An Artificial Neural Network Approach to Plastic Collapse of Oval Boiler Tubes

K. Zarrabi; A. Basu

doi:10.4028/www.scientific.net/AMR.41-42.421

Paper Titles

Process and Properties of Pulse Electrodeposited RE-Ni-W-P-SiC Composite Coatings
p.385

Advances in Residual Stress Modeling and Measurement for the Structural Integrity Assessment of Welded Thermal Power Plant
p.391

The Effect of Prestress on Vibration Behavior of Structures in Impedance Method Damage Detection
p.401

Barkhausen Noise and its Use for Quality Control of the Production of Transmission Gears
p.407

An Artificial Neural Network Approach to Plastic Collapse of Oval Boiler Tubes
p.421

Test Methods to Assess Transverse Weld Metal Hydrogen Cracking
p.427

Microstructure and Texture Evolution of Cross Rolled AZ31 Mg Sheet
p.435

Kowari – OPAL’s Residual-Stress Diffractometer and its Application to Materials Science and Engineering
p.439

Secondary Buckling and Progressive Failure Analysis of Tailored Composite Panels in Thin-Walled Box-Shape Composite Beams under Bending and Torsion
p.445

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 41-42An Artificial Neural Network Approach to Plastic...

An Artificial Neural Network Approach to Plastic Collapse of Oval Boiler Tubes

Abstract:

Boilers in power, refinery and chemical processing plants contain extensive range of tube bends. Tube bends are manufactured by bending a straight-section tube. As a result, the crosssection of a tube bend becomes oval. Using the finite element analysis (FEA) and artificial neural network (ANN), the paper presents the relationships between the plastic collapse pressures and tube bend dimensions with various degrees of ovality. It is found that as ovality increases the plastic collapse pressure decreases. Also, the reduction of plastic collapse pressure with ovality is small for a thick tube bend when compared with that for a thin tube bend.