This paper presents an effect of friction welding parameters on the tensile strength and microstructural properties of dissimilar AISI 1020-ASTM A536 joints. A hybrid response surface methodology (RSM) and genetic algorithm (GA)-based technique were successfully developed to model, simulate, and optimise the welding parameters. Direct and interaction effects of process parameters on the ultimate tensile strength (UTS) were studied by plotting graphs. Friction force and friction time have a positive effect on tensile strength. As friction force and friction time increase, the tensile strength also increases. The maximum tensile strength of the friction-welded low carbon steel-ductile iron joints was 87 % of that of the base metal. The tensile properties, microstructure, Vickers hardness distribution, and fracture morphology of the welded specimen have been studied and presented in this study. Additionally, the distribution of carbon element on both sides of the interface was estimated using energy-dispersive spectroscopy (EDS). The results of the metallographic study show clearly that the friction welding process was accompanied by a diffusion of carbon atoms from ductile iron to steel. This process causes the formation of a carbon-rich zone at the interface and decarburization zone in the ductile iron close to the bond interface.

In this study, an efficient optimisation method by combining response surface methodology (RSM) and genetic algorithm (GA) is introduced to find the optimal topology of artificial neural networks (ANNs) for predicting colour changes in rehydrated apple cubes. A multi-layered feed-forward backpropagation ANN model of algorithms was developed to correlate one output (colour change) to four input variables (drying air temperature, drying air velocity, temperature of distilled water and rehydration time). A predictive model for ANN topology in terms of the best mean squared error (MSE) performance on validation samples was created using RSM. RSM model was integrated with an effective GA to find the optimum topology of ANN. The optimum ANN had minimum MSE when the number of hidden neurons, learning rate, momentum constant, number of epochs and number of training runs were 13, 0.33, 0.89, 3869 and 3, respectively. MSE of optimal ANN topology on validation samples was 0.0072095. It turned out that the optimal ANN topology can be considered as more precise for predicting colour change in the rehydrated apple cubes. Mean absolute error and regression coefficient (R) of the optimal ANN topology were determined as 0.0259 and 0.96475 for training, 0.0399 and 0.95243 for testing and 0.0264 and 0.95151 for validation data sets. The results of the testing model on new samples showed excellent agreement between the actual and predicted data with coefficient of determination R ² = 0.97.