Towards a Practical Means of Predicting Weld Distortion

2001 ◽  
Vol 17 (02) ◽  
pp. 62-68
Author(s):  
George J. Bruce ◽  
M. Z. Yuliadi ◽  
A. Shahab
Keyword(s):  
Neural Network ◽  
Chemical Composition ◽  
Network Model ◽  
Neural Network Model ◽  
Heat Input ◽  
Weld Distortion ◽  
Good Agreement

Distortion due to heat input from welding is well known, but difficult to predict. It causes rework, adds cost and may affect strength. The paper addresses the complexity of the problem using a neural network model as a predictor. This gave good agreement with experimental distortion data. The sensitivity of results to different variables, including chemical composition, is reported.

A Study on the Prediction of Ship Plate Distortion Topology by Neural Networks

1999 ◽  
Vol 15 (04) ◽  
pp. 191-197
Author(s):  
M. Z. Yuliadi ◽  
A. Shahab ◽  
G. Bruce
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Chemical Composition ◽  
Network Model ◽  
Neural Network Model ◽  
Production Cost ◽  
Detrimental Effect ◽  
Major Contributor ◽  
Variable Sensitivity ◽  
Good Agreement

Ship plate distortion results in a decrease in strength and aesthetics, has a detrimental effect on the fabrication process, as well as an increase in production cost due to the need for correction. Welding heat has been regarded as a major contributor to distortion. Assessing the distortion problem, without making assumptions, is extremely difficult due to the complexity of the variables involved, e.g., welding procedures, materials, design, and geometry. This paper develops a neural network model to predict the topology of ship plate distortion. The developed model presents good agreement with actual distortion data that have been obtained. In terms of variable sensitivity, chemical composition should be taken into account.

PREDICTION OF MECHANICAL PROPERTIES OF 25CrMo48V SEAMLESS TUBE USING NEURAL NETWORK MODEL

2009 ◽  
Vol 23 (06n07) ◽  
pp. 1074-1079 ◽  
Author(s):  
LAIBO SUN ◽  
CHUANYOU ZHANG ◽  
QINGFENG WANG ◽  
MINGZHI WANG ◽  
ZESHENG YAN
Keyword(s):  
Neural Network ◽  
Mechanical Properties ◽  
Chemical Composition ◽  
Network Model ◽  
Neural Network Model ◽  
Transverse Impact ◽  
Relative Significance ◽  
Line Production ◽  
Prediction Of Mechanical Properties ◽  
Trained Neural Network

In this investigation, a neural network model was established to predict mechanical properties of 25 CrMo 48 V seamless tubes. The sensitivity analysis was also performed to estimate the relative significance of each chemical composition in mechanical behavior of steel tubes. The results of this investigation show that there is a good agreement between experimental and predicted values indicating desirable validity of the model. Among those alloying elements, the elements of carbon, silicon and chromium tended to play a more important role in controlling both the yielding strength and the Charpy-V-Notch transverse impact toughness. In comparison, the impurities such as O , N , S and P have a relatively weak impact. More detailed dependences of mechanical properties on each chemical composition in isolation can be revealed using the established model. The well-trained neural network has a great potential in designing tough and ultrahigh-strength seamless tubes and modeling the on-line production parameters.

THE INVESTIGATION OF THE SPIN GLASS PROPERTIES OF THE HOPFIELD NEURAL NETWORK MODEL

2005 ◽  
Vol 16 (03) ◽  
pp. 427-437 ◽  
Author(s):  
FATİH YAŞAR
Keyword(s):  
Neural Network ◽  
Spin Glass ◽  
Network Model ◽  
Neural Network Model ◽  
Mean Field ◽  
Hopfield Neural Network ◽  
Infinite Range Interactions ◽  
Physical Quantities ◽  
Infinite Range ◽  
Good Agreement

In this work, the Hopfield neural network model with infinite-range interactions is simulated by using the multicanonical algorithm. All simulations and measurements are done in spin glass states of the model with discrete ± 1 values of the random variables. Physical quantities such as the energy density, the ground-state entropy and the order parameters are evaluated at all temperatures. Our results in the spin glass region show multiple degenerate ground-states and good agreement with the replica symmetry mean field solutions.

Sign in / Sign up

Export Citation Format

Share Document