2. Thesis and Dissertations
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/1/10
Browse
9 results
Search Results
Item A Study on Performance Enhancement of Cutting Tools through Perforated Surface for the Machining of Titanium Alloy using PCD Inserts(National Institute of Technology Karnataka, Surathkal, 2019) Rao, Charitha M.; Rao, Shrikantha S.; Herbert, Mervin A.In the manufacturing industry, high-speed machining technology has been widely used in metal cutting due to its remarkable advantages in improving the productivity. However, the cutting tools have minimum tool life when used for machining difficult-to-cut materials such as titanium alloys and nickel-based alloys. Titanium alloy (Ti-6Al-4V alloy) is one of the widely used materials in the application of aerospace industries, military applications, automobile industries and biomedical implants. Rapid tool wear is the main issue in machining these difficult-to-cut materials due to the high heat generation in the machining zone and high chemical reactivity at higher cutting conditions. The heat produced at shear zone during machining of Ti-6Al-4V alloy is highly centralized and temperature increases rapidly. Tribological properties at the toolchip contact area can be improved by using a number of methods like Minimum Quantity Lubrication (MQL) and surface coatings. The surface texturing technology is a promising approach in this regard. Many researchers have discussed with different surface texturing patterns such as parallel, perpendicular and elliptical micro/nano textures on cutting inserts. These surface textures helped in improving the tribological properties. The present work is focused on surface textures with micro-hole patterns on cutting inserts, under the MQL environment. In this process, the lubricant surrounded in the micro-holes at the tool-chip interface could be squeezed to the cutting interface to reduce friction under proper viscosity and sliding speed. A novel configuration of holes and tunnels in the inserts has been tried out successfully. The present work is divided into three phases while machining of Ti-6Al- 4V alloy using the micro-hole patterned cutting insert under MQL environment. In the first phase, the modelling and simulation of micro-hole patterned cutting inserts were developed using Finite Element Analysis software. In this phase, different micro-hole patterns were developed on PolyCrystalline Diamond (PCD) cutting insert using CAD modelling and later static and dynamic analysis were carried out. From the results, it was observed that cutting inserts with micro-holes embedded on rake face and flank face had lower stress concentration. Hence, proved that cutting inserts with micro-holes withdifferent hole configurations had no adverse impact on mechanical properties of cutting tool materials. In the second phase, optimization strategy is applied to identify the right configuration of surface texture and experiments were conducted based on the one factor at a time approach to study the behaviour of individual process parameters like cutting velocity, feed rate and depth of cut on the performance indexes such as cutting temperature, machining vibrations, tool flank wear, Material Removal Rate (MRR), chip-morphology and surface integrity (surface roughness, surface topography and microhardness) under MQL environment machining using normal and modified cutting inserts. It is evident from the experimental results that machining with modified inserts significantly improved the machining performance and quality of the product. One more finding, out of the present work, is the mitigation of serrated chips, when compared to chip formation in machining of Ti-6Al-4V alloys with normal inserts. The chip formation with less shear bands were obtained during machining process due to the improvement in the thermal stability property caused by a reduction in cutting temperature through micro-hole patterns. A best feasible micro-hole configuration for the machining of Ti-6Al-4V alloy under MQL environment was arrived at, as a unique solution. In the third phase, the modified PCD insert with the chosen pattern of micro-holes was compared with Polycrystalline Cubic Boron Nitride (PCBN) inserts, for machining of the Ti-6Al-4V alloy. From the experimental results, it was found that modified PCD insert had better efficiency in reducing the cutting temperatures and also reduces the tool wear by increasing the wear resistance properties due to the micro-pool lubrications when compared to modified PCBN inserts. Another important outcome of this research is the development of prediction model using Adaptive Neuro-Fuzzy Inference System (ANFIS) to assist in validation. This method is a combination of two soft-computing methods of ANN and Fuzzy logic. Fuzzy logic helps in the transformation of the human knowledge and the ANN helps in the learning process and reduces the rate of errors in the determination of rules in fuzzy logic. In this research, gauss membership function model