Prediction of Weld Penetration in FCAW of HSLA steel using Artificial Neural Networks

Abstract

Flux‐cored arc welding (FCAW) is a semiautomatic or automatic arc welding process that requires a continuously‐fed consumable tubular electrode containing a flux. The main FCAW process parameters affecting the depth of penetration are welding current, arc voltage, nozzle‐to‐work distance, torch angle and welding speed. Shallow depth of penetration may contribute to failure of a welded structure since penetration determines the stress‐carrying capacity of a welded joint. To avoid such occurrences; the welding process parameters influencing the weld penetration must be properly selected to obtain an acceptable weld penetration and hence a high quality joint. Artificial neural networks (ANN), also called neural networks (NN), are computational models used to express complex non‐linear relationships between input and output data. In this paper, artificial neural network (ANN) method is used to predict the effects of welding current, arc voltage, nozzle‐to‐work distance, torch angle and welding speed on weld penetration depth in gas shielded FCAW of a grade of high strength low alloy steel. 32 experimental runs were carried out using the bead‐on‐plate welding technique. Weld penetrations were measured and on the basis of these 32 sets of experimental data, a feed‐forward back‐propagation neural network was created. 28 sets of the experiments were used as the training data and the remaining 4 sets were used for the testing phase of the network. The ANN has one hidden layer with eight neurons and is trained after 840 iterations. The comparison between the experimental results and ANN results showed that the trained network could predict the effects of the FCAW process parameters on weld penetration adequately.