Faculty Publications

Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736

Publications by NITK Faculty

Browse

Subject: search.filters.subject.Artificial neural network approach

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    A study on the behavior of CO2 corrosion on pipeline using computational fluid dynamics, experimental and artificial neural network approach
    (IOP Publishing Ltd custserv@iop.org, 2020) Nayak, N.; Anarghya, A.; Al Adhoubi, M.
    Corrosion of the piping systemis a genuine problem in the oil and gas industry.Most oil and gas industries used a carbon steel pipeline for the transportation of crude oil, which is affected by CO2 corrosion. Now a day, the computational approach and artificial neural network approach will be used to study the corrosion rate. Therefore, in this work, Computational Fluid Dynamics (CFD) and Artificial Neural Network (ANN) studies on piping systems were made to determine the corrosion rate induced byCO2 saturated aqueous solutions on carbon steel pipeline. In CFD study, corrosion rates were computed by modeling the electrochemical processes occurring at themetal substrate fromcathodic reductions of the carbonic acid and hydrogen ions, and the anodic oxidation of the metal component. Also, an artificial neural network study wasmade using a multilayer perceptron neural network method; and, computational fluid dynamics and artificial neural network simulations were validated with in-house built experiment set-up. The experimental study had been carried out for more than 200-h to find the corrosion rate on the pipeline, and satisfactory trendswere observed between computational fluid dynamics, artificial neural network, and experimental values. In the end, corroded pipes were observed under a scanning electron microscope and X-ray spectroscopy, and the corroded zones were viewed as against the non-corroded pipe. © 2020 IOP Publishing Ltd.
  • No Thumbnail Available
    Item
    A novel EFG meshless-ANN approach for static analysis of FGM plates based on the higher-order theory
    (Taylor and Francis Ltd., 2024) K P, A.; Swaminathan, K.; Indu, N.; H, S.
    An Element Free Galerkin (EFG) meshless formulation and solutions using higher order shear deformation theory with nine degrees of freedom for the static analysis of Functionally Graded Material (FGM) plates are provided. This technique estimates the shape function using Moving Least Squares (MLS) method. The proposed method is validated by comparing the present findings with those in the literature. A novel Artificial Neural Network (ANN) model is developed to forecast the deflection of FGM plates within less computational time. Detailed parametric and convergent studies reveal that the proposed EFG solution and the ANN technique are more efficient than their conventional counterparts. The validation and comparison of the generated results in the present investigation with the other analysis methods revealed that the EFG method and ANN model give more accurate results than the FEM and other meshless methods. The current EFG-ANN model reduces computing time by 99.94% when compared to the EFG approach. Also, the accuracy is enhanced using the EFG approach with HSDT9 for the FGM plate. © 2023 Taylor & Francis Group, LLC.
  • No Thumbnail Available
    Item
    Effect of addition of Ce and accumulative roll bonding on structure-property of the Mg-Ce-Al hybrid composite and its prediction and comparison using artificial neural network (ANN) approach
    (Institute of Physics, 2024) Anne, G.; Bhat, N.; Vishwanatha, H.M.; Ramesh, S.; Maruthi Prashanth, B.H.; Sharma, P.; Aditya Kudva, S.; Jagadeesh, C.; Nanjappa, Y.
    Light alloys play a crucial role in realizing the national strategy for energy conservation and emission reduction, as well as promoting the upgrading of manufacturing industries. Mg/Al composite laminates combine the corrosion resistance and ductility of aluminium alloy with the lightweight characteristics of magnesium alloy. The addition of Ce (rare earth elements) can improve the mechanical properties of magnesium via grain refinement and improve the ductility of the hybrid composites. In the present work, an investigation on addition of Ce into the Mg/Al matrix through Accumulative Roll Bonding (ARB) has been presented. The Mg/Ce/Al hybrid composite consists of Mg-4%Zn alloy and Al 1100 alloy with 0.2% Ce particles added between the dissimilar layers. The changes occurred in the evaluation of microstructure, corrosion and mechanical properties of the Mg/Ce/Al hybrid composite as a result of deformation process and also the addition of Ce have been explicated. The ARB parameters: temperature, rolling speed, percentage reduction, and aging time, have been studied. An increase of about 2.36 times in strength and hardness of the hybrid composite, has been reported. Further, the structure-property relations in the Mg/Ce/Al hybrid composites were aslo predict and compare using machine learning models: Decision Tree and Multi-Layer Perceptron (MLP) models. © 2024 The Author(s). Published by IOP Publishing Ltd.