was developed for the prediction ofoutput parameters. The comparison made between the predicted values derived from ANFIS and experimental values proved that the gauss membership function adaptation achieved accuracy of 96 % with 4-5% prediction error. Thus, a unique surface texturing consisting of micro-holes and tunnels in the PCD inserts, for machining Ti-6Al-4V alloy has been successfully developed, tested and validated.Item Estimation of saturated hydraulic conductivity in spatially variable fields using various soft computing techniques(National Institute of Technology Karnataka, Surathkal, 2019) More, Satish Bhaurao; Deka, Paresh ChandraSaturated hydraulic conductivity (Kfs) is one of the dominant and most essential soil hydrology characteristics, for understanding and duplicating various hydrological processes having environmental importance. Its estimation by (laboratory / field) method is cumbersome, time consuming and costly. In addition, the results may not be representative due to spatial variability of Kfs. This attracted researcher to address this problem by developing pedotransfer function (PTF), which estimate saturated hydraulic conductivity by using routinely measured soil properties. Objective of this study is to investigate the spatial variability of saturated hydraulic conductivity under different land use land cover by using Guelph permeameter, and to develop PTF for estimating Kfs, from soil index properties, by using soft computing techniques and thus evaluate the performance of these techniques by using statistical tests. Study is carried out at Solapur, India. Three sites (0.76ha) were identified which are having different land use land cover. The site is divided in to small grids of 10m X 10m, and observations were taken at corner of each such grid, at 15cm, 30cm and 45cm depth. In situ and laboratory tests were carried out to estimate Kfs and other basic index properties of soil. Observed data (In situ as well as laboratory) were preprocessed and then used for modeling purpose. Total dataset (Three sites, three depth with 100 sampling points; so overall 900 sample data) is segregated into six sub dataset (college, Mulegaon, Punanaka, 15cm, 30cm and 45cm). Each subset consisting of 300 observations is further split into two parts in six different ways (90% + 10%, 85% + 15%, 80% +20%, 75% + 25%, 70% + 30%, and 67% + 33%) to train the models and validate it, the combination which gives good results during training and validation is selected. For checking performance of model, various statistical parameters such as correlation coefficient (R), mean relative error(MRE), root mean square error (RMSE), normalized root mean square error (NRMSE) and Nash Sutcliffe efficiency (NSE) has been made. Scatter plots were used to evaluate the accuracies of the models. For deciding best model these checks are used, Value of R ~ 1, value and NSE ~ 1, MRE close to zero, and NRMSE is close to zero. Scatter plot point distribution should be around and close to 1:1 line. Maximum value of log saturated hydraulic conductivity was observed at Punanaka (3.842 m yr-1) and minimum value at college site (0.002myr-1). Standard deviation for Kfs was least at Punanaka (0.598m yr-1) and was maximum at college site (0.804myr- 1). Porosity has strong positive Correlation coefficient 0.9 whereas bulk density has strong negative correlation of 0.9. The performance of ELM model at all six subsets was found performing better than SVM and ANFIS model. NRMSE values of ELM model (training: testing) were found [0.02:0.06, 0.07:0.09, 0.02:0.07, 0.03:0.08, 0.07:0.10 and 0.008:0.04] at college site, Mulegaon site, Punanaka site, 15cm depth, 30cm depth and 45cm depth respectively. Saturated hydraulic conductivity was found varying spatially, land use land cover has influence on Kfs and it found declining with depth. College station has shown more variability in Kfs also variation of Kfs was found more at 45cm depth. Maximum Standard deviation was found in college site and minimum standard deviation was found at Punanaka site. Variability of porosity, bulk density and particle density was found insignificant in logarithmic scale. Soil particle size was found declining with depth. Porosity has shown strong positive correlation with Kfs, whereas bulk density has shown strong negative correlation. Performance of ELM model was found excellent in all six sub data set both during training and testing. Performance of SVM and ANFIS was not found satisfactory during testing although they are within acceptable accuracy. Saturated hydraulic conductivity has shown spatial variation; it was varying along depth as well as lateral and longitudinal direction, generally Kfs was found decreasing with depth. Kfs was found decreasing down the slope. ELM model outperformed other two models tried in this study (ANFIS and SVM). Texture of soil was founddeclining from coarse to fine with depth at majority of sampling location. Mean value of Kfs was found more at Punanaka site (15cm depth) as