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 (ANN)

Search Results

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    Prediction of damage level of inner conventional rubble mound breakwater of tandem breakwater using swarm intelligence-based neural network (PSO-ANN) approach
    (Springer Verlag service@springer.de, 2019) Kuntoji, G.; Rao, S.; Rao, M.; Reddy, E.N.B.
    The conventional rubble mound breakwater is a coastal protective structure commonly used decades before which alone failed to withstand the deepwater wave and its energy, and suffered a catastrophic failure. Keeping in mind both the safe functioning of harbor and stability of the breakwater for the fast-growing economy of the country, different types of breakwaters are being developed to serve this purpose. Tandem breakwater is an innovative type of breakwater, which is a combination of main conventional rubble mound breakwater and submerged reef in front of it. One of the advantages of this breakwater is that most of the wave energy is dissipated and wave intensity is reduced by submerged reef and the smaller waves interact with main breakwater and ensure its stability. Experimental studies are laborious and time-consuming to conduct. Therefore, it is necessary to carry out the detailed study of tandem breakwater stability by making use of simple and alternate techniques using the experimental data. In the present study, an attempt is made to understand the suitability and applicability of PSO-ANN, a hybrid soft computing technique for predicting damage level of conventional rubble mound breakwater of tandem breakwater. Based on the experimental data available in Marine Structure Laboratory, NITK, Surathkal, India, soft computing models are developed. The performances of the models are evaluated using model performance indicators. Results obtained demonstrate that the proposed new approach can be used to predict the damage level of conventional rubble mound breakwater of tandem breakwater efficiently and accurately. © Springer Nature Singapore Pte Ltd. 2019
  • No Thumbnail Available
    Item
    Classifying behavioural traits of small-scale farmers: Use of a novel artificial neural network (ANN) classifier
    (Institute of Electrical and Electronics Engineers Inc., 2016) Jena, P.R.; Majhi, R.
    This paper develops and employs a novel artificial neural network (ANN) model to study farmers' behaviour towards decision making on maize production in Kenya. The paper has compared the accuracy level of ANN based model and the statistical model and found out that the ANN model has achieved higher accuracy and efficiency. The findings from the study reveal that the farmers are mostly influenced by their demographic and food security for decision making. Further to examine the relative importance of different demographic and food security characteristics, an ANOVA test is undertaken. The results found that education and food security indices are instrumental in influencing farmers' decision making. © 2016 IEEE.
  • No Thumbnail Available
    Item
    Numerical Modeling on Buckling Behavior of Structural Stiffened Panel
    (Springer Science and Business Media Deutschland GmbH, 2023) Alagundi, S.; Palanisamy, T.
    Stiffened panels are essential building elements in weight-sensitive structures. They have various applications in marine, aircraft, and other structures. Plate structures can undergo buckling when subjected to axial compression loads and then exhibit out of plane displacements. The present work aims to study the buckling behavior of the stiffened panel. The finite element model of the stiffened panel is developed, and buckling analysis is performed using ANSYS software. This model is validated with the published experimental work. Once the model is validated, total of 320 numbers of models of stiffened panels with varying plate thickness, stiffener height, stiffener thickness, and distance between stiffeners are modeled in ANSYS-2020, and buckling analysis is performed. An artificial neural network model is proposed to predict the buckling load of the stiffened panel. Neural network model is created in MATLAB software, and it is trained, tested, and validated, and its performance is checked by statistical relations like coefficient of correlation and mean square error. Proposed ANN model shows high accuracy in the prediction of buckling load. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
  • No Thumbnail Available
    Item
    Response surface methodology and artificial neural network-based models for predicting performance of wire electrical discharge machining of inconel 718 alloy
    (MDPI Multidisciplinary Digital Publishing Institute rasetti@mdpi.com, 2020) Lalwani, V.; Sharma, P.; Pruncu, C.I.; Unune, D.R.
    This paper deals with the development and comparison of prediction models established using response surface methodology (RSM) and artificial neural network (ANN) for a wire electrical discharge machining (WEDM) process. The WEDM experiments were designed using central composite design (CCD) for machining of Inconel 718 superalloy. During experimentation, the pulse-on-time (TON), pulse-off-time (TOFF), servo-voltage (SV), peak current (IP), and wire tension (WT) were chosen as control factors, whereas, the kerf width (Kf), surface roughness (Ra), and materials removal rate (MRR) were selected as performance attributes. The analysis of variance tests was performed to identify the control factors that significantly affect the performance attributes. The double hidden layer ANN model was developed using a back-propagation ANN algorithm, trained by the experimental results. The prediction accuracy of the established ANN model was found to be superior to the RSM model. Finally, the Non-Dominated Sorting Genetic Algorithm-II (NSGA- II) was implemented to determine the optimum WEDM conditions from multiple objectives. © 2020 by the authors.