Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
8 results
Search Results
Item Brushless DC hub motor drive control for electric vehicle applications(Institute of Electrical and Electronics Engineers Inc., 2020) Vishnu Sidharthan, P.; Kashyap, Y.Global warming, air pollution and sound pollution are major environmental problems faced by today's world. Environmental pollution and increasing cost of fuels had led to the importance of using alternate sources for transportation since Internal combustion (IC) engine vehicles carries more than 40% of the pollution. Battery electric vehicles (BEV) is an alternative which received high attention in transportation industry. This paper focus on the control of Brushless DC (BLDC) motor which is used to drive the Electric two-wheeler. Hardware implementation of the motor is developed and an Atmega 328 microcontroller is utilized to control the motor which is provides a speed control with current commutation. A 60V, 1000W BLDC hub Motor is used to meet the drive requirements. The mathematical modeling of BLDC motor is discussed with the mathematical equations. MATLAB Simulation is developed, and the closed loop speed control is done in Simulink. PWM pulses generated from the MCU as per the commutation sequence and loaded to control the switches of 3-phase inverter and in response to the driver inputs (start/stop, accelerator, brake) the motor speeds are dynamically varied. © 2020 IEEE.Item Airborne Manoeuvre Tracking Device for Kite-based Wind Power Generation(Springer Science and Business Media Deutschland GmbH, 2021) Castelino, R.V.; Kashyap, Y.Airborne wind technology eliminates the structure costs and reaches higher altitudes for extracting the power from stronger winds. The main objective is to perform the aerodynamic test on the airfoil kite with lightweight, low-power wireless devices for better data reception. The kite maneuvers in eight shapes to deliver maximum power; therefore, the positioning device has to be low powered, low weight, and weatherproof, to avoid indeterminacy in airfoil flight at 200–300 m altitude. The device consists of ultra-low-power TI CC1310 SimpleLink Sub-1Ghz wireless Microcontroller Unit (MCU), GPS Sensor, Inertial Measurement Unit (IMU) to find the speed, direction, longitude, latitude, and altitude, roll, pitch, and yaw at the ground station, for controlling the tethered wings autonomously. The base station receives data at 868 MHz optimum frequency at 50 kbps data rate; the optimized frequency is estimated using a virtual toolbox and a field test. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.Item Intelligent Power Allocation Strategy of Hybrid Source System in Solar Electric Vehicle(Institute of Electrical and Electronics Engineers Inc., 2022) Vishnu Sidharthan, P.; Kashyap, Y.Technological developments in Battery electric vehicles (BEV) gains the utmost attention in recent transportation scenarios. Internal Combustion Engine (ICE) vehicles are facing several issues due to their effects on the environment, fuel cost, and availability. This shifts the automotive trends towards Electric Vehicles (EV). However, BEV faces few problems on range anxiety and battery life depletion for varying driving conditions. Supercapacitor (SC) coupled with batteries is the right solution for these rising problems. This paper focuses on the energy management of a battery-SC Hybrid Source System for a Solar Electric Vehicle (SEV). SC handles sudden power variations during varying driving load demands and solar irradiance. The proposed fuzzy logic power allocation strategy achieves improved battery life, source performances, and reduced battery peak currents for different driving and environmental factors. MATLAB/Simulink simulation results verify the significance of the integration of SC by reducing the battery stresses. The proposed strategy improves the battery longevity by 43% and 20% compared to BEV and hybrid conventional strategy respectively for a Worldwide Harmonized Light-duty Vehicles Test Procedure (WLTP) driving profile. Different driving conditions are considered in this work with varying driving and environmental conditions to prove the effectiveness of the proposed strategy. © 2022 IEEE.Item Ensemble RDLR Architecture for Short-Term Solar Power Forecasting(Institute of Electrical and Electronics Engineers Inc., 2024) Ayappane, H.; Kashyap, Y.Given the drastic shift of global sentiment towards renewable energy, it becomes incredibly important to match supply with demand. However the highly variable nature of weather makes it difficult to accurately predict the output of a solar power plant. Through this paper, we will approach this problem by using an ensemble model consisting of both machine learning and neural networks (NN) as base models to forecast the amount of energy that needs to be produced by a solar plant over a short-term time horizon, which in our case will be 0 minute (immediate), 5 minute, 30 minute and 90 minute. Each base model is fine tuned to encourage high diversity and low correlation to improve prediction accuracy. The expected stability or generalization from RF-DNN combined with the memory retention capability of the LSTM network should