compared to other two sites.Item Prediction of Local scour around bridge pier using Soft Computing Techniques(National Institute of Technology Karnataka, Surathkal, 2019) B. M, Sreedhara; Manu; Mandal, S.Bridges play an essential role in the society since they enable quick access across a river or any water body. Bridges facilitate transportation of goods and people and hence play a leading role in the development of a province. The safety of the bridge is the important factor with respect to scour failure which is the leading failure factor in river bridges. Scour is the removal of sediment near or around the structure which is located in the flowing water. There are different factors which affects scour mainly on the scour depth are flow depth, discharge, velocity, sediment size, porosity, pier shape and size etc. There are two types of scour conditions on which scour is classified and studied namely, clear water and live bed scour. The scour is the complex phenomenon and there is no common or general simple method to predict the scour depth around the bridge pier. There are several researchers who studied the scour mechanism using laboratory experiments. In the present days the artificial intelligence is the focal point for several researchers. Soft computing techniques, such as, Artificial Neural Network (ANN), Support Vector Machine (SVM), Adaptive Neuro-Fuzzy Inference System (ANFIS) and Particle Swarm Optimization (PSO) have been efficiently used for modeling scour related problems. The study used the data for developing the soft computing models, is obtained from a physical model study on scour depth around bridge pier, carried out by Goswami Pankaj in 2013 in a 2-D wave flume. The input parameters, namely, sediment size (d50), velocity (U), time (t) and sediment quantity (ppm) are used to predict the scour depth of different pier shapes such as circular, rectangular, round nosed and sharp nosed pier for both clear water and live bed scour condition. The complete original data is divided into training and testing. In the study, the soft computing techniques such as ANN, SVM, ANFIS, PSO-SVM and PSO-ANN are developed. The ANN model with feed-forward backpropagation network is developed with different hidden neurons. The RBF, Linear and Polynomial kernel functions are used in the SVM model. the ANFIS model is also developed with Trapezoidal, Gbell and Triangular membership function. The evolutionary optimization technique, particle swarm optimization is used to tune the SVM and ANN parameters to improve the efficiency of models prediction.ii The performance of individual and hybrid soft computing models are compared using statistical parameters such as, Correlation Coefficient (CC), Normalized Root Mean Square Error (NRMSE), Nash–Sutcliffe coefficient (NSE) and Normalized Mean Bias (NMB). Scatter plots are used to evaluate the accuracies of the models and box plots were used to analyze the spread or distribution of the data points estimated by the models. The validation of the developed models is done using the experimental values. The validation results shows that the proposed models are well correlated and in good agreement with experimental results. The hybrid models displayed a better performance compared to individual models. It is found that the hybrid PSO-SVM model is the best and efficient model in estimating the scour depth effectively around bridge pier for both live bed and clear water scour condition when compared to all the other models developed.Item Computational Intelligence in Prediction of Wave Transmission for Horizontally Interlaced Multi-layer Moored Floating Pipe Breakwater(National Institute of Technology Karnataka, Surathkal, 2013) Govind, Patil Sanjay; Hegde, Arkal Vittal; Mandal, SukomalEnergy dissipation process of Horizontally Interlaced Multi-layer Moored Floating Pipe Breakwater (HIMMFPB) depends on various factors like pipe interference effect, the spacing between the pipes and number of layers. As the effect of all these factors on transmission is not clearly understood, it will be extremely difficult to quantify them mathematically. Furthermore, it is a complex problem, and till now there has not been available a simple mathematical model to predict the wave transmission through HIMMFPB by considering all the boundary conditions, and hence one has to depend on physical model studies which are expensive and time consuming. Computational Intelligence (CI) techniques, such as, Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), Support Vector Machine Regression (SVMR), Genetic Programming (GP) and Genetic Algorithm (GA) have been efficaciously proposed as an efficient tool for modelling and predictions in coastal/ocean engineering problems. For developing CI models in prediction of wave transmission for HIMMFPB, data set were obtained from experimental wave transmission of HIMMFPB using regular wave flume at Marine Structure Laboratory, National Institute of Technology, Karnataka, Surathkal, Mangalore, India. These