Journal of Welding Science

In this research, the optimization of the artificial neural network (ANN) capability for predecting the tensile strength and elongation of friction stir welded Al-5083 (FS-welded Al-5083) was carried out. The effective parameters of ANN, such as the number of layers, number of neurons in hidden layers, transfer function between layers, the learning algorithm and etc. were investigated and the efficient neural network was determined to predict the tensile properties of FS-welded Al-5083. The investigations revealed that the perceptron neural network with two hidden layers and 17 neurons numbers, Lunberg-Marquardt training algorithm and Logsig transfer function for the intermediate layers and Tansig transformation function for the output layer is the most optimized neural network for the prediction. The optimized network has an optimal structure based on the minimum value of the mean square error of 0.05, the maximum total correlation coefficient of 0.93 and the line regression with an angle of 45 degrees between the actual and estimated values. Therefore, this network has a good performance for training, generalizing and estimating of tensile strength and elongation of FS-welded Al-5083.

In this study, mechanical properties of the transient liquid phase (TLP) bonds between Hastelloy X to Ni3Al IMC at temperature range of 800 - 900 °C were investigated. The microstructure of the joints was examined by optical and scanning electron microscopy. Also, high temperature XRD (HTXRD) analysis was utilized to investigate the phase changes at different temperatures of half-joints. According to microscopic observations, the joint cross-section consisted of three regions including diffusion affected zone (DAZ), isothermal solidification zone (ISZ), and Athermal solidification zone (ASZ), which increasing temperature and time result in ISZ consisting of nickel-rich solid solution developed across the microstructure. The optimum joint bonding strength was achieved for the sample treated at 1100 °C – 180 min equal to 355 ± 4.5 MPa. The ultimate tensile strength reached 36.5 ± 1 and 20.5 ± 1 MPa at temperatures of 800 °C and 900 °C, respectively. Fracture occurred on the side of the IMC substrates at both test temperatures due to the presence of shrinkage porosity during the solidification stage of IMC and crystal lattice parameters mismatch with the matrix.

This study aimed to investigate the effect of diffusion welding parameters on the microstructural characteristics and mechanical properties of the dissimilar joint between AISI 418 stainless steel and Inconel 738 superalloy using Ni interlayer with a thickness of 50 µm. The experiments were performed in a vacuum furnace at three temperatures of 1000, 1050 and 1150 °C for 45, 60, 75 and 90 min under the pressure of 5 MPa.The results show that voids and non-bonded areas are seen in the samples that were bonded at a lower temperature (1000 °C). By increasing the joining temperature from 1000 °C to 1050 °C, all micro discontinuities have disappeared, which shows that the microplastic deformation of roughness has improved. Then, by increasing the temperature to 1150 °C,non-bonded areas are observed in the joint due to the reduction of pressure on the contact surfaces. When pure nickel is used as an interlayer, intermetallic compounds of
γ' [Ni3(Al, Ti)] are formed in the γ matrix phase on the side of Inconel 738 superalloy while compounds of FeNi3 and γ (γFe, Ni) are formed on the side of AISI 418 stainless steel. According to the results of line scan analysis, the slope and penetration of elements in Inconel 738 superalloy is lower than AISI 418 stainless steel , which indicates less penetration in Inconel 738 superalloy. In the sample welded at the temperature of 1050 °C and the time of  90 Min, the penetration value of the nickel interlayer in AISI 418 stainless steel  and Inconel 738 superalloy was 40 µm and 35 µm, respectively. By comparing the maximum hardness, it can be concluded that the joint at the temperature of 1050 °C and the time of 90 Min has a lower maximum hardness than other samples. Therefore, it has better joint characteristics than other samples in terms of intermetallic compounds. The highest value of shear strength was obtained at the temperature of 1050 °C and the time of 90 Min, which is equal to 270 MPa.

In this research, the transient liquid phase bonding of St52 carbon steel to WC-Co cermet using a copper interlayer with 50 μm thickness was done. For this purpose, samples were jointed to each other at a constant temperature of 1100 ºC and bonding times of 1, 15, 30, and 45 min. The microstructure of the joints was examined using an optical microscope and scanning electron microscope equipped with energy-dispersive X-ray spectroscopy. XRD analysis was also used to investigate the effect of bonding on the phase changes of the bonding area. Microhardness and tensile shear tests were also conducted to study the mechanical properties of the samples. Microstructural investigations showed the formation of three different zones including isothermal and athermal solidification zones and DAZ in the WC-Co base material side, which determine the characteristics of the samples. The isothermal solidification zone contained a Fe-rich solid solution and the athermal solidification zone contained a Cu-rich solid solution. η phase was not formed in the DAZ of WC-Co cermet at bonding times of 1 and 15 min. This phase was formed in the DAZ of WC-Co cermet by increasing the bonding time to 30 and 45 min. The microhardness studies showed that all samples had the same trend. Maximum microhardness was 1100 HV which was related to WC-Co base cermet and the lowest microhardness was about 220 HV which was related to steel base metal. Also, the maximum tensile-shear strength of the bonded samples was about 180 MPa for a bonded sample at a bonding time of 15 min, which was due to the increase in the volume fraction of iron-rich solid solution, as well as proper microstructural continuity and the presence of an optimal amount of copper-rich phase in the microstructure.