Crack Evaluation Based on Novel Circle-Ferrite Induction Thermography

Zhao, Jian; Gao, Bin; Woo, Wai Lok; Qiu, Fasheng; Tian, Gui Yun

doi:10.1109/jsen.2017.2723432

Cited by 18 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The visual results are presented along with the quantitative results based on running times and SNR [39]. To show the efficacy of the proposed algorithm the comparative analysis is presented with general IT detection algorithms and other tensor decomposition based algorithms.…”

Section: Experiments Analysismentioning

confidence: 99%

“…A variety of metallic specimen are selected such as pipeline and axle with irregular shape having artificial as well as natural defect profiles to validate its robustness and efficiency. Along with the visual results, the event-based signal-tonoise ratio (SNR) [39] and precision and recall based F-score [30] is also used for the quantitative analysis. To show the efficacy of the proposed model a comparison is also presented with recent and stateof-the-art tensor decomposition algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sparse Low-Rank Tensor Decomposition for Metal Defect Detection Using Thermographic Imaging Diagnostics

Ahmed

Gao

Woo

2021

IEEE Trans. Ind. Inf.

Self Cite

View full text Add to dashboard Cite

Section: Experiments Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Sparse Low-Rank Tensor Decomposition for Metal Defect Detection Using Thermographic Imaging Diagnostics

Ahmed

Gao

Woo

2021

IEEE Trans. Ind. Inf.

Self Cite

View full text Add to dashboard Cite

“…When the velocity of the two different carriers (electrons and holes) varies greatly, the resistivity of metal or semiconductor materials is mainly caused by the carrier with larger speed. Expression: B is the magnetic induction intensity, ρ is the resistivity of metal or semiconductor materials when the applied magnetic induction intensity is B, so ρ 0 is the resistivity of metal or semiconductor materials when the applied magnetic induction intensity is zero, ν is the velocity of the carrier of a conductive material in the magnetic field [8]. It can be seen from the first formula that when the magnetic induction intensity B is constant, the larger the carrier speed is, the more obvious the magnetoresistance effect is [9].…”

Section: System Hardware Designmentioning

confidence: 99%

Research on Non-Contact Weak Current Detection Technology

Chen¹,

Wu²,

Wang³

et al. 2018

JEMAA

View full text Add to dashboard Cite

With the continuous development of industrial technology, the weak current plays an increasingly important role in all fields of life. In order to facilitate the user to carry, the study of contactless weak current measurement technology is also emerging. This article's design idea is based on two-dimensional reluctance sensor device built non-contact weak current detection system. The system uses the reluctance sensor HMC1002 to collect the current signal and the temperature sensor DS18B20 to compensate the temperature. The signals collected by the reluctance sensor and the temperature sensor are extremely weak. After being amplified by the amplifying circuit, the signal is conducive to subsequent detection and processing. Filter circuit can filter out interference signals to achieve the goal of improving accuracy. After the corresponding algorithm of the microcontroller will convert the signal voltage, easy to read and store, thus designing a non-contact current measurement capable of detecting weak currents and achieving higher accuracy.

show abstract

“…The welding is the important process for manufacturing the different kind of materials. The quality of the material is based on the type of welding [3][4][5]. In general, though there are numerous types of welding available, four types of welds are frequently seen in many materials.…”

Section: Introductionmentioning

confidence: 99%

Performance Analysis of Weld Image Classification Using Modified Resnet CNN Architecture

L¹

2021

TURCOMAT

View full text Add to dashboard Cite

The detection and classifications of weld images is important for improving the quality of the joined materials during production period. In order to automate the classification of weld images in industry, this paper proposes an effective automatic method for the detection and classifications of the weld images into four different cases using deep learning methods. In this work, Convolutional Neural Network (CNN) is adopted for the weld image classification by modifying the internal architecture of the CNN architecture. This proposed ResNet CNN architecture is designed with three Convolutional layers, two numbers of pooling layers with activation layer and two numbers of Fully Connected Neural Networks (FCNN).The FCNN in proposed CNN architecture is designed with 15 internal hidden layers and each hidden layer is designed with 20 neurons which obtains high classification efficiency. The morphological activity functional methods are used on the classified weld images to detect the crack regions.

show abstract

Crack Evaluation Based on Novel Circle-Ferrite Induction Thermography

Cited by 18 publications

References 22 publications

Sparse Low-Rank Tensor Decomposition for Metal Defect Detection Using Thermographic Imaging Diagnostics

Sparse Low-Rank Tensor Decomposition for Metal Defect Detection Using Thermographic Imaging Diagnostics

Research on Non-Contact Weak Current Detection Technology

Performance Analysis of Weld Image Classification Using Modified Resnet CNN Architecture

Contact Info

Product

Resources

About