Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
5 results
Search Results
Item A novel nine-level boost inverter with a low component count for electric vehicle applications(John Wiley and Sons Ltd, 2021) Shiva Naik, B.S.; Yellasiri, Y.; Aditya, K.; Nageswar Rao, B.N.In electric vehicles (EVs), considerable battery cells are cascaded in series for motor driving to improve the output voltage. The series combination of battery cells causes challenges like isolation of faulty cells, voltage unbalance, and slow charge equalization. Therefore, state-of-charge (SOC) and voltage equalization circuits are often used in industries to protect the battery cells. A nine-level inverter circuit with a double voltage boost is proposed to reduce the above issues based on the switch-capacitor (SC) principle. Unique features like self-balancing, voltage boosting are attained, which cannot be achieved through traditional inverters. The proposed topology can operate at a wide range of modulation indices ((Formula presented.)) to produce different voltage levels. The absence of a back-end H-bridge in the proposed circuit offers low voltage stress across the semiconductors. The operating principle, capacitor sizing, and modulation approach are presented. Further, experimental tests are conducted at different loading conditions to verify the performance of the proposed circuit. © 2021 John Wiley & Sons Ltd.Item Solar Photovoltaic Hotspot Inspection Using Unmanned Aerial Vehicle Thermal Images at a Solar Field in South India(MDPI, 2023) Umesh, P.; Kashyap, Y.; Baxevanaki, E.; Kosmopoulos, P.The sun is an abundant source of energy, and solar energy has been at the forefront of the renewable energy sector for years. A way to convert it into electricity is by the use of solar cells. Multiple solar cells, connected to each other, create solar panels, which in their turn, are connected in a solar string, and they create solar farms. These structures are extremely efficient in electricity production, but also, cells are fragile in nature and delicate to environmental conditions, which is the reason why some of them show discrepancies and are called defective. In this research, a thermal camera mounted on a drone has been used for the first time in the solar farm operating conditions of India in order to capture images of the solar field and investigate solar panels for defective cells and create an orthomosaic image of the entire area. This procedure next year will be established on an international scale as a best practice example for commercialization, providing effortless photovoltaic monitoring and maintenance planning. For this process, an open source software WebODM has been used, and the entire field was digitized so as to identify the location of defective panels in the field. This software was the base in order to provide and analyze a digital twin of the studied area and the included photovoltaic panels. The defects on solar cells were identified with the use of thermal bands, which record and point out their temperature of them, whereas anomalies in the detected temperature in defective solar cells were captured using thermal electromagnetic waves, and these areas are mentioned as hotspots. In this research, a total number of 232.934 solar panels were identified, and 2481 defective solar panels were automatically indicated. The majority of the defects were due to manufacturing failure and normal aging, but also due to persistent shadowing and soiling from aerosols and especially dust transport, as well as from extreme weather conditions, including hail. The originality of this study relies on the application of the proposed under development technology to the specific conditions of India, including high photovoltaic panels wear rates due to extreme aerosol loads (India presents one of the highest aerosol levels worldwide) and the monsoon effects. The ability to autonomously monitor solar farms in such conditions has a strong energy and economic benefit for production management and for long-term optimization purposes. © 2023 by the authors.Item Performance prediction and analysis of perovskite solar cells using machine learning(Elsevier B.V., 2024) Sadhu, D.; Dattatreya, D.; Deo, A.; Tarafder, K.; De, D.The conventional way to develop perovskite solar cells (PSCs) is generally based on trial and error and time-consuming synthesis methods. This motivates the adoption of machine learning (ML) models for performance prediction of PSCs. In this work, four ML models have been chosen out of 24 prediction models created to forecast open circuit voltage (Voc), short circuit current density (Isc), fill factor (FF), and power conversion efficiency (PCE) of PSCs. The prediction model derived from Multi-layer Perceptron algorithm demonstrates the highest level of accuracy and RMSE values for predicting PCE, Voc, Isc, and FF are as low as 0.58 %, 0.054 V, 1.01 mA cm−2 and 0.021, respectively. Through Shapley Additive exPlanations theory, the factors affecting the performance parameters of PSCs are analysed. Among 15 distinct features, hole mobility of hole transport layer, electron mobility of electron transport layer, formamidinium in cations and Br in anions, grain size and band gap of the perovskite absorber play the most vital role in improving the performance of PSCs. Herein, four new distinct attributes: grain size, tolerance factor, and electron and hole mobility values of perovskite absorber layer, have been included to the dataset and analysed to predict the performance of PSCs. These results suggest that ML techniques effectively forecast the performance of PSCs and minimize the synthesis cost and time towards the fabrication of efficient cells for commercialization. © 2024 Elsevier B.V.Item Optimization-based convolutional neural model for the classification of white blood cells(Springer Nature, 2024) Devi, T.G.; Patil, N.White blood cells (WBCs) are one of the most significant parts of the human immune system, and they play a crucial role in diagnosing the characteristics of pathologists and blood-related diseases. The characteristics of WBCs are well-defined based on the morphological behavior of their nuclei, and the number and types of WBCs can often determine the presence of diseases or illnesses. Generally, there are different types of WBCs, and the accurate classification of WBCs helps in proper diagnosis and treatment. Although various classification models were developed in the past, they face issues like less classification accuracy, high error rate, and large execution. Hence, a novel classification strategy named the African Buffalo-based Convolutional Neural Model (ABCNM) is proposed to classify the types of WBCs accurately. The proposed strategy commences with collecting WBC sample databases, which are preprocessed and trained into the system for classification. The preprocessing phase removes the noises and training flaws, which helps improve the dataset's quality and consistency. Further, feature extraction is performed to segment the WBCs, and African Buffalo fitness is updated in the classification layer for the correct classification of WBCs. The proposed framework is modeled in Python, and the experimental analysis depicts that it achieved 99.12% accuracy, 98.16% precision, 99% sensitivity, 99.04% specificity, and 99.02% f-measure. Furthermore, a comparative assessment with the existing techniques validated that the proposed strategy obtained better performances than the conventional models. © The Author(s) 2024.Item Choosing engineering education: understanding the motives of Indian young women-a narrative inquiry(Taylor and Francis Ltd., 2025) Geethalakshmi, P.M.; Thomas, V.V.; David, S.Young women in India are now seen choosing engineering education in the institutes of national importance, marking the beginning of inclusivity. With the aim of sustaining this positive momentum, this study explores the experiences of young women which led them into engineering education. Polkinghorne’s Two kinds of analysis–‘Analysis of narratives’ and ‘Narrative analysis’ are adopted to understand the narratives. The study revealed a nuanced understanding of their motives and triggers. The stories of nine students are shared under two narrative types–‘Engineer by choice’ and ‘Engineer by chance’. ‘Engineer by choice’ captures the narratives of those women who employed their agentic self in realizing their dream, while ‘engineer by chance’ captures the stories of those women who used engineering education as a fallback option when their dreams did not materialize. McAdam’s Narrative identity theory and Gotfredson’s theory of circumscription and compromise are used in analysis to understand the nature of contextual support needed in the growing years. Interventions at the school level by career counselling cells are proposed. Exposure to potential careers, awareness of favourable policies in organizations, and conduct of workshops with opportunities to solve real-life challenges, are proposed to create favourable disposition towards engineering among girls. © 2025 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.