD) CFRP composite laminates with three types of damage were made, and the acoustic emission signals during the three-point bending test were used as the input for training. Cheng et al [25] employed deep learning methods for the estimation of the depth of damage in CFRP samples. The dataset was made up of ultrasonic A-scan signals of artificial defects, and the accuracy was checked using samples with low-velocity impact damage.…”

Section: Introductionmentioning

confidence: 99%

Machine learning-enabled thickness estimation of thin coatings on carbon fibre composites using microwaves

Li,

Meng,

Liu

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Accurate thickness measurement of thin coatings (typically 50-500 μm) on carbon fibre-reinforced polymer composites is a major challenge in the manufacturing and maintenance processes of modern aircraft. Different from the conventional material-dependent technique for prediction, a machine learning-enabled strategy with an artificial neural network configuration is used with no requirement of prior knowledge of the type of coating or substrate under test. In the test, an open microwave cavity resonator sensor is directly placed on a coated composite, and any variation of the coating material, coating thickness and conductivity of the composite alters the resonance frequency. Principal component analysis is employed in the signal pre-processing for the dimensionality reduction of the raw measurement data. In terms of the root-mean-square error, the maximum value for the calibration approach is approximately 15 μm and that for the machine learning-based approach is 12 μm. The sensor system developed enables real-time on-site assessment of coated composite structures and thus offers a new approach for non-destructive evaluation 4.0 with improved efficiency, accuracy and automation.

show abstract

Automatic defect depth estimation for ultrasonic testing in carbon fiber reinforced composites using deep learning

Cited by 27 publications

References 27 publications

Systematic Evaluation of Ultrasonic In-Line Inspection Techniques for Oil and Gas Pipeline Defects Based on Bibliometric Analysis

Systematic Evaluation of Ultrasonic In-Line Inspection Techniques for Oil and Gas Pipeline Defects Based on Bibliometric Analysis

Laser spot thermography and Pulse thermography – comparison of performance for non-destructive testing of composite structures

Machine learning-enabled thickness estimation of thin coatings on carbon fibre composites using microwaves

Contact Info

Product

Resources

About