Yazar "Varuvel, Edwin Geo" seçeneğine göre listele

Listeleniyor 1 - 20 / 57
  • Küçük Resim Yok
    Öğe
    A comparative analysis of advanced machine learning models for the prediction of combustion, emission and performance characteristics using endoscopic combustion flame image of a pine oil–gasoline fuelled spark ignition engine
    (Elsevier Ltd., 2024) Godwin, D. Jesu; Varuvel, Edwin Geo; Jesu Martin, M. Leenus; Jasmine R, Anita; Josephin JS, Femilda
    This research focuses on using machine learning to predict the spark ignition engine's combustion, performance, and emission parameters with bio-fuel blends such as pine oil blend, which significantly diminishes the environmental impact of traditional fuels, reduces the limitations of repeated engine experimentation and addresses the nonlinearities in engine test results contributing to sustainable cleaner fuel and energy solutions. The models used were Ensemble Decision Tree Bagging, Ensemble Least Squares Boosting, Gaussian Process Regression and Support Vector Machine Regression, with good generalization ability. Brake Specific Fuel Consumption data from the test engine trials and endoscopic image flame area data after spark timing at different crank angles (320, 400, 480, 560, and 640 after Spark Timing) were fed into the machine-learning models as predictors. The response variables were Brake thermal efficiency, Unburnt Hydrocarbons, Carbon monoxide, Carbon dioxide, Oxides of nitrogen, maximum In-cylinder pressure, and maximum heat release rate. The bootstrap technique was used to generate numerous datasets from the experimental data for data-driven model training and tested using both interpolative and extrapolative data. The experimental and predicted values for all these algorithms were subjected to repeated hyperparameter optimization trials and the best machine learning method was identified using the performance and error metrics. The Ensemble Least Squares Boost model showed the overall best correlation (R2) in the range of 0.97–0.99 for gasoline and pine oil PN20 blend for the predicted versus experimental engine parameters. The root-mean-squared error (RMSE) at maximum load ranged between 0.0086 and 0.3044 for gasoline and 0.0049–0.2046 for the Pine oil PN20 fuel blend respectively. Therefore, employing an Ensemble Least Squares Boosting machine learning framework can effectively predict the characteristics of gasoline engines using pine oil and blends. This approach serves as a virtual engine model, efficiently overcoming the limitations and complexities inherent in conventional engine experiments. © 2024 Elsevier Ltd
  • Küçük Resim
    Öğe
    A deep learning multi-feature based fusion model for predicting the state of health of lithium-ion batteries
    (Elsevier ltd, 2025) Sonthalia, Ankit; Bai, Femilda Josephin Joseph Shobana; Varuvel, Edwin Geo; Chinnathambi, Arunachalam; Subramanian, Thiyagarajan; Kiani, Farzad
    Lithium-ion batteries have become the preferred energy storage method with applications ranging from consumer electronics to electric vehicles. Utilization of the battery will eventually lead to degradation and capacity fade. Accurately predicting the state of health (SOH) of the cells holds significant importance in terms of reliability and safety of the cell during its operation. The battery degradation mechanism is strongly non-linear and the physics-based model have their inherent disadvantages. The machine learning method has become popular for estimating SOH due to its superior non-linear mapping, adaptive, and self-learning capabilities, made possible by advances in deep learning technologies. In this study parallel hybrid neural network is formulated for predicting the state of health of lithium-ion cell. Firstly, the factors that have an effect on the cell state were analysed. These factors are cell voltage, charging & discharging time and incremental capacity curve. The features were then processed for use as input to the model. Spearman correlation coefficient analysis shows that all the factors had a positive correlation with SOH. While charging time has a negative correlation with the other features. Next the deep learning models namely convolution neural network (CNN), temporal convolution network (TCN), long-short-term memory (LSTM) and bi-directional LSTM were used to make fusion models. The number of layers in CNN and TCN were also varied. The hyperparameters used in the models were optimized using Bayesian optimization algorithm. The models were validated through comparative experiments on the University of Maryland battery degradation dataset. The prediction accuracy with CNN 3-layer LSTM was found to be the best for the training and the test dataset. The overall R2 value, root mean squared error (RMSE) and mean absolute percentage error (MAPE) with the model was found to be 0.999646, 0.003807 and 0.3, respectively. The impact of the features on the model was also analysed by removing one feature and retraining the model with the other features. The effect of discharging time and the peak of the discharge incremental capacity curve was maximum. The analysis also reveals that either charging voltage or discharging voltage can be used. Further, the proposed model was also compared with the other studies. The comparison shows that the R2, RMSE and MAPE values of the proposed model was better.