data sets are divided into two groups, one for training and other for testing. The input parameters that influence the wave transmission Kt of floating breakwater, such as, relative spacing to pipesS D, relative breakwater widthW L, ratio of incident wave height to water depthHi d, incident wave steepness Hi L are considered in developing CI models for prediction of wave transmission past HIMMFPB. In the present work, five layer pipes with S / D of 2, 3, 4 and 5 are considered. The ANN model is developed for prediction of wave transmission for HIMMFPB. Two network models, ANN1 and ANN2 are constructed based on the parameters which influence the wave transmission of floating breakwater. The input parameters of ANN1 model areW / L , Hi / d and Hi / L . To study over a range of spacing of pipesiv S / D on Kt , an input parameter, S / D is added to form ANN2 model. Training and testing of the network models are carried out for different hidden nodes and epochs. It is observed that the correlation (above 90%) between predicted wave transmission values by the network models and measured values are in good agreement. Furthermore, to improve the result of prediction of wave transmission of HIMMFPB, recently developed technique such as SVMR is used. This technique 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. Support vector machines (SVMs) are based on statistical learning theory. The basic idea of support vector machines is to map the original data x into a feature space with high dimensionality through a non-linear mapping function and construct an optimal hyper-plane in new space. Six SVMR models are constructed using kernel functions. In order to study the performance of each kernel in predicting wave transmission of HIMMFPB, SVMR is trained by applying these kernel functions. Performance of SVMR is based on the best setting of SVMR and kernel parameters. Correlation Coefficient (CC) of SVMR (b-spline) model (CC Train = 0.9779 and CC Test = 0.9685) is considerably better than other SVMR models. However, it is noticed that ANN model in isolation cannot capture all data patterns easily. Adaptive neuro-fuzzy inference system (ANFIS) uses hybrid learning algorithm, which is more effective than the pure gradient decent approach used in ANN. ANFIS models are developed to predict wave transmission of HIMMFPB. The performance of the ANFIS models in the prediction of Kt is compared with the measured values using statistical measures, such as, CC, Root mean Square Error ( RMSE ) and Scatter Index ( SI ). All the ANFIS models have shown CCs higher than or equal to 0.9510, with RMSE less than or equal to 0.051074 and SI less than or equal to 0.102296. ANFIS5 model predictions are very realistic when compared with the measured values (CC Train = 0.9723, CC Test = 0.9635). It is also observed that an S D plays an important role to train ANFIS5 model to map an input-output relation. Furthermore influence of input parameters is assessed using Principalv Component Analysis (PCA). It is observed that Hi / L is the least influential parameter Based on the PCA study discarding the least influential parameters, ANFIS6 model is developed. It is observed that the ANFIS models yield higher CCs as compared to that of ANN models. To improve the performance of SVMR and better selection of SVMR and kernel parameters, hybrid genetic algorithm tuned support vector machine regression (GASVMR) model is developed to predict wave transmission through HIMMFPB. Furthermore, parameters of both linear and nonlinear SVM models are determined by GA. The results are compared with ANN, SVMR and ANFIS models in terms of CC, RMSE and SI . Performance of GA-SVMR is found to be reliably superior. CI models can be utilized to provide a fast and reliable solution in prediction of the wave transmission for HIMMFPB, thereby making GA-SVMR as an alternate approach to map the wave structure interactions of HIMMFPB.Item Water Quality Assessment in Distribution System Using Artificial Intelligence(National Institute of Technology Karnataka, Surathkal, 2014) Krishnaji, Patki Vinayak; Shrihari, S.; Manu, B.In this study various artificial intelligence techniques have been compared for assessment and prediction of water quality in various zones of municipal distribution system using six physico-chemical characteristics viz. pH, alkalinity, hardness, dissolved oxygen (DO), total solids (TS) and most probable number (MPN). Fuzzy expert system, artificial neural network (ANN) and adaptive neuro fuzzy inference system (ANFIS) were used for the comparative study. The proposed expert system includes a fuzzy model consisting of IF-THEN rules to determine WQI based on water quality characteristics. The fuzzy models are developed using triangular and trapezoidal membership functions with centroid, bisector and mean of maxima (MOM) methods for defuzzification. In ANN method the cascade feed forward back propagation (CFBP) and feed forward back propagation (FFBP) algorithms were compared for prediction