Selective laser melted (SLM) IN 718 alloy specimens are subjected to heat treatment and shot peening to assess the effect of post processing on the corrosion performance of the alloy in a 3.5 wt % NaCl solution. The four conditions used in this analysis are as-built material (AB), heat-treated as-built material (HT), shot-peened as-built material (SP), and heat-treated and shot-peened as-built material (HTSP). Microstructural studies revealed the presence of a 500 nm sized cellular structure with a γ matrix surrounded by the Laves phase in the AB material. Shot-peening reduced the surface roughness of the AB and HT samples to almost 80%. The potentiodynamic experiments revealed a highest I_corr value of 0.21 µA/cm² for the AB material and the lowest I_corr value of 0.04 µA/cm² for the HTSP material. In the Electrochemical Impedance Spectroscopy (EIS) analysis, the Nyquist plot substantiated the increasing corrosion resistance in the same order of decreasing corrosion rate. The Bode plot exhibited two resistance–capacitance (RC) time constants for all four conditions. The solution resistance measured around 30 Ω, with the HTSP specimen exhibiting the highest passive film resistance of 676 kΩ cm² and the AB specimen exhibiting the lowest passive film resistance of 234 kΩ cm². This study has shown that elimination of the network of the Laves phase in SLM material through heat treatment and smooth surface morphology achieved through shot peening improves the corrosion resistance of Inconel 718 alloy.

The present work investigates the relationship between fatigue crack growth rate (da/dN) and stress intensity factor range (∆K) using machine learning models with the experimental fatigue crack growth rate (FCGR) data of cryo-rolled Al 2014 alloy. Various machine learning techniques developed recently provide a flexible and adaptable approach to explain the complex mathematical relations especially, non-linear functions. In the present work, three machine algorithms such as extreme learning machine (ELM), back propagation neural networks (BPNN) and curve fitting model are implemented to analyse FCGR of Al alloys. After tuning of networks with varying hidden layers and number of neurons, the trained models found to fit well to the tested data. The three tested models are compared with each other over the training as well as testing phase. The mean square error for predicting the FCG of cryo-rolled Al 2014 alloy by BPNN, ELM and curve fitting methods are 1.89, 1.84 and 0.09 respectively. While the ELM models outperform the rest of models in terms of training time, curve fitting model showed best performance in terms of accuracy over testing data with least mean square error (MSE). In terms of local optimisation, back propagation neural networks excel the other two models.