Development of ANN modelling for estimation of weld strength and integrated optimization for GTAW of Inconel 825 sheets used in aero engine components

Abstract

Nickel-based superalloys are widely used in fabrication of components in aero space and nuclear sectors due to excellent strength, corrosion resistance, good ductility and high-temperature resistance. Inconel 825 superalloy is predominantly used for making aircraft engine components. This work investigates single pass welding of Inconel 825 strips employing gas tungsten arc welding. Four weld parameters, viz. welding speed (V), welding current (I), arc length (N) and gas flow rate (GFR), were used to investigate ultimate tensile strength (UTS) of weld employing Box-Behnken design having 27 experiments. The welding current is found the most dominating factor followed by welding speed (V). Higher heat input with low welding speed increases deposition rate that ensures more strength in weldment. Microstructural analysis shows two different grain boundaries, i.e., solidification sub-grain boundaries and solidification grain boundaries, in fusion zone. Artificial neural network (ANN) modelling for UTS is developed, and its predictive capability is compared with multiple regression analysis. A new integrated ANN-TLBO-based soft computing modelling and optimization approach is proposed for obtaining optimum weld parameters to maximize weld strength. The proposed optimization methodology obtained maximum UTS of 701.73 MPa at optimal weld parameters I = 120 A, V = 180 mm/min, GFR= 12 l/min and N = 2.24 mm. Validation result was found highly encouraging with 0.60% error with confirmation experiment. The proposed method has better convergent capability with minimum number of iterations.

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

“…Synapses are the linkages that interconnect neurons, and each synapse has a weighting related to them. The artificial neural modeling technique is elaborated herein [38,39]. The hidden layers and neurons throughout the neural network influence the functioning of the ANN.…”

Prediction of heat generation effect on force torque and mechanical properties at varying tool rotational speed in friction stir welding using Artificial Neural Network

“…Sathiya et al 26 worked on laser welding, and they implemented ANN model to develop a relationship between input parameters of laser welding like beam power, travel speed, and focal position, etc. Moreover, the other researchers like Shanjeevi et al, 27 Jha et al, 28 Mi and Ume, 29 Choudhury et al, 30 Paventhan et al, 31 Jeng et al, 32 Lee and Um, 33 Aktepe et al, 34 Kshirsagar et al 35 used the ANN tool to validate the experimental and numerical results and predicted the data for mentioned input in different welding processes. Dehabadi et al 36 predicted the microhardness of friction stir welded AA6061 plates using ANN technique.…”

Retrieval of parameters in micromixer with obstacle by cascade‐forward‐type artificial neural network: Comparison of four training algorithms under noisy data

“…As compared to any numerical/experimental approach, ANN offers the following advantages: (1) only correct pair of data (input-output) is required; that is, exact relation between the output and input is not needed, (2) a trained ANN model can give the result in much less time, that is, time taken to solve any similar problem is drastically less as compared to other means, (3) both the experimental and/or numerical data can be used to develop an ANN model, and (4) inverse problem can be solved easily. [7][8][9][10][11] Various advantages of the ANN approach make it a useful tool to solve scientific problems in different fields, like, manufacturing, 12,13 oil exploration, 14 biofuels, 15,16 solar, 17 lubrication, 18 automobile, 19 power plants, 20 and so on. Various thermal and fluid problems solved by employing ANN and various optimization tools are listed in Table 1.…”

“…Various advantages of the ANN approach make it a useful tool to solve scientific problems in different fields, like, manufacturing, 12,13 oil exploration, 14 biofuels, 15,16 solar, 17 lubrication, 18 automobile, 19 power plants, 20 and so on. Various thermal and fluid problems solved by employing ANN and various optimization tools are listed in Table 1.…”