Yazar "Subramanian, Balaji" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim
    Öğe
    Comparative analysis of regression models to predict the performance of the dual fuel engine operating on diesel and hydrogen gas
    (Elsevier ltd, 2025) S, Priya; Feenita, C.; Goel, Uday; T, Manoranjitham; Duraisamy, Boopathi; Subramanian, Balaji; Ganeshan, Kavitha; Bai, Femilda Josephin Joseph Shobana; Albeshr, Mohammed F.; Pugazhendhi, Arivalagan; Varuvel, Edwin Geo
    Internal combustion engines (ICEs) have long been essential in both the transportation and industrial sectors, providing primary power for vehicles, ships, and machines globally. Optimising the efficiency of ICEs is vital for decreasing their environmental impart, as increased fuel efficiency and lower emissions play a significant role in mitigating the effects of climate change as well as improving air quality. This study employed 15 regression algorithms and machine learning approaches to analyse and anticipate the performance parameters of ICEs that run on hydrogen-diesel in dual fuel mode. The input parameters include engine torque, speed, hydrogen flow rate, brake power and diesel energy share to hydrogen supply and the output parameters are brake specific fuel consumption, brake thermal efficiency, volumetric efficiency and actual air intake. The model's performance is evaluated using five different performance metrics. Among the studied algorithms, the RANSAC Regressor demonstrated exceptional predictive capability, reaching an R-squared value of 0.999, a mean squared error (MSE) of 0.0064, a root mean square error (RMSE) of 0.08, and a mean absolute error (MAE) of 0.057. These outcomes show the algorithm's accuracy and precision in capturing the complicated data of engine system. The equivalency ratio, volumetric efficiency, brake thermal efficiency, brake specific fuel consumption, and actual air intake are among the critical performance outputs that are optimised by utilizing key input parameters like engine load, rotational speed, hydrogen flow rate, brake power, and the diesel fuel energy share. This study highlights the significant potential of machine learning in optimising ICE performance, offering a reliable alternative to traditional experimental analysis by reducing both risk and economic costs. The research findings also support the paradigm shift towards intelligent and sustainable energy systems by compellingly advocating for the inclusion of data-driven methodologies in contemporary engine design and operational methods
  • Küçük Resim Yok
    Öğe
    A comparative study on bayes classifier for detecting photovoltaic module visual faults using deep learning features
    (Elsevier, 2024) Venkatesh, S. Naveen; Sugumaran, V.; Subramanian, Balaji; Josephin, J. S. Femilda; Varuvel, Edwin Geo
    Renewable energy is found to be an effective alternative in the field of power production owing to the recent energy crises. Among the available renewable energy sources, solar energy is considered the front runner due to its ability to deliver clean energy, free availability and reduced cost. Photovoltaic (PV) modules are placed over large geographical regions for efficient solar energy harvesting, making it difficult to carry out maintenance and restoration works. Thermal stresses inherited by photovoltaic modules (PVM) under varying environmental conditions can lead to failure of internal components. Such failures when left undetected impart a number of complications in the system that will lead to unsafe operation and seizure. To avoid the aforementioned uncertainties, frequent monitoring of PVM is found necessary. The fault identification in PVM using essential features taken from aerial images is presented in this study. The feature extraction procedure was carried out using convolutional neural networks (CNN), while the feature selection process was carried out by the J48 decision tree method. Six test conditions were considered such as delamination, glass breakage, discoloration, burn marks, snail trail, and good panel. Bayes Net (BN) and Naive Bayes (NB) classifiers were utilized as primary classifiers for all the test conditions. Results obtained from the classifiers were compared and the best classifier for fault detection in PVM is suggested.
  • Küçük Resim
    Öğe
    Crafting high-performance polymer-integrated solid electrolyte for solid state sodium ion batteries
    (Wiley, 2024) Kannadasan, Mahalakshmi; Sathiasivan, Kiruthika; Balakrishnan, Muthukumaran; Subramanian, Balaji; Varuvel, Edwin Geo
    The development of modern solid-state batteries with high energy density has provided the reliable and durable solution needed for over-the-air network connectivity devices. In this study, a NASICON-type Na3Zr2Si2PO12 (NZSP) ceramic filler was prepared using the sol-gel method and then a polymer-integrated solid electrolyte consisting of polyethylene oxide (PEO), NZSP, and sodium perborate (SPB) was prepared by Stokes' solution casting process. Through physico-chemical and electrochemical characterization techniques, the morphology, electrochemical, and thermal properties of the prepared solid electrolyte sample were carefully studied. The PEO/NZSP/SPB electrolyte developed for all-solid-state sodium-ion batteries (ASSSBs) exhibited a strong ionic conductivity, a large window for electrochemical stability, and was effective in controlling the growth of sodium dendrites. Furthermore, the polymer-integrated solid electrolyte showed impressive rate capability, high discharge capacity (73.2 mAh g-1) at 0.1 mA cm-2, and good faradaic efficiency (98%) even after 100 cycles. These results reveal that the PEO/NZSP/SPB electrolyte is a potential and inevitable candidate for the evolution of high-performance rechargeable ASSSBs.
  • Küçük Resim Yok
    Öğe
    Efficacy of machine learning algorithms in estimating emissions in a dual fuel compression ignition engine operating on hydrogen and diesel
    (Pergamon-Elsevier Science Ltd, 2023) Venkatesh, S. Naveen; Sugumaran, V; Thangavel, Venugopal; Balaji, P. Arun; Vijayaragavan, Mathanraj; Subramanian, Balaji; Josephin, J. S. Femilda
    Emission created by combustion of fossil fuels are a major concern of the world for the past few decades. The stringent emission norms have impacted the automobile manufacturers to work on exhaust emissions and its impact. This research focused on using machine learning regression models to evaluate the efficacy of experimental results for a dual fuel compression ignition (CI) engine operating on hydrogen and diesel. In the present study, engine emissions were estimated using 29 regression algorithms. A total of 5 input data namely, concentration of hydrogen, engine load, diesel intake, speed and equivalence ratio were considered in the study to estimate various emissions like oxides of nitrogen (NOx), carbon dioxide (CO2), hydrocarbon (HC) and smoke. Correlation coefficient, mean absolute error, root mean squared error, relative absolute error and root relative squared error were adopted as the performance metrics in the present study. Amongst the algorithms considered, pace regression, radial basis function regressor, multilayer perceptron regressor and alternating model tree produced the highest correlation coefficient of 0.9985, 0.8958, 0.9950 and 0.9256 in estimating the engine emissions like CO2, smoke, NOx and HC respectively. Additionally, an attempt was made to establish an individual algorithm that can estimate all the emissions was identified as multilayer perceptron regressor with correlation coefficient values of 0.9977 (CO2), 0.9950 (NOx), 0.8501(smoke) and 0.8731(HC) respectively. (c) 2023 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved.