Dendukuri Ananth Pavan Prabhakar

A proposed study based on an artificial neural network (ANN) model will be used to predict microhardness (VHN) and tensile strength (TS) of Friction Stir Additive Manufacturing (FSAM) of AA8090 alloy. The process parameters taken into consideration were rotational speed (1000, 1500, 2000 rpm), traverse speed (45, 65, 85 mm/min) and tilt angle (0°, 1°, 2°). We performed 90 physical experiments (74 + 7 + 6 + 3), in which 74 experiments were generated with the help of the Central Composite Design of ANN modeling, seven independent experiments were used to validate the results, six repeat experiments were taken, and three mid-level interpolation experiments were performed. Out of 74 modeling runs, 60 samples were trained, 14 were internally tested, and seven separate modeling runs were exclusively tested externally. An ANN model was created based on the Adam optimizer, where the loss was taken to be Mean Squared Error (MSE). The level of model robustness was assessed employing 5-fold cross-validation and grouped validation (LOPCO, LOFLO-RPM, and LOFLO-TA). Under 5-fold cross-validation, the ANN had mean R² values equal to 0.940 (VHN), 0.920 (TS). In normalized training, the model achieves MAE = 0.26 and R² = 0.97, whereas testing in physical units has developed MAE values of 1.0 and 2.0, respectively (VHN and TS). These results correspond with the high predictive ability and generalization of the ANN model, as indicated by the uniform performance of the ANN model on training, cross-validation, internal testing, and independent validation. The importance analysis of features revealed that rotational speed was the most significant factor that influenced the tensile strength and microhardness. The constructed ANN model is a credible and sound system for optimizing and replicating processes from other friction-stir processing methods on AA8090 alloy.

Aircraft structures are frequently exposed to damage from environmental factors and operational wear, leading to the development of surface imperfections such as cracks. These imperfections can increase aerodynamic drag, a phenomenon known as excrescence drag. To mitigate these effects and quickly restore structural integrity, repair patches, often made from aluminium alloys and tailored to the damage, are applied following guidelines set out in the Aircraft Battle Damage Repair (ABDR) manuals. This paper investigates the aerodynamic performance impacts of applying such patches to two prominent airfoil models: the symmetric NACA 0012 and the cambered NACA 2412. Utilizing advanced computational tools including CATIA V5 for 3D modelling and CFD++ for fluid dynamics simulation, this study examines changes in aerodynamic characteristics such as lift, drag, and pressure distribution under various flow conditions. The research particularly focuses on quantifying the aerodynamic changes introduced by the patches through detailed analyses of lift curves, drag polars, and pressure coefficient (Cp) plots. Our findings aim to provide insights into the trade-offs involved in patch repairs, exploring how different patch configurations influence airfoil performance. This contributes to the development of optimized repair strategies that ensure minimal aerodynamic disruption while extending the operational lifespan of aircraft components.

This review reports on the influencing parameters on the joining parts quality of tools and techniques applied for conducting process analysis and optimizing the friction stir welding process (FSW). The important FSW parameters affecting the joint quality are the rotational speed, tilt angle, traverse speed, axial force, and tool profile geometry. Data were collected corresponding to different processing materials and their process outcomes were analyzed using different experimental techniques. The optimization techniques were analyzed, highlighting their potential advantages and limitations. Process measurement techniques enable feedback collection during the process using sensors (force, torque, power, and temperature data) integrated with FSW machines. The use of signal processing coupled with artificial intelligence and machine learning algorithms produced better weld quality was discussed.

FDM is a prominent AM process from which 3D models can be generated. Optimisation algorithms are used to get best levels of process parameters. The aim of this article is to analyse statistically the L16 OA and its corresponding responses in order to obtain optimal process parameter level combinations which could make the product efficient. The process parameters considered were extrusion temperature and infill density. The optimal parameter settings obtained were an extrusion temperature of 220°C and an infill density of 80%. Each parameter was considered at four different levels. Since there were two factors at four levels, L16 OA was preferred to design the experimental plan. The process parameters were selected based on the output responses. A total of 16 samples for each response were manufactured and tested, and statistical analysis was carried out. Statistical approaches like ANOVA analysis and S/N ratio analysis were used to get significance of factors and optimal parameter settings, and analysis was performed using MINITAB 16. Validation tests were carried out with optimal parameter settings as input parameters. Statistical analysis showed that extrusion temperature was a more significant factor compared to infill density for both tensile and compressive strengths.