Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
87 results
Search Results
Item Swarm intelligence-based support vector machine (PSO-SVM) approach in the prediction of scour depth around the bridge pier(Springer Verlag service@springer.de, 2019) Marulasiddappa, B.M.; Rao, M.; Mandal, S.The mechanism of scour around the bridge pier is a complex phenomenon, and it is very difficult to make a common method to predict or estimate the depth of scour hole. In this paper, a hybrid model is developed, combining support vector machine and particle swarm optimization (PSO-SVM) to predict scour depth around a bridge pier. The input parameters such as sediment size (d50), the velocity of flow (U), and time (t) are used in the study to predict the scour depth. The models are developed with RBF, polynomial, and linear kernel functions, and the performances are evaluated using different statistical parameters such as CC, RMSE, NSE, and NMB. The predicted results are compared with measured scour depth. The predicted scour depth reveals that PSO-SVM with RBF kernel function model is found to be reliable and efficient in predicting the scour depth around bridge piers. © Springer Nature Singapore Pte Ltd. 2019Item Application of Neural Networks in coastal engineering - An overview(2008) Mandal, S.; Patil, S.G.; Manjunatha, Y.R.; Hegde, A.V.Artificial Neural Network (ANN) is being applied to solve a wide variety of coastal/ocean engineering problems. In practical terms ANNs are non-linear modeling tools and they can be used to model complex relationship between the input and output system. In addition, ANNs have a very high degree of freedom and are very simple to train the system for any number of input values, which makes the network attractive and reliable. ANNs are ideally suited to find many solutions like pattern reorganization, data classification, forecasting future events and time series analysis. This paper gives an overview of application of ANN in the field of coastal engineering.Item Hybrid genetic algorithm tuned support vector machine regression for wave transmission prediction of horizontally interlaced multilayer moored fl oating pipe breakwater(2011) Patil, S.G.; Mandal, S.; Hegde, A.V.; Muruganandam, A.Support Vector Machine (SVM) works on structural risk minimization principle that has greater generalization ability and is superior to the empirical risk minimization principle as adopted in conventional neural network models. However, it is noticed that one particular model in isolation cannot capture all data patterns easily. In the present paper, a hybrid genetic algorithm tuned support vector machine regression (HGASVMR) model was developed to predict wave transmission of horizontally interlaced multilayer moored fl oating pipe breakwater (HIMMFPB). Furthermore, parameters of both linear and nonlinear SVM models are determined by Genetic Algorithm. HGASVMR model was trained on the dataset obtained from experimental wave transmission of HIMMFPB using regular wave fl ume at Marine Structure Laboratory, National Institute of Technology, Surathkal, India. The results are compared with artifi cial neural network (ANN) model in terms of Correlation Coeffi cient, Root Mean Square Error and Scatter Index. Performance of HGASVMR is found to be reliably superior.Item Low Temperature Development of Nano-Hydroxyapatite from Austromegabalanus psittacus, Star fish and Sea urchin(Elsevier Ltd, 2017) Komalakrishna, H.; Shine Jyoth, T.G.; Kundu, B.; Mandal, S.The study focuses the preparation and characterization (physico-chemical and mechanical) of hydroxyapatite [Ca10(PO4)6(OH)2] (HAp) from naturally occurring dead marine species widely available in Arabian sea shore; namely Austromegabalanus psittacus, star fish (Asteroidea) and sea urchin (Echinoidea). All three marine species were found to be source of calcium carbonate in the form of aragonite (calcite) that crystallize in an organic matrix. The calcined aragonite was converted to nano-sized hydroxyapatite powder by chemical reaction with Ortho-phosphoric acid while maintaining stoichiometry, Ca/P = 1.67 at 80 °C. It was found from XRD that the powders were composed of pure HAp with average crystallite size of 10 nm. SEM, on the other hand, revealed nano-rod like elongated structures having a length in the range of 100 to 700 nm with an aspect ratio of 3.5. Further, the HAp powders were used to prepare cylindrical pellet samples by uni-axial pressing, sintered at 1100 °C temperature, made flat-parallel, polished and used finally for assessment of elastic modulus by compression test method. Primary results showed typical elastic modulus of pellets from Austromegabalanus psittacus is 3 GPa, star fish 2.1 GPa and sea urchin 2.3 GPa (L/D = 1.3 and strain rate = 0.01 mm/s). Thus, the powder synthesized from marine source could be a potential alternative for development of structural bio-ceramics and also can be used as scaffolds for bone or dental implants, because of its easy and economical fabrication. © 2017 Elsevier Ltd. All rights reserved.Item PSO-SVM approach in the prediction of scour depth around different shapes of bridge pier in live bed scour condition(Springer Verlag service@springer.de, 2019) Marulasiddappa, B.M.; Kuntoji, G.; Rao, M.; Mandal, S.Scour is one of the major factors which affects directly on the durability and safety of the Bridge abutments. Based on the experimental data of Goswami in 2012, an effort is made to predict local scour by using a hybrid approach of Swarm Intelligence based algorithms which is today one of the powerful tools of optimization techniques. In this work, an intelligent model based on support vector machine in combination with the particle swarm optimization (PSO-SVM) technique is developed. The PSO-SVM models are developed with RBF, Polynomial and Linear kernel functions. The circular, rectangular, round-nosed, and sharp-nosed shapes of piers are considered in live bed scour condition. The scour depth around bridge piers is predicted by considering Sediment size, flow velocity, and time of flow