scholarly journals A Transfer Residual Neural Network Based on ResNet-34 for Detection of Wood Knot Defects

Forests ◽  
2021 ◽  
Vol 12 (2) ◽  
pp. 212
Author(s):  
Mingyu Gao ◽  
Dawei Qi ◽  
Hongbo Mu ◽  
Jianfeng Chen
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Detection Accuracy ◽  
Non Destructive Testing ◽  
Destructive Testing ◽  
Feature Extractor ◽  
Testing Technology ◽  
Excessive Consumption ◽  
Non Destructive ◽  
Deep Learning Model

In recent years, due to the shortage of timber resources, it has become necessary to reduce the excessive consumption of forest resources. Non-destructive testing technology can quickly find wood defects and effectively improve wood utilization. Deep learning has achieved significant results as one of the most commonly used methods in the detection of wood knots. However, compared with convolutional neural networks in other fields, the depth of deep learning models for the detection of wood knots is still very shallow. This is because the number of samples marked in the wood detection is too small, which limits the accuracy of the final prediction of the results. In this paper, ResNet-34 is combined with transfer learning, and a new TL-ResNet34 deep learning model with 35 convolution depths is proposed to detect wood knot defects. Among them, ResNet-34 is used as a feature extractor for wood knot defects. At the same time, a new method TL-ResNet34 is proposed, which combines ResNet-34 with transfer learning. After that, the wood knot defect dataset was applied to TL-ResNet34 for testing. The results show that the detection accuracy of the dataset trained by TL-ResNet34 is significantly higher than that of other methods. This shows that the final prediction accuracy of the detection of wood knot defects can be improved by TL-ResNet34.

scholarly journals Research on road engineering detection method based on GPR technology

2020 ◽  
Vol 165 ◽  
pp. 04014
Author(s):  
Liu Tao ◽  
Li Jia ◽  
Zheng Zhi-gang ◽  
Huang Zhi ◽  
Jiang Jian ◽  
...  
Keyword(s):  
Parameter Setting ◽  
Non Destructive Testing ◽  
Practical Application ◽  
Distribution Law ◽  
Destructive Testing ◽  
Road Engineering ◽  
The Road ◽  
Image Optimization ◽  
Testing Technology ◽  
Non Destructive

GPR is an effective non-destructive testing technology. This paper introduces its composition principle and operation method, explains the process of parameter setting and image optimization, obtains the dielectric constant of 10000 points, compares it with the density, and then obtains the uniformity distribution law of construction quality based on image. By calibrating the thickness of the road surface, the effective detection of road diseases can be realized, and the theoretical basis and practical application conditions of GPR technology can be clarified.

An Attempt at the Detection of a Flaw Using the Inverse Problem Solution of Impedance Imaging

1991 ◽  
Author(s):  
M. A. Hussain ◽  
M. McKee ◽  
J. Frankel
Keyword(s):  
Electrical Current ◽  
Problem Solution ◽  
Non Destructive Testing ◽  
Destructive Testing ◽  
Impedance Imaging ◽  
Testing Technology ◽  
Connected Body ◽  
Simply Connected ◽  
Non Destructive ◽  
Single Flaw

Abstract In this paper we present some preliminary numerical simulations which allow us to predict a single flaw in a simply connected body. The purpose of this investigation was to detect flaws and cracks of engineering components using the method of electrical current computed tomography (ECCT), which is used in non-destructive testing technology. As in the previous paper, we have utilized the network analogy to detect a single flaw anywhere in the object. For detection of multiple flaws, the analysis has to be refined to give consistent results.

scholarly journals Pattern Deep Region Learning for Crack Detection in Thermography Diagnosis System

Metals ◽  
2018 ◽  
Vol 8 (8) ◽  
pp. 612 ◽  
Author(s):  
Jue Hu ◽  
Weiping Xu ◽  
Bin Gao ◽  
Gui Tian ◽  
Yizhe Wang ◽  
...  
Keyword(s):  
Crack Detection ◽  
Pattern Mining ◽  
Learning Method ◽  
Non Destructive Testing ◽  
Destructive Testing ◽  
Pulsed Thermography ◽  
Testing Technology ◽  
Deep Region ◽  
Detection And Localization ◽  
Non Destructive

Eddy Current Pulsed Thermography is a crucial non-destructive testing technology which has a rapidly increasing range of applications for crack detection on metals. Although the unsupervised learning method has been widely adopted in thermal sequences processing, the research on supervised learning in crack detection remains unexplored. In this paper, we propose an end-to-end pattern, deep region learning structure to achieve precise crack detection and localization. The proposed structure integrates both time and spatial pattern mining for crack information with a deep region convolution neural network. Experiments on both artificial and natural cracks have shown attractive performance and verified the efficacy of the proposed structure.

Terahertz Non-destructive Testing Technology for Glass Fiber Honeycomb Composites

2019 ◽  
Vol 48 (2) ◽  
pp. 212002 ◽  
Author(s):  
张丹丹 ZHANG Dan-dan ◽  
任姣姣 REN Jiao-jiao ◽  
李丽娟 LI Li-juan ◽  
乔晓利 QIAO Xiao-li ◽  
顾健 GU Jian
Keyword(s):  
Glass Fiber ◽  
Non Destructive Testing ◽  
Destructive Testing ◽  
Testing Technology ◽  
Non Destructive

scholarly journals Infrared Non-Destructive Testing via Semi-Nonnegative Matrix Factorization

