Using baffles in exhaust mufflers is known to improve their transmission loss. The baffle cut ratio should affect the muffler performance analogous to a shell-and-tube heat exchanger. To the authors’ knowledge, there is no previous assessment reported in literature of the effects that the baffle cut ratio configuration has on acoustic response and back pressure. This investigation presents a parametric study on the effect of baffle configuration on transmission loss and pressure drop predicted. The effect of (i) the baffle cut ratio and baffle spacing, (ii) the number of baffle holes, and (iii) the hole distribution for their effect on transmission loss was investigated. Results show that decreasing the baffle cut ratio tends to increase the transmission loss at intermediate frequencies by up to 45%. Decreasing the spacing between muffler plates was shown to enhance the muffler transmission loss by 40%. To assess the baffle effect on flow, the OpenFoam CFD libraries were utilized using the thermal baffle approach model. Baffles were found to cause sudden drop in fluid temperature in axial flow direction. The outlet exhaust gases temperature was found to decrease by 15% as the baffle cut ratio changed from 75% to 25%

Prediction of weld bead geometry is critical for any welding process, since several mechanical properties of the weldment depend on this. Researchers have used artificial neural networks (ANNs) to predict the bead geometry based on the input parameters for a welding process; however, the number of hidden layers used in these ANNs are limited to one due to the small amount of data usually available through experiments. This results in a reduction in the accuracy of prediction. Such ANNs are also incapable of capturing sudden changes in the input–output trends; for example, where a wide range of heat inputs results in flat crown (zero crown height), but any further reduction in the current sharply increases the crown height. In this study, it was found that above mentioned issues can be resolved on using a two-stage algorithm consisting of support vector machine (SVM) and an ANN. The two-stage SVM–ANN algorithm significantly improved the accuracy of prediction and could be used as a replacement for the multiple hidden layer ANN, without requiring additional data for training. The improvement in prediction was evident near regions of sudden changes in the input–output correlation and can lead to a better prediction of mechanical properties.