of water quality in the municipal distribution system. The comparative study was carried out by varying the number of neuron (1-10) in the hidden layer, by changing length of training dataset and by changing transfer function. ANFIS models are developed by using triangular, trapezoidal, bell and Gaussian membership function. Further, these artificial intelligence techniques are compared with multiple linear regression technique, which is the commonly used statistical technique for modelling water quality variables. The study revealed that artificial neural network (ANN) outperforms other modelling techniques and is a robust tool for understanding the poorly defined relations between water quality variables and water quality index (WQI) in municipal distribution system. This tool could be of great help to the distribution system operator and manager to find change in WQI with changes in water quality varibles.Item Damage Level Prediction of NonReshaped Berm Breakwater using Soft Computing Techniques(National Institute of Technology Karnataka, Surathkal, 2014) N, Harish.; Rao, Subba; Mandal, SukomalTranquility condition inside the port and harbor has to be maintained for loading cargo and passengers. In order to maintain calm condition inside the port and harbor, breakwater has to be constructed to dissipate wave energy that is coming inside. The alignment of the breakwater must be carefully considered after examining the predominant direction of approach of waves and winds, degree of protection required, magnitude and direction of littoral drift and the possible effect of these breakwaters on the shoreline. In general these studies are invariably conducted in a physical model test where various alternatives are studied and the final selection will be based on performance consistent with cost. Considering the coastal boundary and depth variation, field analysis of wave structure interaction, determination of stability and damage level of berm breakwater structure is difficult. Mathematical modeling of these complex interactions is difficult while physical modeling will be costly and time consuming. Hence one has to depend on physical model studies which are expensive and time consuming. Soft computing techniques, such as, Artificial Neural Network (ANN), Support Vector Machine (SVM),Adaptive Neuro-Fuzzy Inference System (ANFIS) and Particle Swarm Optimization (PSO) have been efficiently proposed as a powerful tool for modeling and predictions in coastal/ocean engineering problems. For developing soft computing models in prediction of damage level of non-reshaped berm breakwater, data set are obtained from experimental damage level of non-reshaped berm breakwater using regular wave flume at Marine Structure Laboratory, National Institute of Technology, Karnataka, Surathkal, Mangalore, India. These data sets are divided into two groups, one for training and the other for testing. The input parameters that influence the damage level (S) of nonreshaped berm breakwater, such as, relative wave steepness (H/L0), surf similarity (ζ), slope angle (cotα) relative berm position by water depth (hB/d), relative armour stone weight (W50/W50max), relative berm width (B/ L0) and relative berm location (hB/L0) are considered in developing soft computing models for prediction damage level. The ANN model is developed for the prediction of damage level of non-reshaped berm breakwater. Two network models, ANN1 and ANN2 are constructed based on the parameters which influence the damage level of non-reshaped berm breakwater. The seven input parameters that are initially considered for ANN1 model are (H/L0), (ζ), (cotii α), (hB/d), (W50/W50max), (B/ L0) and (hB/L0). The ANN1 model is studied with different algorithm namely, Scaled Conjugate Gradient (SCG), Gradient Descent with Adaptive learning (GDA) and Levenberg-Marquardt Algorithm (LMA) with five numbers of hidden layer nodes and a constant 300 epochs. LMA showed good performance than the other algorithms. Also, influence of input parameters is evaluated using Principal Component Analysis (PCA). From PCA study, it is observed that cotα is the least influencing parameter on damage level. Based on the PCA study, least influencing parameter is discarded and ANN2 model is developed with remaining six input parameters. Training and testing of the ANN2 network models are carried out with LMA for different hidden layer nodes and epochs. The ANN2 with LMA 6-5-1 with 300 epochs gave good results. It is observed that the correlation of about 88% between predicted and observed damage level values by the ANN2 network models and measured values are in good agreement Furthermore, to improve the result of prediction of damage level of non-reshaped berm breakwater, SVM model was developed. This technique 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. This model was developed based on statistical learning theory. The basic idea of SVM is to map the original data x into a feature space with high dimensionality through a nonlinear