Classification of the Resistance Spot Weld Failure Mode Using Convolutional Neural Network

2021 ◽  
Author(s):  
Watchanun Piriyabunjerd ◽  
Chettapong Janya-anurak
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Failure Mode ◽  
Spot Weld ◽  
Resistance Spot ◽  
Weld Failure ◽  
Resistance Spot Weld

On the Failure Mode of Resistance Spot Welded Hsla 420 Steel / Tryb Uszkodzenia Zgrzewanych Spoin Stali Hsla 420

2013 ◽  
Vol 58 (1) ◽  
pp. 67-72 ◽  
Author(s):  
M. Pouranvari
Keyword(s):  
Failure Mode ◽  
Fusion Zone ◽  
Peak Load ◽  
Spot Weld ◽  
Zone Size ◽  
Spot Welds ◽  
Resistance Spot ◽  
Resistance Spot Welds ◽  
Resistance Spot Weld ◽  
Pullout Failure

Failure mode of resistance spot welds (interfacial vs. pullout) is a qualitative measure of resistance spot weld performance. Considering adverse effect of interfacial failure mode on the vehicle crashworthiness, process parameters should be adjusted so that the pullout failure mode is guaranteed ensuring reliability of spot welds during vehicle lifetime. In this paper, metallurgical and mechanical properties of HSLA 420 resistance spot welds are studied with particular attention to the failure mode. Results showed that the conventional weld size recommendation of 4t0:5 (t is sheet thickness) is not sufficient to guarantee pullout failure mode for HSLA steel spot welds during the tensile-shear test. Considering the failure mechanism of spot welds during the tensileshear test, minimum required fusion zone size to ensure the pullout failure mode was estimated using an analytical model. Fusion zone size proved to be the most important controlling factor for peak load and energy absorption of HSLA 420 resistance spot weld.

LENS CLASSIFICATION ACCORDING TO THE TYPE OF LIGHT SPOT USING A NEURAL NETWORK

2020 ◽  
Vol 2020 (4) ◽  
pp. 4-14
Author(s):  
Vladimir Budak ◽  
Ekaterina Ilyina
Keyword(s):  
Neural Network ◽  
Light Intensity ◽  
Convolutional Neural Network ◽  
Deep Convolutional Neural Network ◽  
Beam Angle ◽  
New Model ◽  
Technical Parameters ◽  
Transfer Training ◽  
Trained Network

The article proposes the classification of lenses with different symmetrical beam angles and offers a scale as a spot-light’s palette. A collection of spotlight’s images was created and classified according to the proposed scale. The analysis of 788 pcs of existing lenses and reflectors with different LEDs and COBs carried out, and the dependence of the axial light intensity from beam angle was obtained. A transfer training of new deep convolutional neural network (CNN) based on the pre-trained GoogleNet was performed using this collection. GradCAM analysis showed that the trained network correctly identifies the features of objects. This work allows us to classify arbitrary spotlights with an accuracy of about 80 %. Thus, light designer can determine the class of spotlight and corresponding type of lens with its technical parameters using this new model based on CCN.

Sign in / Sign up

Export Citation Format

Share Document