Faculty Publications

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

Publications by NITK Faculty

Browse

Has files: NoSubject: search.filters.subject.Artificial neural network models

Search Results

Now showing 1 - 5 of 5
  • No Thumbnail Available
    Item
    Neuro-fuzzy based approach for wave transmission prediction of horizontally interlaced multilayer moored floating pipe breakwater
    (2011) Patil, S.G.; Mandal, S.; Hegde, A.V.; Alavandar, S.
    The ocean wave system in nature is very complicated and physical model studies on floating breakwaters are expensive and time consuming. Till now, there has not been available a simple mathematical model to predict the wave transmission through floating breakwaters by considering all the boundary conditions. This is due to complexity and vagueness associated with many of the governing variables and their effects on the performance of breakwater. In the present paper, Adaptive Neuro-Fuzzy Inference System (ANFIS), an implementation of a representative fuzzy inference system using a back-propagation neural network-like structure, with limited mathematical representation of the system, is developed. An ANFIS is trained on the data set obtained from experimental wave transmission of horizontally interlaced multilayer moored floating pipe breakwater using regular wave flume at Marine Structure Laboratory, National Institute of Technology Karnataka, Surathkal, India. Computer simulations conducted on this data shows the effectiveness of the approach in terms of statistical measures, such as correlation coefficient, root-mean-square error and scatter index. Influence of input parameters is assessed using the principal component analysis. Also results of ANFIS models are compared with that of artificial neural network models. © 2010 Elsevier Ltd. All rights reserved.
  • No Thumbnail Available
    Item
    Modeling and genetic algorithm-based multi-objective optimization of the MED-TVC desalination system
    (2012) Janghorban Esfahani, I.; Ataei, A.; Shetty K, K.V.; Oh, T.; Park, J.H.; Yoo, C.
    This study proposes a systematic approach of analysis and optimization of the multi-effect distillation-thermal vapor compression (MED-TVC) desalination system. The effect of input variables, such as temperature difference, motive steam mass flow rate, and preheated feed water temperature was investigated using response surface methodology (RSM) and partial least squares (PLS) technique. Mathematical and economical models with exergy analysis were used for total annual cost (TAC), gain output ratio (GOR) and fresh water flow rate (Q). Multi-objective optimization (MOO) to minimize TAC and maximize GOR and Q was performed using a genetic algorithm (GA) based on an artificial neural network (ANN) model. Best Pareto optimal solution selected from the Pareto sets showed that the MED-TVC system with 6 effects is the best system among the systems with 3, 4, 5 and 6 effects, which has a minimum value of unit product cost (UPC) and maximum values of GOR and Q. The system with 6 effects under the optimum operation conditions can save 14%, 12.5%, 2% in cost and reduces the amount of steam used for the production of 1m 3 of fresh water by 50%, 34% and 18% as compared to systems with 3, 4 and 5 effects, respectively. © 2012 Elsevier B.V..
  • No Thumbnail Available
    Item
    Fluid-Structure Interaction Study and Flowrate Prediction Past a Flexible Membrane Using Immersed Boundary Method and Artificial Neural Network Techniques
    (American Society of Mechanical Engineers (ASME), 2020) Kanchan, M.; Maniyeri, R.
    Many microfluidics-based applications involve fluid-structure interaction (FSI) of flexible membranes. Thin flexible membranes are now being widely used for mixing enhancement, particle segregation, flowrate control, drug delivery, etc. The FSI simulations related to these applications are challenging to numerically implement. In this direction, techniques like immersed boundary method (IBM) have been successful. In this study, two-dimensional numerical simulation of flexible membrane fixed at two end points in a rectangular channel subjected to uniform fluid flow is carried out at low Reynolds number using a finite volume based IBM. A staggered Cartesian grid system is used and SIMPLE algorithm is used to solve the governing continuity and Navier-Stokes equations. The developed model is validated using the previous research work and numerical simulations are carried out for different parametric test cases. Different membrane mode shapes are observed due to the complex interplay between the hydrodynamics and structural elastic forces. Since the membrane undergoes deformation with respect to inlet fluid conditions, a variation in flowrate past the flexible structure is confirmed. It is found that, by changing the membrane length, bending rigidity, and its initial position in the channel, flowrate can be controlled. Also, for membranes that are placed at the channel midplane undergoing self-excited oscillations, there exists a critical dimensionless membrane length condition L ? 1.0 that governs this behavior. Finally, an artificial neural network (ANN) model is developed that successfully predicts flowrate in the channel for different membrane parameters. © 2020 American Society of Mechanical Engineers (ASME). All rights reserved.
  • No Thumbnail Available
    Item
    Numerical Simulation to Predict the Effect of Process Parameters on Hardness during Martempering of AISI4140 Steel
    (Springer, 2021) Pranesh Rao, K.M.P.; Prabhu, K.N.
    Martempering is a widely practiced industrial heat treatment process to harden steel parts with minimum distortion. A numerical experiment to predict hardness distribution in AISI 4140 steel cylinders of various diameters during martempering is presented in this work. Apart from the diameter (D), the effect of other process variables such as heat transfer coefficient (h), bath temperature (Tb), and residence time (tr) was also studied. The relationship between hardness distribution and the aforementioned process variables was highly nonlinear. An artificial neural network (ANN) model with a single hidden layer and 30 hidden layer neurons was thus developed to predict the hardness distribution in martempered AISI 4140 steel cylinders. The increase in bath temperature, diameter, and residence time decreased the average hardness, and an increase in the heat transfer coefficient increased the average hardness of martempered AISI 4140 cylinders. The weights of the ANN model were used to calculate the relative importance of all input variables and they followed a decreasing order of Tb>D>tr>h. © 2021, ASM International.
  • No Thumbnail Available
    Item
    An application of artificial neural network classifier to analyze the behavioral traits of smallholder farmers in Kenya
    (Springer Science and Business Media Deutschland GmbH, 2021) Jena, P.R.; Majhi, R.
    This paper develops and employs a novel artificial neural network (ANN) model to study farmers’ behavior towards decision making on maize production in Kenya. The paper has compared the accuracy level of ANN based models and the statistical model. The results show that the ANN models has achieved higher accuracy and efficiency. The findings from the study reveal that the farmers are mostly influenced by their demographic characteristics and food security conditions in their 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. © 2018, Springer-Verlag GmbH Germany, part of Springer Nature.