mapping function and construct an optimal hyper-plane in new space. SVM models were constructed using different kernel functions. In order to study the performance of each kernel in predicting damage level of non-reshaped berm breakwater, SVM is trained by applying these kernel functions. Performance of SVM is based on the best setting of SVM and kernel parameters. Correlation Coefficient (CC) of SVM (polynomial) model (CC Train = 0.908 and CC Test = 0.888) is considerably better than other SVM models. To avoid over-fitting or under-fitting of the SVM model due to the improper selection of SVM and kernel parameters and also the performance of SVM, hybrid particle swarm optimization tuned support vector machine regression (PSO-SVM) model is developed to predict damage level of non-reshaped berm breakwater. The performance of the PSOSVM models in the prediction of damage level is compared with the measured values using statistical measures, such as, CC, Root mean Square Error (RMSE) and Scatteriii Index (SI). PSO-SVM model with polynomial kernel function gives realistic prediction when compared with the observed values (CC Train = 0.932, CC Test = 0.921). It is observed that the PSO-SVM models yield higher CCs as compared to that of SVM models. However, it is noticed that ANN model in isolation cannot capture all data patterns easily. Adaptive Neuro-Fuzzy Inference System (ANFIS) uses hybrid learning algorithm, which is more effective than the pure gradient decent approach used in ANN. ANFIS models were developed with different membership namely Triangular-shaped built-in membership function (TRIMF), Trapezoidal-shaped built-in membership function (TRAPMF), Generalized bell-shaped built-in membership function (GBELLMF), and Gaussian curve built-in membership function (GAUSSMF) to predict damage level of non-reshaped berm breakwater. The performance of the ANFIS models in the prediction of damage level is compared with the measured values using statistical measures, such as, CC, RMSE and SI. ANFIS model with GAUSSMF gave realistic prediction when compared with the observed values (CC Train = 0.997, CC Test = 0.938). It is observed that the ANFIS models yield higher CCs as compared to that of ANN models. The different soft computing models namely, ANN, SVM, PSO-SVM and ANFIS results are compared in terms of CC, RMSE, SI and computational time. The hybrid models in both (ANFIS and PSO-SVM) cases showed better results compared to individual models (ANN and SVM). When the hybrid models are compared, ANFIS model gives higher CC and lower RMSE. But considering computational time, ANFIS has taken more time than PSO-SVM model. Hence PSO-SVM is computationally efficient as compared to ANFIS. ANFIS and PSO-SVM models perform better and similar to observed values. Hence, ANFIS or PSO-SVM can replace the ANN, SVM for damage level prediction of nonreshaped berm breakwater. ANFIS or PSO-SVM can be utilized to provide a fast and reliable solution in prediction of the damage level prediction of non-reshaped berm breakwater, thereby making ANFIS or PSO-SVM as an alternate approach to map the wave structure interactions of berm breakwater.Item Modeling Of Air Temperature Using Hybrid Wavelet Transform - ANFIS - Support Vector Machine Computing Techniques(National Institute of Technology Karnataka, Surathkal, 2016) B. S, Karthika; Deka, Paresh ChandraThe accurate modeling of average air temperature is a significant and much essential parameter in frame of reference for decision-making. Therefore, the characterization of such parameter is an important task. The information about the air temperature also helps in planning and management of water resources, irrigation, drought detection, tourism, health and issues of day to day life. In this study, a hybrid model consists of Wavelet - ANFIS has been developed for air temperature modeling. The results are compared with Wavelet - SVM, single ANFIS, and single SVM to confirm the superiority of the proposed model. To model average air temperature, ANFIS models were developed with different membership, namely generalized bell-shaped built-in membership function (GBELLMF), and Gaussian curve built-in membership function (GAUSSMF). Additionally, to check the result of modeling of average air temperature, SVM model was developed. To enhance the accuracy of modeling performance, single ANFIS and single SVM is integrated along with wavelet transformations were tested. Here wavelet transformation was used as pre-processing the data by capturing valuable information on various resolution levels. This study extends for seven stations in Karnataka state of India (Shimoga station, Raypura station, Linganmakki station, Honnali station, Hiriyur station, Bhadra station (B. R. Project) and Davanagere station) observed data of meteorological data like rainfall, wind speed, humidity and sunshine hour as input and as target average air temperatures are used for all the models. In the next phase, the influence of air pollutants along with