Browsing by Author "Srinivasa Pai, P."

Now showing 1 - 7 of 7

Efficient modelling and simulation of wind power using online sequential learning algorithm for feed forward networks
(Bangladesh University of Engineering and Technology, 2019) Shetty, R.P.; Sathyabhama, A.; Srinivasa Pai, P.
In this paper, an online sequential learning algorithm known as online sequential extreme learning machine (OS ELM) is applied to simulate the power output of a wind turbine. The OS ELM is used both in 1-by-1 and chunk-by-chunk mode and the results are compared with batch learning algorithms, namely Back Propagation (BP) and Extreme Learning Machine (ELM) algorithm. Different activation functions such as Sigmoidal, Sin, Radial Basis Function (RBF) and Hardlim have been used in OS ELM to decide upon most optimal function. It has been found that OS ELM with fixed chunk size of 50-by-50 and sigmoidal activation function with training time of 0.080s, Root Mean Square Error (RMSE) of 1.96%, prediction accuracies on training and test data of 100% and 99.95 % respectively, is best suited for wind power modelling and simulation applications, where the data arrives in a sequential manner. © 2019 Bangladesh University of Engineering and Technology.All rights reserved.
Enhancing the surface integrity characteristics of Al-Li alloy using face milling
(Elsevier B.V., 2022) Marakini, V.; Srinivasa Pai, P.; Udaya Bhat, K.; Thakur, D.S.; Achar, B.P.
This work presents the milling induced surface integrity investigation of Al-Li alloy. The effect of milling on the surface roughness, microhardness, microstructure, and residual stress is studied. Uncoated carbide inserts are used for milling due their superior hardness and greater life, when machining softer materials such as aluminium and its alloys. Results show that the minimum surface roughness (Ra = 0.043 µm) and maximum microhardness (216 HV) are achievable from the milling process, when compared with the roughness (Ra = 0.528 µm) and microhardness (180 HV) of the as-received material. Results indicate limited harm to alloy microstructure from the milling process and the presence of compressive residual stress induced from milling. The work finds scope for aerospace applications. © 2022 Elsevier B.V.
High Speed Machining for Enhancing the AZ91 Magnesium Alloy Surface Characteristics: Influence and Optimisation of Machining Parameters
(Defense Scientific Information and Documentation Centre, 2022) Marakini, V.; Srinivasa Pai, P.; Udaya Bhat, K.; Thakur, D.S.; Achar, B.P.
In this study, optimum machining parameters are evaluated for enhancing the surface roughness and hardness of AZ91 alloy using Taguchi design of experiments with Grey Relational Analysis. Dry face milling is performed using cutting conditions determined using Taguchi L9 design and Grey Relational Analysis has been used for the optimisation of multiple objectives. Taguchi’s signal-to-noise ratio analysis is also performed individually for both characteristics and grey relational grade to identify the most influential machining parameter affecting them. Further, Analysis of Variance is carried to see the contribution of factors on both surface roughness and hardness. Finally, the predicted trends obtained from the signal-to-noise ratio are validated using confirmation experiments. The study showed the effectiveness of Taguchi design combined with Grey Relational Analysis for the multi-objective problems such as surface characteristics studies. © 2022, DESIDOC
Influence of milling parameters on Al-Li alloy surface characteristics
(Elsevier Ltd, 2023) Marakini, V.; Srinivasa Pai, P.; Udaya Bhat, K.; Thakur, D.S.; Achar, B.P.
Lightweight alloys attract the aerospace industries due to their high specific strength. Al-Li alloy has been investigated in the present study to identify their functional performance in terms of surface characteristics namely surface roughness and hardness. Dry face milling was performed using uncoated carbide inserts for the experimental conditions obtained from Taguchi L27 design of experiments. The effect of milling parameters, such as feed rate, cutting speed and depth of cut on surface roughness and hardness have been investigated and presented. Further, the optimal milling conditions are identified using statistical techniques â€“ Grey Relational Analysis (GRA) and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS). The study showed that feed rate is the most influential parameter on both surface characteristics. Both GRA and TOPSIS showed similarity in identifying the same condition as optimal for milling Al-Li alloy under dry condition. Â© Â© 2023 Elsevier Ltd. All rights reserved.
Surface Roughness Prediction in High Speed Turning of Ti-6Al-4V: A Comparison of Techniques
(Institute of Physics Publishing helen.craven@iop.org, 2018) D'Mello, D.; Srinivasa Pai, P.; Puneet, N.P.
Surface finish of machined products is important and plays an important role in ascertaining its quality and other attributes. Surface roughness of difficult to machine materials like titanium alloys are difficult to model due to several factors influencing it. This study makes an attempt to compare the performance of a statistical technique, Response Surface Methodology (RSM) and two Artificial Neural Network (ANN) techniques namely Multi Layered Perceptron (MLP) and Radial Basis Function Neural Network (RBFNN) to model and predict the surface roughness parameters Ra and Rt in high speed turning of Ti-6Al-4V. Experiments have been carried out using uncoated carbide inserts under dry condition. The input parameters for the modeling studies include cutting speed, feed rate and depth of cut. This work also makes use of tool wear and cutting tool vibration (Vy) which are uncontrollable parameters as the inputs for modeling studies. The ANOVA analysis has revealed that feed rate and cutting tool vibrations are the most significant parameters affecting Rt and cutting speed and vibrations affect Ra. A comparison between the modeling techniques revealed that RBFNN performed better in terms of prediction accuracy when compared to MLP and RSM. Â© Published under licence by IOP Publishing Ltd.
Wind Power Optimization: A Comparison of Meta-Heuristic Algorithms
(Institute of Physics Publishing helen.craven@iop.org, 2018) Shetty, R.P.; Sathyabhama, A.; Srinivasa Pai, P.
The wind being a most promising renewable energy, has become a strong contender for fossil fuels. Optimizing the blade pitch angle of a wind turbine is important to obtain the maximum power output, as the other variables are considered to be uncontrollable. In this paper an effort has been made to compare performances of three different optimization algorithms namely Particle swarm optimization (PSO), Artificial bee colony (ABC) and cuckoo search (CS) for optimizing the blade pitch angle and hence optimize the power output of a 1.5 MW capacity, pitch regulated, three-bladed horizontal axis wind turbine operating at a large wind farm in central dry zone of Karnataka. The objective function development is done using Artificial Neural Network. The CS algorithm is found to be faster and more efficient as compared to ABC and PSO for the problem under consideration. Â© Published under licence by IOP Publishing Ltd.
Wind speed forecasting in different seasons using ELM batch learning algorithm in Indian context
(Science Publishing Corporation Inc ijet@sciencepubco.com, 2018) Shetty, R.P.; Sathyabhama, A.; Srinivasa Pai, P.; Ranjith Shetty, K.
Efficient wind speed forecasting is important for wind energy sector for better wind power integration. This paper focuses on developing seasonal wind speed forecasting models in Indian context. Wavelet transform (WT) technique has been used for denoising the data obtained from supervisory control and data acquisition (SCADA) of a 1.5 MW wind turbine located in central dry zone of Karnataka, to reduce the unnecessary fluctuations in the wind speed time series. Partial auto correlation function (PACF) has been used for selection of input parameters, which greatly influences the forecasting accuracy. Forecasting models have been developed using a fast and efficient extreme learning machine (ELM) algorithm. The results have been compared with conventional back propagation (BP) algorithm. The results show that the seasonal models developed using ELM have better forecasting performance compared to BP. © 2018 Authors.