THE YIELD AND ULTIMATE TENSILE-STRENGTH OF STEEL WELDS

The design of welding alloys to match the ever advancing properties of newly developed steels is not an easy task. It is traditionally attai ned by experimental trial and error, modifying compositions and weldin g conditions until a satisfactory result is discovered. Savings in cos t and time might be achieved if the trial process could be minimised. This work outlines the use of an artificial neural network to model th e yield and ultimate tensile strengths of weld deposits from their che mical composition, welding conditions and heat treatments. The develop ment of the models is described, as is the confirmation of their metal lurgical accuracy. (C) 1997 Elsevier Science S.A.