the meteorological parameters has been investigated for average air temperature modeling for a specific Bhadra station in Karnataka state, India, which is near to industrial city. The obtained results were evaluated using Correlation Coefficient, Root Mean Square Error and Scatter Index. The performance of ANFIS, SVM, hybrid Wavelet - ANFIS and hybrid Wavelet - SVM is analyzed for modeling of average air temperature. Out of seven stations, station Linganamakki showed better performance with CC of 0.954, RMSE is 0.71and SI is 0.027 with hybrid Wavelet- ANFIS model (Gbell membership). Also for single Bhadra station, Hybrid Wavelet - ANFIS model with the parameter combinationiv (rainfall, wind speed, humidity, sunshine hour) for Db5 with level4 (2MF) and Gauss membership function is having the results of CC is 0.98, which is best in case of accuracy. The study reveals the higher accuracy of hybrid Wavelet - ANFIS in modeling air temperature for various meteorological and air pollutants input scenarios.Item Short-term Offshore Wind Speed Forecasting using Buoy Observations and Regional scale Wind Resource Assessment based on Scatterometer Data(National Institute of Technology Karnataka, Surathkal, 2016) Gadad, Sanjeev; Deka, Paresh ChandraOffshore winds are valuable source of renewable energy. To recognize the potential of area it is essential to assess the available resource and understand the sporadic nature of winds. Wind Resource Assessment (WRA) coupled with short-term forecast of winds will aid in establishing the confidence for undertaking offshore wind farm development. Wind speed forecasting is important for estimating power generation capacity of turbines. The knowledge of availability of the winds in future time steps will be pivotal in planning and improving the efficiency of energy production. Buoys are the fundamental source of in situ atmospheric parameter observations. One of the primary objectives of the present research is to determine suitable technique for short-term forecasting of offshore winds. So, the present study focuses on assessing accuracy of the ANFIS hybrid model for short-term wind speed forecasting. In addition, the Arabian Sea belongs to tropical humid climate zone and therefore the influence of Relative Humidity (RH) on the ANFIS model to estimate offshore wind speed was investigated. In the study, two buoys with id– AD07 and CB02 apart approximately by 500 km were selected. Two models (model 1: 5 inputs, 1 output and model 2: 4 inputs, 1 output) and two scenarios (scenario 1: estimate wind speeds and scenario 2: forecasting wind speeds) were developed for the study. From scenario 1, it was found that at both the buoy locations the model 1 outperformed model 2 in estimating observed wind speeds and RH had noticeable influence on the model performance. Persistence Method (PM) was chosen as base method for comparing the wind speed forecasts. From scenario 2, at AD07, model 1 forecasts were accurate than other two models and at CB02, the PM forecasts were most accurate. However, it was found that the model 1 forecasts at CB02 were closer to PM. Altogether, the model 1 performance was higher than model 2 indicating the error in forecasts due to absence of RH observations. The study concludes that the model performance was enhanced by incorporating RH observations as an input to the ANFIS model. The RMSE of forecasted wind speeds up to three time steps, at AD07 and CB02 would be approximately lower by 37% and 14% respectively.ii Further, the study examines the performance of ANFIS and Wavelet-ANFIS (WT+ANFIS) hybrid techniques to forecast wind speeds for multiple time steps at the same buoy locations (AD07 and CB02) in the Arabian Sea. The forecast accuracy of ANFIS and WT+ANFIS were compared with PM. The RMSE for the testing dataset at AD07 and CB02 using ANFIS model was found to be 1.3 m s-1 and 1.26 m s-1 for 1st (t+1) time step respectively. The RMSE for WT+ANFIS model at AD07 and CB02 was obtained as 1.5 m s-1 and 1.20 m s-1 for 1st (t+1) time step respectively. It was observed at CB02, the WT+ANFIS model forecast was closest to PM. At AD07, an ANFIS and WT+ANFIS model performance was almost similar and found to be better than PM. In general, the WT+ANFIS model outperformed ANFIS and PM for multiple time steps. Thus, the analysis establishes that WT+ANFIS hybrid method has the potential to be a complementary tool in obtaining short-term offshore wind speed forecasts. In the offshore region the scarcity of in situ wind data in space proves to be a major setback for wind power potential assessments. Satellite data effectively overcomes this setback by providing continuous and total spatial coverage. The satellite data needs to be validated at the study area before conducting WRA study. Hence the work centers on estimating the performance of Oceansat–2 scatterometer (OSCAT)– derived wind vector using in situ data from buoys (id– AD02 and CB02) at different locations in the Arabian Sea. For the validation of OSCAT winds, the