provide an ideal predictor for time series forecasting of a stochastic process like weather. © 2024 IEEE.Item Cloud Classification in Sky Images using Deep Neural Networks(Institute of Electrical and Electronics Engineers Inc., 2024) Archit; Kumar, A.; Kashyap, Y.In this research endeavor, a thorough analysis of a 10-minute sky video sequence was conducted. The study commenced by extracting frames at a consistent rate of 30 frames per second, resulting in a dataset of 1200 cloud images. Following frame extraction, color image segmentation was applied to identify distinct color regions within each frame.The primary goal was to estimate the percentage of cloudy pixels within each frame. To achieve this, three pre-trained Convolutional Neural Network (CNN) models namely - VGG16, MobileNetV2, and ResNet50 - were employed for cloud detection and pixel classification. This three-model approach contributed to a comprehensive assessment of cloud cover in the images. Cloudy pixel percentage was calculated using both area-based and pixel count-based approaches, adding depth to the analysis. This holistic approach provided a nuanced perspective on cloud cover dynamics, with the results shedding light on the evolution of cloud cover over the video's duration.The report meticulously outlines the methodology employed, encompassing data preprocessing techniques, feature extraction, and model training parameters. It presents the findings of the classification process, including accuracy and performance metrics, and discusses insights gained from the analysis of results. This paper contributes to the scientific discourse by presenting a comprehensive framework for cloud analysis in video sequences, with practical implications for a range of disciplines. © 2024 IEEE.Item Machine Learning and Thresholding Approach for Defects Classification in Solar Panels(Springer Science and Business Media Deutschland GmbH, 2025) Abhishek, G.H.; Kumar, A.; Kashyap, Y.This research addresses critical aspects of solar photovoltaic (PV) system maintenance and monitoring to ensure sustained performance. Emphasizing solar panel reliability, the study employs image processing, clustering algorithms, and machine learning (K-Means, Naive Bayes) to detect and categorize factors impacting efficiency, such as dust accumulation and sunlight exposure. The developed system facilitates comprehensive assessment and classification, enhancing operational lifespan. Demonstrating versatility, the project incorporates alternative feature extraction and interactive threshold selection, ensuring adaptability to diverse scenarios. Experimental validation, including hotspot detection in thermal images, underscores the robustness of the proposed methodology, contributing significantly to solar panel monitoring and maintenance advancements. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.Item Enhancing High-Frequency PV Power Forecast Using Optimal Hyperparameter Setting in LSTM(Springer Science and Business Media Deutschland GmbH, 2025) Kumar, A.; Kashyap, Y.; Nasar, R.Solar energy plays a significant role in the world’s shift to renewable and sustainable energy. So, accurate forecasting techniques are essential for effective grid management and smooth integration into current energy infrastructures. Traditional solar forecasting approaches often encounter limitations in capturing the complex and nonlinear relationships inherent in solar power generation patterns. In response to these challenges, the present paper demonstrates the forecast analysis of high-frequency (HF) PV power components, which is obtained with the decomposition of actual PV power data. The focus of this paper is on the analysis of high-frequency PV power components as they exhibit high fluctuation. To capture this high fluctuation feature present in PV power, a moving average filter is applied to smooth the input data and potentially enhance the 60 min ahead forecasting performance using the long short-term memory (LSTM) model. The best-performing LSTM model has secured MAE= 1.114 % and RMSE = 2.608 % for 60 min ahead forecast. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.Item An Improved ResNet-50 Neural Network Design for PV Panel Image Classification(Springer Science and Business Media Deutschland GmbH, 2025) Kumar, A.; Kashyap, Y.; Sharma, A.The increasing popularity of photovoltaic (PV) setups stems from their capacity to generate clean and cost-effective electricity. However, various factors can either totally or partially disrupt the production of PV panels. To address this challenge, this study proposes a ResNet-50 model with dynamically adjusted hyperparameters to classify real-time captured images of PV panels into efficient and non-efficient categories. The hyperparameter tuning within the ResNet-50 model is conducted across three distinct cases, revealing that the most optimal classification results are achieved with the following settings: 50 epochs, a learning rate of 0.001, and a batch size of 32. The highest weighted average metrics, including accuracy (96%), recall (96%), precision (97%), and F1-score (96%), were obtained under these settings. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.