Proceedings ◽  
2019 ◽  
Vol 27 (1) ◽  
pp. 13 ◽  
Author(s):  
Yousefi ◽  
Ibarra-Castanedo ◽  
Maldague
Keyword(s):  
Matrix Factorization ◽  
Nonnegative Matrix ◽  
Principal Component ◽  
Computational Time ◽  
Detection Accuracy ◽  
Non Destructive Testing ◽  
Destructive Testing ◽  
Non Destructive ◽  
Non Negative Matrix Factorization ◽  
Subsurface Defects

Detection of subsurface defects is undeniably a growing subfield of infrared non-destructive testing (IR-NDT). There are many algorithms used for this purpose, where non-negative matrix factorization (NMF) is considered to be an interesting alternative to principal component analysis (PCA) by having no negative basis in matrix decomposition. Here, an application of Semi non-negative matrix factorization (Semi-NMF) in IR-NDT is presented to determine the subsurface defects of an Aluminum plate specimen through active thermographic method. To benchmark, the defect detection accuracy and computational load of the Semi-NMF approach is compared to state-of-the-art thermography processing approaches such as: principal component thermography (PCT), Candid Covariance-Free Incremental Principal Component Thermography (CCIPCT), Sparse PCT, Sparse NMF and standard NMF with gradient descend (GD) and non-negative least square (NNLS). The results show 86% accuracy for 27.5s computational time for SemiNMF, which conclusively indicate the promising performance of the approach in the field of IR-NDT.

scholarly journals Non-destructive testing technology for raw eggs freshness: a review

2020 ◽  
Vol 2 (6) ◽  
Author(s):  
Liang Qi ◽  
Mao-cheng Zhao ◽  
Zhong Li ◽  
De-hong Shen ◽  
Jun Lu
Keyword(s):  
Non Destructive Testing ◽  
Destructive Testing ◽  
Testing Technology ◽  
Non Destructive

Progress of laser-generated ultrasonic non-destructive testing technology

2011 ◽  
Author(s):  
Shi-tu Luo ◽  
Xiang-lin Tan ◽  
Meng-chun Pan ◽  
Cheng-guang Fan
Keyword(s):  
Non Destructive Testing ◽  
Destructive Testing ◽  
Testing Technology ◽  
Non Destructive

scholarly journals Wireless power transfer-based eddy current non-destructive testing using a flexible printed coil array

2020 ◽  
Vol 378 (2182) ◽  
pp. 20190579
Author(s):  
Lawal Umar Daura ◽  
GuiYun Tian ◽  
Qiuji Yi ◽  
Ali Sophian
Keyword(s):  
Deep Learning ◽  
Eddy Current ◽  
Feature Fusion ◽  
Non Destructive Testing ◽  
Wireless Power ◽  
Destructive Testing ◽  
Multiple Feature ◽  
Excitation Coil ◽  
Dual Resonance ◽  
Non Destructive

Eddy current testing (ECT) has been employed as a traditional non-destructive testing and evaluation (NDT&E) tool for many years. It has developed from single frequency to multiple frequencies, and eventually to pulsed and swept-frequency excitation. Recent progression of wireless power transfer (WPT) and flexible printed devices open opportunities to address challenges of defect detection and reconstruction under complex geometric situations. In this paper, a transmitter–receiver (Tx–Rx) flexible printed coil (FPC) array that uses the WPT approach featuring dual resonance responses for the first time has been proposed. The dual resonance responses can provide multiple parameters of samples, such as defect characteristics, lift-offs and material properties, while the flexible coil array allows area mapping of complex structures. To validate the proposed approach, experimental investigations of a single excitation coil with multiple receiving coils using the WPT principle were conducted on a curved pipe surface with a natural dent defect. The FPC array has one single excitation coil and 16 receiving (Rx) coils, which are used to measure the dent by using 21 C-scan points on the dedicated dent sample. The experimental data were then used for training and evaluation of dual resonance responses in terms of multiple feature extraction, selection and fusion for quantitative NDE. Four features, which include resonant magnitudes and principal components of the two resonant areas, were investigated for mapping and reconstructing the defective dent through correlation analysis for feature selection and feature fusion by deep learning. It shows that deep learning-based multiple feature fusion has outstanding performance for 3D defect reconstruction of WPT-based FPC-ECT. This article is part of the theme issue ‘Advanced electromagnetic non-destructive evaluation and smart monitoring’.

Sensibility Analysis of the Parameters Affecting Infrared Thermal Images for the Evaluation of Building Pathologies

2014 ◽  
Vol 353 ◽  
pp. 23-27
Author(s):  
E. Barreira ◽  
S.S. de Freitas ◽  
V.P. de Freitas ◽  
João M.P.Q. Delgado
Keyword(s):  
Infrared Thermography ◽  
Non Destructive Testing ◽  
Infrared Images ◽  
Destructive Testing ◽  
Testing Technology ◽  
Sensibility Analysis ◽  
Infrared Thermal Images ◽  
Building Physics ◽  
Non Destructive ◽  
Do So

Infrared thermography is a non destructive testing technology that has been applied to detect buildings pathologies for some decades. The thermograms are affected by several parameters and it is crucial to fully understand them in order to correctly interpret the temperature readings. The infrared radiation is affected by the radiation emitted by the surface and the radiation reflected and emitted by the surroundings. Therefore there are two kinds of parameters that affect the infrared images: parameters connected to the properties of the material itself and parameters connected with the environmental conditions. In this paper we present a sensibility study of the main parameters involved with infrared thermography evaluations to detect building pathologies. To do so, some simple experiments were carried out at the Building Physics Laboratory (LFC) of the Engineering Faculty of Porto University (FEUP). The sensibility study was performed with LFC’s equipment to evaluate how measurements are influenced by emissivity, reflections, absorptance and the meteorological conditions.

Sign in / Sign up

Export Citation Format

Share Document