Failure of a Steam Accumulator Due to Lack of Complete Weld Penetration

2019 ◽  
Keyword(s):  
Weld Penetration ◽  
Steam Accumulator

Investigations on the effect of weld penetration on fatigue strength of rib-to-deck welded joints in orthotropic steel decks

2014 ◽  
Vol 15 (2) ◽  
pp. 299-310 ◽  
Author(s):  
Cao Vu Dung ◽  
Eiichi Sasaki ◽  
Keiji Tajima ◽  
Toshimitsu Suzuki
Keyword(s):  
Fatigue Strength ◽  
Welded Joints ◽  
Weld Penetration ◽  
Orthotropic Steel Decks

Monitoring of laser weld penetration using sensor fusion

2002 ◽  
Vol 14 (2) ◽  
pp. 114-121 ◽  
Author(s):  
Allen Sun ◽  
Elijah Kannatey-Asibu ◽  
Mark Gartner
Keyword(s):  
Sensor Fusion ◽  
Weld Penetration ◽  
Laser Weld

OCT-Einschweißtiefenüberwachung bei Unterdruck/OCT-based weld penetration monitoring at reduced ambient pressure – Influence of reduced ambient pressure on the OCT signal quality in laser deep penetration welding

2021 ◽  
Vol 111 (11-12) ◽  
pp. 863-868
Author(s):  
Thorsten Mattulat ◽  
Ronald Pordzik ◽  
Peer Woizeschke
Keyword(s):  
Penetration Depth ◽  
Ambient Pressure ◽  
Laser Beam Welding ◽  
In Situ Monitoring ◽  
Deep Penetration ◽  
Weld Penetration ◽  
Laser Deep Penetration Welding ◽  
Deep Penetration Welding ◽  
Non Destructive

Die optische Kohärenztomographie (OCT) erlaubt die zerstörungsfreie In-situ-Überwachung der Einschweißtiefe beim Laserstrahlschweißen. Für dieses Verfahren wird hier der Einfluss von verringerten Umgebungsdrücken auf die Messqualität untersucht. Es wird gezeigt, dass sich bei niedrigerem Umgebungsdruck deutlich größere Signalanteile aus dem Bereich des Bodens der Dampfkapillare zurückerhalten lassen. Auf diese Weise steigen die effektive Messfrequenz und die Erkennbarkeit von Änderungen der Einschweißtiefe.   Optical coherence tomography (OCT) enables non-destructive in-situ monitoring of the weld penetration depth during laser beam welding. For this technology, the influence of reduced ambient pressures on the measurement quality is investigated. It is shown that significantly larger signal components are obtained from the bottom of the vapor capillary at lower ambient pressure increasing the applicable measurement frequency and the detectability of changes in the weld penetration depth.

Vision sensing and feedback control of weld penetration in helium arc welding process

2021 ◽  
Vol 72 ◽  
pp. 168-178
Author(s):  
Guodong Peng ◽  
Baohua Chang ◽  
Guoqing Wang ◽  
Yanjun Gao ◽  
Runshi Hou ◽  
...  
Keyword(s):  
Feedback Control ◽  
Arc Welding ◽  
Welding Process ◽  
Weld Penetration ◽  
Vision Sensing ◽  
Arc Welding Process

Estimation of Al/Cu laser weld penetration in photodiode signals using deep neural network classification

2021 ◽  
Vol 33 (4) ◽  
pp. 042009
Author(s):  
Kidong Lee ◽  
Sanghoon Kang ◽  
Minjung Kang ◽  
Sung Yi ◽  
Cheolhee Kim
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Weld Penetration ◽  
Laser Weld ◽  
Neural Network Classification

scholarly journals Dynamic Characteristics of the Steam Accumulator Charging and Discharging

2017 ◽  
Vol 100 ◽  
pp. 03005
Author(s):  
Peizhi Yang ◽  
Xia Hu ◽  
Gang Liao
Keyword(s):  
Dynamic Characteristics ◽  
Steam Accumulator

scholarly journals Deep Learning-Based Detection of Penetration from Weld Pool Reflection Images

2020 ◽  
Vol 99 (9) ◽  
pp. 239s-245s
Author(s):  
CHAO LI ◽  
◽  
QIYUE WANG ◽  
WENHUA JIAO ◽  
MICHAEL JOHNSON ◽  
...  
Keyword(s):  
Weld Pool ◽  
Data Augmentation ◽  
Welding Process ◽  
Descent Method ◽  
Machine Learning Techniques ◽  
Gradient Descent Method ◽  
Neural Net ◽  
Weld Penetration ◽  
Process Data ◽  
Pool Surface

An innovative method was proposed to determine weld joint penetration using machine learning techniques. In our approach, the dot-structured laser images reflected from an oscillating weld pool surface were captured. Experienced welders typically evaluate the weld penetration status based on this reflected laser pattern. To overcome the challenges in identifying features and accurately processing the images using conventional machine vision algorithms, we proposed the use the raw images without any processing as the input to a convolutional neural network (CNN). The labels needed to train the CNN were the measured weld penetration states, obtained from the images on the backside of the workpiece as a set of discrete weld penetration categories. The raw data, images, and penetration state were generated from extensive experiments using an automated robotic gas tungsten arc welding process. Data augmentation was performed to enhance the robustness of the trained network, which led to 270,000 training examples, 45,000 validation examples, and 45,000 test examples. A six-layer convolutional neural net-work trained with a modified mini-batch gradient descent method led to a final testing accuracy of 90.7%. A voting mechanism based on three continuous images increased the classification accuracy to 97.6%.

Sign in / Sign up

Export Citation Format

Share Document