Neural Network Prediction of Hardness in HAZ of Temper Bead Welding Using the Proposed Thermal Cycle Tempering Parameter (TCTP)

Abstract

A new thermal cycle tempering parameter (TCTP) to characterize the tempering effect during multi-pass thermal cycles has been proposed by extending the Larson-Miller parameter (LMP) to non-isothermal heat treatment. Experimental results revealed that the hardness in synthetic HAZ of low-alloy steel subjected to multi-pass tempering thermal cycles has a good linear relationship with the TCTP. The new hardness prediction system was constructed by using a neural network taking into consideration of the tempering effect during multi-pass welding, estimated by using the TCTP. Based on the thermal cycles numerically obtained by FEM and the experimentally obtained hardness database, the hardness distribution in HAZ of low-alloy steel welded with temper bead welding method was calculated. The predicted hardness was in good accordance with the experimental results. It follows that our new prediction system is effective for estimating the tempering effect in HAZ during multi-pass welding and hence enables us to assess the effectiveness of temper bead welding.