Real-time holographic nondestructive inspection system with automatic defect classification

1997 ◽  
Author(s):  
Helen H. Chen ◽  
Tin M. Aye ◽  
Dai Hyun Kim ◽  
Jack A. Latchinian ◽  
Vernon A. Brown ◽  
...  
Keyword(s):  
Real Time ◽  
Nondestructive Inspection ◽  
Inspection System ◽  
Defect Classification

A league-winner algorithm for defect classification in an industrial web inspection system

2021 ◽  
Vol 175 ◽  
pp. 114753
Author(s):  
Angel Gaspar Gonzalez-Rodriguez ◽  
Antonio Gonzalez-Rodriguez ◽  
Fernando Jose Castillo-Garcia
Keyword(s):  
Inspection System ◽  
Defect Classification ◽  
Web Inspection

Real-Time Image-Based Defect Inspection System of Internal Thread for Nut

2019 ◽  
Vol 68 (8) ◽  
pp. 2830-2848
Author(s):  
Chun-Fu Lin ◽  
Sheng-Fuu Lin ◽  
Chi-Hung Hwang ◽  
Hao-Kai Tu ◽  
Chih-Yen Chen ◽  
...  
Keyword(s):  
Real Time ◽  
Inspection System ◽  
Internal Thread ◽  
Defect Inspection ◽  
Real Time Image ◽  
Time Image

Modeling of Characteristics of Magneto-Optical Sensor Using FEM and Dipole Model for Nondestructive Evaluation

2005 ◽  
Vol 297-300 ◽  
pp. 2022-2027 ◽  
Author(s):  
Jin Yi Lee ◽  
Ji Seoung Hwang ◽  
Tetsuo Shoji ◽  
Jae Kyoo Lim
Keyword(s):  
Optical Sensor ◽  
High Speed ◽  
Crack Depth ◽  
Image Data ◽  
Nondestructive Inspection ◽  
Dipole Model ◽  
Inspection System ◽  
Optical Intensity ◽  
The Finite Element Method ◽  
Reflected Light

The magneto-optical nondestructive inspection system (hereafter refer to as RMO system) using magneto-optical sensor (hereafter refer to as MO sensor) offers the benefits of providing image data and LMF information at the same time. Therefore this system makes it possible to carry out remote and high speed inspection of cracks from the intensity of the reflected light and to estimate the shape of a crack more effectively than by already existing methods. In other words, the shape of crack could be evaluated using image data, and crack depth can be determined by calculating the intensity of reflected light. The purposes of this study were to confirm the vertical components of leakage magnetic flux from a crack using RMO system and to verify the effects of MO sensor using the finite element method and dipole model calculation. The effectiveness of these analysis methods was compared with experiments using a RMO system and several types and sizes of the crack on plate specimens. The volume of a crack could be estimated using the optical intensity regardless of the shape of cracks.

Real-time on-site inspection system for power transmission based on heterogeneous computing

2021 ◽  
pp. 1-10
Author(s):  
Xiaohong Yan ◽  
Zhigang Zhao ◽  
Yongqiang Liu
Keyword(s):  
Computational Complexity ◽  
Real Time ◽  
Power Supply ◽  
Heterogeneous Computing ◽  
Power Transmission ◽  
Modern Society ◽  
Power Line ◽  
Frame Rate ◽  
Inspection System ◽  
On Site Inspection

As the need of power supply is tremendously increasing in modern society, the stableness and reliability of the power delivery system are the two essential factors that ensure the power supply safety. With the quick expansion of electricity infrastructures, the failures of power transmission system are becoming more frequent, leading to economic loss and high risk of maintenance work under hazardous conditions. The existing automatic power line inspection utilizes advanced convolutional neural network (CNN) to improve the inspection efficiency, emerging as one promising solution. But the needed computational complexity is high since CNN inference demands large amount of multiplication-and-accumulation operations. In this paper, we alleviate this problem by utilizing the heterogeneous computing techniques to design a real-time on-site inspection system. Firstly, the required computational complexity of CNN inference is reduced using FFT-based convolution algorithms, speeding up the inference. Then we utilize the region of interest (ROI) extrapolation to predict the object detection bounding boxes without CNN inference, thus saving computing power. Finally, a heterogeneous computing architecture is presented to accommodate the requirements of proposed algorithms. According to the experiment results, the proposed design significantly improves the frame rate of CNN-based inspection visual system applied to power line inspection. The processing frame rate is also drastically improved. Moreover, the precision loss is negligible which means our proposed schemes are applicable for real application scenarios.

?Nondestructive Inspection System Using Optical Profiles and Laser Surface Waves to Detect a Surface Crack

2010 ◽  
Vol 56 (1(1)) ◽  
pp. 333-337 ◽  
Author(s):  
Seung-Kyu Park ◽  
Sung-Hoon Baik ◽  
Hyung-Ki Cha ◽  
Yong-Moo Cheong ◽  
Young-June Kang
Keyword(s):  
Surface Waves ◽  
Surface Crack ◽  
Nondestructive Inspection ◽  
Laser Surface ◽  
Inspection System

A Nondestructive Inspection System for the Inspection of Wear Surfaces in Tank Track Shoes

2005 ◽  
Author(s):  
Valery F. Godínez-Azcuaga ◽  
Finlayson Richard D. ◽  
Basavaraju B. Raju
Keyword(s):  
Nondestructive Inspection ◽  
Inspection System

Real-time Analysis of an IC Wire-bonding Inspection System

1999 ◽  
Vol 5 (6) ◽  
pp. 409-421 ◽  
Author(s):  
M. Rajeswari ◽  
M.G. Rodd
Keyword(s):  
Real Time ◽  
Wire Bonding ◽  
Inspection System ◽  
Time Analysis ◽  
Real Time Analysis
Sign in / Sign up

Export Citation Format

Share Document