Grey-Based Taguchi Multiobjective Optimization and Artificial Intelligence-Based Prediction of Dissimilar Gas Metal Arc Welding Process Performance

The quality of a welded joint is determined by key attributes such as dilution and the weld bead geometry. Achieving optimal values associated with the above-mentioned attributes of welding is a challenging task. Selecting an appropriate method to derive the parameter optimality is the key focus of this paper. This study analyzes several versatile parametric optimization and prediction models as well as uses statistical and machine learning models for further processing. Statistical methods like grey-based Taguchi optimization is used to optimize the input parameters such as welding current, wire feed rate, welding speed, and contact tip to work distance (CTWD). Advanced features of artificial neural network (ANN) and adaptive neuro-fuzzy interface system (ANFIS) models are used to predict the values of dilution and the bead geometry obtained during the welding process. The results corresponding to the initial design of the welding process are used as training and testing data for ANN and ANFIS models. The proposed methodology is validated with various experimental results outside as well as inside the initial design. From the observations, the prediction results produced by machine learning models delivered significantly high relevance with the experimental data over the regression analysis.

Performance of weld bead profile during A-TIG welding on nitrogen alloyed stainless steel

Austenitic stainless steel (ASS) is widely fabricated by tungsten inert gas (TIG) welding for aesthetic look and superior mechanical properties while compared to other arc welding process. Hitherto, the limitation of this process is low depth of penetration and less productivity. To overcome this problem activated tungsten inert gas (A-TIG) welding process is employed as an alternative. In this investigation the welding performance of conventional TIG welding is compared with A-TIG process using TiO2 and SiO2 flux with respect to weld bead geometry. The experimental investigation on A-TIG welding of ASS-201 grade shows TiO2 flux helps in achieve higher penetration as compared to SiO2 flux. While welding with SiO2 the hardness in HAZ and weld region higher than that of TIG welding process.

Experimental and Numerical Analysis on TIG Arc Welding of Stainless Steel Using RSM Approach

This study involves the validating of thermal analysis during TIG Arc welding of 1.4418 steel using finite element analyses (FEA) with experimental approaches. 3D heat transfer simulation of 1.4418 stainless steel TIG arc welding is implemented using ABAQUS software (6.14, ABAQUS Inc., Johnston, RI, USA), based on non-uniform Goldak’s Gaussian heat flux distribution, using additional DFLUX subroutine written in the FORTRAN (Formula Translation). The influences of the arc current and welding speed on the heat flux density, weld bead geometry, and temperature distribution at the transverse direction are analyzed by response surface methodology (RSM). Validating numerical simulation with experimental dimensions of weld bead geometry consists of width and depth of penetration with an average of 10% deviation has been performed. Results reveal that the suggested numerical model would be appropriate for the TIG arc welding process. According to the results, as the welding speed increases, the residence time of arc shortens correspondingly, bead width and depth of penetration decrease subsequently, whilst simultaneously, the current has the reverse effect. Finally, multi-objective optimization of the process is applied by Derringer’s desirability technique to achieve the proper weld. The optimum condition is obtained with 2.7 mm/s scanning speed and 120 A current to achieve full penetration weld with minimum fusion zone (FZ) and heat-affected zone (HAZ) width.

An Ensemble Random Forest Model to Predict Bead Geometry in GMAW Process

A prevalent method for rapid prototyping of metallic parts is gas metal arc welding (GMAW). As the input parameters impose a highly nonlinear impact on the weld bead geometry, precise estimation of the geometry is a complex problem. Therefore, in this study, a novel combination of the most powerful machine learning algorithms is selected to overcome the complexity of the problem and also reach an acceptable degree of precision. To this end, the hybrid combination of the support vector machine (SVM) and relevance vector machine (RVM) is developed based on the random forest (RF) ensemble learning approach. The models are established based on a global database of welding geometry, and the corresponding process parameters obtained are based on a set of experiments. Performance evaluation between RVM, SVM, and the proposed model was performed based on the coefficient of determination ([Formula: see text]) and the ratio of root means square error (RMSE) to the maximum measured outputs ([Formula: see text]/[Formula: see text]). The RF-based RVM-SVM model obtained 0.9725 and 0.8850 for [Formula: see text] and 0.0257 and 0.0447 for [Formula: see text]/[Formula: see text] in predicting the height and width of the bead, respectively. The result clearly showed the effectiveness of the proposed model in predicting the GMAW trend.