Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
2 results
Search Results
Item Beyond the data range approach to soft compute the reflection coefficient for emerged perforated semicircular breakwater(Springer, 2019) Kundapura, S.; Hegde, A.V.; Wazerkar, A.V.Prediction of reflection coefficient (Kr) for emerged perforated semicircular breakwater (EPSBW) using artificial neural network (ANN) and adaptive neuro-fuzzy inference systems (ANFIS) is carried out in the present paper. A new approach has been adopted in the present work using ANN and ANFIS models for the prediction of the reflection coefficient (Kr) for the wave periods beyond the range of the dataset used for training the network. The experimental data obtained for a scaled down EPSBW model from regular wave flume experiments at Marine Structure laboratory of National Institute of Technology Karnataka, Surathkal, Mangaluru, India was used. The ensemble was segregated such that certain higher ranges of wave periods were excluded in the training, and possibility of prediction was checked. The independent input parameters (Hi, T, S, D, R, d, hs) that influence the reflection coefficient (Kr) are considered for training as well as testing, where Hi is the incident wave height, T is the wave period, S is the spacing of perforations, D is the diameter of the perforations, R is the radius of the breakwater, d is the depth of the water and hs is the structure height. The accuracy of predictions of reflection coefficient (Kr) is done based on the coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE). The study shows that ANN and ANFIS models may be used for prediction of reflection coefficient Kr of semicircular breakwater for beyond the data range of wave periods used for training. However, ANFIS outperformed ANN model in the prediction of Kr in the case of beyond the data range segregation method. © Springer Nature Singapore Pte Ltd. 2019.Item Relative wave run-up parameter prediction of emerged semicircular breakwater(Springer Science and Business Media Deutschland GmbH, 2021) Kundapura, S.; Rao, S.; Arkal, V.H.Relative wave run-up parameter (Ru/Hi) on breakwaters is a vital component in fixing the elevation of the breakwater crest. In the present study, several soft computing methods has been employed to predict the wave run-up on the emerged seaside perforated semicircular breakwater for the prevailing Arabian sea wave climate, off Mangaluru coast in India. Unlike the mathematical modeling techniques, the soft computing tools have no complexity involved about understanding the nature of underlying process and prediction consumes less time when proper physical model data is available. The soft computing methods like artificial neural network (ANN), adaptive neuro fuzzy inference system (ANFIS), genetic algorithm based adaptive neuro fuzzy inference system (GA-ANFIS) and particle swarm based adaptive neuro fuzzy inference system (PSO-ANFIS) are the four models employed in the study. The ANN predicted well for the set architecture of (5-7-1). The ANFIS is used to predict the wave run-up on semicircular breakwater models using the hybrid efficiency of fuzzy logic and neural network. An initial FIS is generated for input variables by mapping the input-output data; the training is done using ANN; and the objective of GA and PSO is set to find the best FIS, reducing the root mean square error in the prediction of wave run-up. The most influencing input parameters (Hi/gT2, d/gT2, S/D, hs/d, R/Hi) are taken in non-dimensional form. The data required has been acquired from the physical model experiments conducted in the Marine structures laboratory of National Institute of Technology Karnataka (NITK), Surathkal, India. The GA-ANFIS prediction of wave run-up is found to be better than that of ANFIS prediction in terms of Correlation coefficient (R), Root mean square error (RMSE), Nash sutcliffe efficiency (NSE), Bias and Scatter index (SI). However, among the four models developed the ANN prediction outperformed the other three considered models with a higher R = 0.9467. © Springer Nature Singapore Pte Ltd 2021.