Research on Defect Location Method of C Language Code Based on Deep Learning

Author(s):  
Yaling Zhang ◽  
Jie Zhou ◽  
Jing Hu
2021 ◽  
Vol 120 ◽  
pp. 102435
Author(s):  
Lei Yang ◽  
Huaixin Wang ◽  
Benyan Huo ◽  
Fangyuan Li ◽  
Yanhong Liu

Author(s):  
Shaojie Chen ◽  
Shaoping Zhou ◽  
Yong Li ◽  
Lanzhu Zhang

Ultrasonic guided wave technology combined with sparse transducer array provides an efficient and relatively cost-effective means of defect detection and monitoring for rapid interrogation of large in plate-like structures. However, imaging algorithm used baseline subtraction methods may be compromised under mismatched environment and operational conditions. A defect location method based on forward-scattering wave and fuzzy c-means clustering is proposed in this paper. The distance coefficient including location information between sensor pair using exciting and receiving signal and defect is defined to explain feasibility of the method proposed in this paper. A Parallel line array is evaluated using the method to locate defect. Experimental results show that the proposed method can effectively reduce the influence of mismatched environment and operational conditions on the defect location.


Author(s):  
Bin Feng ◽  
Lin Zhang ◽  
Shuai Hou ◽  
Xiaojing Dang ◽  
Wenbo Zhu ◽  
...  

2019 ◽  
Vol 9 (6) ◽  
pp. 1107 ◽  
Author(s):  
Bo Xing ◽  
Zujun Yu ◽  
Xining Xu ◽  
Liqiang Zhu ◽  
Hongmei Shi

This paper proposes a rail defect location method based on a single mode extraction algorithm (SMEA) of ultrasonic guided waves. Simulation analysis and verification were conducted. The dispersion curves of a CHN60 rail were obtained using the semi-analytical finite element method, and the modal data of the guided waves were determined. According to the inverse transformation of the excitation response algorithm, modal identification under low-frequency and high-frequency excitation was realized, and the vibration displacements at other positions of a rail were successfully predicted. Furthermore, an SMEA for guided waves is proposed, through which the single extraction results of four modes were successfully obtained when the rail was excited along different excitation directions at a frequency of 200 Hz. In addition, the SMEA was applied to defect location detection, and the single reflection mode waveform of the defect was extracted. Based on the group velocity of the mode and its propagation time, the distance between the defect and the excitation point was measured, and the defect location was predicted as a result. Moreover, the SMEA was applied to locate the railhead defect. The detection mode, the frequency, and the excitation method Were selected through the dispersion curves and modal identification results, and a series of signals of the sampling nodes were obtained using the three-dimensional finite element software ANSYS. The distance between the defect and the excitation point was calculated using the SMEA result. When compared with the structure of the simulated model, the errors obtained were all less than 0.5 m, proving the efficacy of this method in precisely locating rail defects, thus providing an innovated solution for rail defect location.


2019 ◽  
Vol 36 (2) ◽  
pp. 1143-1151 ◽  
Author(s):  
Liu Jian ◽  
Jin Zequn ◽  
Zhang Rui ◽  
Liu Meiju ◽  
Gao Enyang

Author(s):  
Stellan Ohlsson
Keyword(s):  

2019 ◽  
Vol 53 (3) ◽  
pp. 281-294
Author(s):  
Jean-Michel Foucart ◽  
Augustin Chavanne ◽  
Jérôme Bourriau

Nombreux sont les apports envisagés de l’Intelligence Artificielle (IA) en médecine. En orthodontie, plusieurs solutions automatisées sont disponibles depuis quelques années en imagerie par rayons X (analyse céphalométrique automatisée, analyse automatisée des voies aériennes) ou depuis quelques mois (analyse automatique des modèles numériques, set-up automatisé; CS Model +, Carestream Dental™). L’objectif de cette étude, en deux parties, est d’évaluer la fiabilité de l’analyse automatisée des modèles tant au niveau de leur numérisation que de leur segmentation. La comparaison des résultats d’analyse des modèles obtenus automatiquement et par l’intermédiaire de plusieurs orthodontistes démontre la fiabilité de l’analyse automatique; l’erreur de mesure oscillant, in fine, entre 0,08 et 1,04 mm, ce qui est non significatif et comparable avec les erreurs de mesures inter-observateurs rapportées dans la littérature. Ces résultats ouvrent ainsi de nouvelles perspectives quand à l’apport de l’IA en Orthodontie qui, basée sur le deep learning et le big data, devrait permettre, à moyen terme, d’évoluer vers une orthodontie plus préventive et plus prédictive.


Sign in / Sign up

Export Citation Format

Share Document