Analysis of Depth of Penetration and Impact Strength during Shielded Metal Arc Welding under Magnetic Field using Artificial Neural Networks

Purpose of this work is to find out the optimal welding input process parameters for depth of penetration and impact strength for mild steel plates using shielded metal arc welding process. For this variety of welding experiments were carried out. Parameters such as welding current, welding speed, welding voltage and external magnetic field were chosen as input process parameters, while depth of penetration and impact strength as output parameters. Applications of magnetic field in welding processes have drawn much attention of researchers. However, effect of external magnetic field on quality of weld is still a matter of investigation. In this paper, effect of a longitudinal external magnetic field generated by bar magnets on the weld was experimentally investigated. Based on the results from welding experiments, optimal welding conditions were chosen after analyzing correlation between input and output welding parameters. For this a back propagated feed forward artificial neural network model was trained to predict the output parameters, if four input process parameters were fed to the trained model it would provide the required output variables having values very close to the experimental values. In shielded metal arc welding, non-equilibrium heating and cooling of the weld pool can produce micro structural changes affecting mechanical properties of weld metal. Present work is therefore aimed at characterization of a mild steel weld produced by SMAW technique in terms of its mechanical properties and associated microstructures. Variation in the microstructures of the heat affected zone and weld metal are very critical for life of welded components. Better weld design and optimum combinations of welding parameters are essential for producing high quality weld joints having desired strength, hardness and toughness. Understanding correlation between the process parameters and mechanical properties is a precondition for better productivity and reliability of the welded joints. Although mild steel is widely used in the industry for several applications needed for better strength, hardness and toughness but much information is not available in the open literature regarding variation in tensile strength, hardness and impact properties for change in heat input or other input process parameters. Purpose of present work is to determine effect of input process parameters on the properties of tensile strength and depth of penetration of mild steel using SMAW process. Back propagation artificial neural network having one input layer, one output layer and two hidden layers was used to predict the properties of weld. Initially network was trained with the help of 18 sets of data having input process parameters (current, voltage, speed of welding and external magnetic field) and output properties (tensile strength and depth of penetration) of the weld, obtained by different tests. After this the trained artificial neural network program could be used for predicting the properties of weld for a given set of input process parameters. Similarly desired properties of the weld could be obtained by applying required input welding parameters. Citation: Dr. Rudra Pratap Singh. "Analysis of Depth of Penetration and Impact Strength during Shielded Metal Arc Welding under Magnetic Field using Artificial Neural Networks." Global Research and Development Journal For Engineering 4.10 (2019): 12 - 20.