  • Küçük Resim
    Öğe
    Application of machine learning algorithms for predicting the engine characteristics of a wheat germ oil–hydrogen fuelled dual fuel engine
    (Elsevier, 2022) Joseph Shobana Bai, Femilda Josephin; Shanmugaiah, Kaliraj; Sonthalia, Ankit; Devarajan, Yuvarajan; Varuvel, Edwin Geo
    In this research work, performance and emission parameters of wheat germ oil (WGO) -hydrogen dual fuel was investigated experimentally and these parameters were predicted using different machine learning algorithms. Initially, hydrogen injection with 5%, 10% and 15% energy share were used as the dual fuel strategy with WGO. For WGO +15% hydrogen energy share the NO emission is 1089 ppm, which is nearly 33% higher than WGO at full load. As hydrogen has higher flame speed and calorific value and wider flammability limit which increases the combustion temperature. Thus, the reaction between nitrogen and oxygen increases thereby forming more NO. Smoke emission for WGO +15% hydrogen energy share is 66%, which is 15% lower compared to WGO, since the heat released in the pre-mixed phase of combustion is increased to a maximum with higher hydrogen energy share compared to WGO. Different applications including internal combustion engines have used machine learning approaches for predictions and classifications. In the second phase various machine learning techniques namely Decision Tree (DT), Random Forest (RF), Multiple Linear Regression (MLR), and Support Vector Machines (SVM)) were used to predict the emission characteristics of the engine operating in dual fuel mode. The machine learning models were trained and tested using the experimental data. The most effective model was identified using performance metrics like R-Squared (R2) value, Mean Absolute Error (MAE), Mean Square Error (MSE), and Root Mean Square Error (RMSE). The result shows that the prediction by MLR model was closest to the experimental results. © 2022 Hydrogen Energy Publications LLC
  • Küçük Resim
    Öğe
    Application of Taguchi design in optimization of performance and emissions characteristics of n-butanol/diesel/biogas under dual fuel mode
    (Elsevier, 2023) Goyal, Deepam; Goyal, Tarun; Mahla, Sunil Kumar; Goga, Geetesh; Dhir, Amit; Balasubramanian, Dhinesh; Hoang, Anh Tuan; Joseph Shobana Bai, Femilda Josephin; Varuvel, Edwin Geo
    Combustion experts are in search of some alternative fuel from last few decades owing to diminishing petroleum products and unexpected variations in habitat, which are result of venomous emissions from the CI engines. The present investigation intended to assess the performance and emission parameters of a diesel engine by fueling it with pilot fuel (blends of diesel and n-butanol) and primary fuel (Biogas). Results revealed that BTE, HC and CO increases whilst NOx and smoke emissions were reduced by using the pilot and primary fuel together in relation with natural diesel. Experimentation was done using Taguchi L9 orthogonal array design. The engine load, flow rate of biogas and butanol in fuel blend percentage were selected as input parameters whereas brake thermal efficiency (BTE) and emission characteristics i.e., HC, CO, NOx and smoke were chosen as response variables. ANOVA was carried out for the responses by utilizing MINITAB software. The higher value of raw data and S/N ratio for BTE was noted with high engine load, low flow rate of biogas and butanol blend percent. For the emission characteristics i.e., HC, CO and smoke, lower raw data and high S/N ratio values were attained in the order of rank engine load > butanol blend percent > biogas flow rate while the similar values for NOx were attained in the rank engine load > biogas flow rate > butanol blend percent. Taguchi design was noted to be an effective tool for the optimization of various response parameters and the optimum levels of input parameters were calculated after analysis. Full engine load for BTE and HC, Biogas flow rate of 15 lpm for BTE, HC and CO, and 20 % of butanol blend for HC, CO and smoke were found to be the optimum conditions for the conducted experimentation. © 2022 Elsevier Ltd
  • Küçük Resim Yok
    Öğe
    Assessing the impact of sargassum algae biodiesel blends on energy conversion in a modified single-cylinder diesel engine with a silica-incorporated diamond-like coated piston
    (Taylor & Francis, 2024) Jayaraman, Kamalakannan; Veeraraghavan, Sakthimurugan; Sundaram, Madhu; Varuvel, Edwin Geo
    As coal and oil reserves deplete, the world is shifting to alternative fuels and renewable energy. Researchers are exploring a cleaner alternative to fossil fuels for powering automobiles. In this investigation, biodiesel was synthesized from brown marine algae (Sargassum algae) using transesterification process. Silica-incorporated diamond-like coating (DLC) was done on the engine piston by using the chemical vapor deposition (CVD) process with flow rate of 7sccm of C2H2. Three different coating thicknesses, such as 50,100, and 150 mu m, were employed on the CI engine piston. Mechanical properties such as hardness, wear, and microstructure analysis were investigated. Analysis of mechanical characteristics reveals that pistons with a 100 mu m coating have enhanced characteristics compared to those with other pistons. Using a 100 mu m silicon coated piston on a single-cylinder Kirloskar engine, four blends (B10, B20, B30, and B40) were compared to neat diesel. At maximum engine load conditions, the B40 blends produced 42 ppm of HC whereas neat diesel with 19 ppm which is 57% higher than diesel and CO emission concentration increased by 4.9% than diesel. Similarly, brake-specific fuel consumption was observed at maximum load conditions for diesel with 0.18 kg/kWh and 0.20 kg/kWh for B10D90 which is 9.54% higher than diesel. As a result, it is critical to recognize the importance of sargassum's potential for producing sustainable energy toward green globalization.