as input parameters. Prediction accuracy of the models is evaluated using the model performance indicators such as Root Mean Square Error (RMSE, Correlation Coefficient (CC), Nash Succlift Error (NSE), etc. The results obtained from the model are compared with the measured scour depth to validate the reliability of the hybrid model. Based on the results, PSO based SVM model is found to be successful, reliable, and efficient in predicting the scour depth around the bridge pier. © Springer Nature Singapore Pte Ltd. 2019.Item Fabrication of solution combustion based transparent semiconducting titanium and zinc co-doped indium oxide (Itizo) films(Trans Tech Publications Ltd ttp@transtec.ch, 2019) Vardhan, R.V.; Manjunath, G.; Mandal, S.In this work, solution combustion processed titanium, zinc co-doped indium oxide high transparent semiconducting thin films were demonstrated at annealing temperatures of 300, 350 °C. In the process, low-temperature combustion at 123 °C was verified through thermogravimetric analysis; acetylacetone, 2-methoxyethanol served as fuel and solvent respectively in the redox reaction. Indium titanium zinc oxide (ITiZO) films were developed on glass substrates by spin coating followed by annealing at different temperatures. ITiZO films, powder exhibited high crystallinity exactly matching with indium oxide peaks without forming secondary phases. But, the presence of In, Ti, Zn, and O is clearly visible on film through energy dispersive spectroscopy. Films had transparency more than 85% in the visible range with optical band gap ranging 3.8-3.9 eV. These ITiZO films with smooth and low roughness ranging 0.46-0.5 nm, can have a potential application as an active layer in transparent thin film transistors and optoelectronic devices. © 2019 Trans Tech Publications Ltd, Switzerland.Item A Novel Non-Isolated DC-DC Converter with Active Switched-Inductor for High Voltage Gain Applications(Institute of Electrical and Electronics Engineers Inc., 2022) Mandal, S.; Prabhakaran, P.A Novel, Transformer-less DC-DC Converter for high voltage gain (HVG) applications is proposed in this paper. The proposed converter consists of an active switched inductor for HVG with reduced voltage and current stress across the components. The proposed converter has a voltage gain of (3D+1) times than that of the conventional boost converter. The proposed converter uses fewer components and provides HVG with relatively small duty ratios. A good feature of the proposed topology is all the switches and intermediate capacitors have equal voltage stress. The proposed converter can support bidirectional operation with wide duty ratio variations. The working principle and steady-state analysis of this converter is explained in detail. Dynamic modelling of the converter is presented, and both voltage and current control operations can be carried out. To validate the theoretical analysis, detailed simulation results are presented. © 2022 IEEE.Item A Novel Bidirectional Modified Zeta Converter with Wide Voltage Conversion Ratio(Institute of Electrical and Electronics Engineers Inc., 2023) Mandal, S.; Prabhakaran, P.A Novel, transformer-less, bidirectional and high-gain DC-DC converter is proposed in this paper, which is apt for the interface between two DC voltage levels in various applications, including microgrids. This converter achieves a wide voltage gain with reduced voltage and current stress across the components. The proposed converter supports bidirectional capability with low components. The proposed converter's operating principle and steady-state analysis are explained in detail for continuous conduction mode (CCM). Dynamic modelling of the converter is presented, and closed-loop controllers are designed. The proposed converter operates in both current and voltage control modes. The design of voltage and current compensators are elaborated. Detailed analysis and simulation results are presented in this paper to validate the theoretical analysis and performance of the proposed converter. © 2023 IEEE.Item A Novel Bidirectional Modified SEPIC Converter with Wide Voltage Conversion Ratio(Institute of Electrical and Electronics Engineers Inc., 2023) Mandal, S.; Prabhakaran, P.A Novel, transformer-less, bidirectional DC-DC Converter based on modified SEPIC topology is proposed in this paper. In the proposed converter, an active switched inductor configuration is incorporated in the conventional SEPIC converter to achieve a wide voltage conversion ratio with reduced voltage and current stress across the components. The proposed converter supports bidirectional buck-boost (BBB) capability with low components. The proposed converter's operating principle and steady-state analysis are explained in detail for continuous conduction mode (CCM). Dynamic modelling of the converter is presented and closed-loop controllers are designed. The proposed converter operates in both current and voltage control modes. The design of voltage and current compensators are detailed in this paper. Detailed analysis and simulation results are presented to validate the theoretical analysis and performance of the proposed converter. © 2023 IEEE.Item A Novel Bidirectional Modified SEPIC-Cuk Converter with Wide Voltage Conversion Ratio(Institute of Electrical and Electronics Engineers Inc., 2023) Mandal, S.; Prabhakaran, P.The paper proposes a novel transformer-less bidirectional DC-DC converter that achieves ultra-high gain and reduces voltage stress across components. This converter is based on modified SEPIC and CUK topologies, and its derivation, operating principle, and steady-state analysis are presented. The paper also includes dynamic modeling of the converter and the design of closed-loop controllers for voltage and current control modes. Detailed analysis and simulation results are provided to demonstrate the efficacy and performance of the proposed topology. Overall, this innovative converter offers a promising solution for high-efficiency energy transfer with ultra-high voltage gain in various applications. © 2023 IEEE.