buoy winds are required to be extrapolated to height of 10 m and are known as Equivalent Neutral Winds (ENW). A comparative study among three methods- power law, logarithmic and Liu– Katsaros–Businger (LKB) method for estimating the ENW for buoys is carried out. OSCAT winds were closest to ENW estimated by the Liu–Katsaros–Businger (LKB) method. The spatial and temporal windows for comparison were 0.5° and ±60 minutes, respectively. The monsoon months (June–September) of 2011 were selected for the study. The root mean square deviation for wind speed is less than 2.5 m s−1 and wind direction is less than 20°, and a small positive bias is observed in the OSCAT wind values. From the analysis, the OSCAT wind values were found to be consistent with in situ-observed values. Furthermore, wind atlas maps were developediii with OSCAT winds, representing the spatial distribution of winds at a height of 10 m over the Arabian Sea. Satellite-based regional scale offshore wind power resource assessment was carried out for the Karnataka state, which is located on the west coast of India. OSCAT wind data and GIS based methodology were adopted in the study. The real time ship based observations is considered in the present work, to assess the accuracy of OSCAT wind data. The INCOIS Realtime All Weather Station (IRAWS) data provides greater spatial coverage than conventional buoy setup. Probably, this is the first attempt to validate OSCAT data using IRAWS dataset, which offered greater number of collocated observation points and hence provided better assessment. Wind speed maps at 10 m, 90 m and wind power density maps using OSCAT data were developed to understand the spatial distribution of winds over the study area. Bathymetric map was developed based on the available foundation types and demarking various exclusion zones to help in minimizing conflicts. The wind power generation capacity estimation performed using REpower 5 MW turbine, based on the water depth classes was found to be 9,091 MW in Monopile (0-35 m), 11,709 MW in Jacket (35-50 m), 23,689 MW in Advanced Jacket (50-100 m) and 117,681 MW in Floating (100-1000 m) foundation technology. In Indian scenario, major thrust may be given for wind farm development in Monopile region. Therefore, as first phase of development for 10% of the estimated potential in this region, 116% of energy deficit for FY 2011-12 could be met. Also, up to 79% of the anticipated energy deficit for the FY 2014-15 of the Karnataka state of India could be achieved.Item Modeling reference evapotranspiration using hybrid artificial intelligence techniques in arid and semi-arid regions of India(National Institute of Technology Karnataka, Surathkal, 2017) Patil, Amit Prakash; Deka, Paresh ChandraEvapotranspiration (ET) plays an important role in efficient crop water management. Accurate estimation of ET is a challenging task in developing countries like India, where the availability of meteorological data is often minimal. This study makes an attempt to evaluate the potential and applicability of hybrid Wavelet-Artificial Intelligence (AI) models for estimating reference crop evapotranspiration (ETo) in arid and semi-arid regions of India. The hybrid models were developed by using wavelet decomposed subseries of meteorological variables as inputs to the ANN, ANFIS and LS-SVM models. Performance of the proposed hybrid models was then compared to the classical AI models. The study used forty year weekly dataset from Jodhpur and Pali (arid region) weather station. Also, daily data for six years were obtained from Hyderabad and Kurnool weather station (semi-arid region). In absence of lysimeter data, ETo values are calculated by FAO-56PM equation. Prior to the development of models, factor analysis test was employed to identify the input combination that may yield more efficient model under limited data scenario. Additionally, the effectiveness of using ETo data from another station in the same climatic region (extrinsic data) was also evaluated. It is expected that the proposed hybrid models together with extrinsic input variables would provide efficient ETo estimation models. The performance of hybrid and classical AI models were compared using RMSE, NSE and threshold statistics. Scatter plots were used to evaluate the accuracies of the models and box plots were used to analyze the spread of the data points estimated by the models. The results show that the proposed AI models worked better at estimating weekly ETo in arid regions compared to estimating daily ETo in semi-arid regions. The hybrid AI models displayed a better performance compared to the classical AI models at all the stations. It was found that hybrid W-LSSVM was the best model for estimating ETo in both arid and semi-arid region. Further, it was observed that the use of extrinsic inputs delivered good results only in arid regions. It was also observed that in semi-arid regions, use of wavelet decomposed extrinsic data deteriorated the performance of some hybrid models.