  • Küçük Resim
    Öğe
    Battery fault diagnosis methods for electric vehicle lithium-ion batteries: Correlating codes and battery management system
    (Institution of chemical engineers, 2025) Naresh, G.; Praveenkumar, T.; Madheswaran, Dinesh Kumar; Varuvel, Edwin Geo; Pugazhendhi, Arivalagan; Thangamuthu, Mohanraj; Muthiya, S. Jenoris
    Lithium-ion batteries are the heart of modern electric vehicle technology. Operational stresses such as temperature changes, mechanical impacts, and electrochemical aging often subject them to faults, necessitating accurate fault diagnosis that adheres to international safety standards. Consequently, this review examines state-ofthe-art fault diagnosis methodologies, emphasizing their integration with global safety frameworks such as the International Organization for Standardization, International Electrotechnical Commission, Society of Automotive Engineers, etc. A thorough analysis of artificial fault induction techniques-such as overcharging and overheating-is presented to assess their effectiveness in validating diagnostic algorithms. Additionally, the role of machine learning in battery management systems is reviewed, where the Feature Fusion and Expert Knowledge Integration network emerged effective, achieving an anomaly detection rate of 98.5 %, outperforming conventional methods in accuracy and speed. Hybrid diagnostic frameworks integrating model-based and machine-learning techniques are also highlighted for their scalability and precision in addressing sub-extreme fault scenarios. Looking ahead, this study emphasizes the importance of interdisciplinary research to enhance fault detection, focusing on adaptive machine learning algorithms and real-world testing to ensure the long-term viability of contemporary battery technologies.
  • Küçük Resim Yok
    Öğe
    Biodiesel from Biomass Waste Feedstock Prosopis Juliflora as a Fuel Substitute for Diesel and Enhancement of Its Usability in Diesel Engines Using Decanol
    (Wiley-V C H Verlag Gmbh, 2023) Duraisamy, Boopathi; Velmurugan, Kandasamy; Venkatachalapathy, V. S. Karuppannan; Madheswaran, Dinesh Kumar; Varuvel, Edwin Geo
    Biomass-based biofuel production is a promising solution to the decline of fossil fuels. Prosopis juliflora seed-derived vegetable oil, known as Prosopis juliflora methyl ester (JFME), offers a potential feedstock for biodiesel. To enhance its properties, the addition of Decanol is investigated, a higher-order alcohol similar to Diesel. Experiments are conducted on a 5.2 kW compression ignition (CI) engine using JFME blended with different decanol concentrations (5%, 10%, 15%, and 20%). Fourier-transform infrared spectroscopy and gas chromatography-mass spectrometry analysis confirm its compliance with fuel standards. The findings reveal that the 20% decanol blend (D20) achieves a brake thermal efficiency of 29.9% at full load, with reduced NO, smoke, and hydrocarbon (HC) emissions compared to diesel. D20 shows NO emissions of 1265 ppm, smoke opacity of 53%, and HC emissions of 69 ppm, while diesel records 1320 ppm, 69%, and 75 ppm, respectively. The CO emissions for D20 are 0.359 vol%, slightly higher due to decanol's higher latent heat of evaporation. Moreover, D20 exhibits improved combustion with a higher mass fraction burnt and faster heat release rates. These results indicate the potential of using JFME blended with 20% decanol as an alternative fuel for CI engines, offering higher performance and reduced emissions.
  • Küçük Resim
    Öğe
    Biofuel from leather waste fat to lower diesel engine emissions: Valuable solution for lowering fossil fuel usage and perception on waste management
    (Institution of Chemical Engineers, 2022) Devarajan, Yuvarajan; Jayabal, Ravikumar; Munuswamy, Dinesh Babu; Ganesan, S.; Varuvel, Edwin Geo
    This work examines the viability of examining waste fat extracted from industrial leather waste as an alternative to diesel. These wastes are harmful if disposed to the environment. Conventional transesterification was per- formed to produce leather waste methyl ester (LWME). Post-processing, a yield of 82.6% of methyl ester was obtained. The obtained LWME was inspected for its thermophysical properties and falls with ASTM standards. LWME was blended with petroleum diesel at 10%, 20% and 30% on a volume basis and referred to as LWME10D90, LWME20D80 and LWME30D70 correspondingly. The effect of LWME/ diesel blends was inspected in a four-stroke, single-cylinder, direct-injection engine under diverse loads. Test results revealed that the brake thermal efficiency for LWME/ diesel blends was lower than diesel at all loads with higher specific brake-specific fuel consumption was higher as both are inversely proportional. Carbon monoxide emissions were reduced by 22.7%, Hydrocarbon emissions were reduced by 48%, and Smoke emissions were reduced by 6.43%, with a 9.84% increase in nitrogen oxide emissions for LWME30D70 than diesel. It has been concluded that including LWME in diesel lowers the greenhouse gases with a marginal reduction in performance pattern.
  • Küçük Resim
    Öğe
    CO2 reduction in a common rail direct injection engine using the combined effect of low carbon biofuels, hydrogen and a post combustion carbon capture system
    (Taylor & Francis, 2021) Varuvel, Edwin Geo; Thiyagarajan, S.; Sonthalia, Ankit; Prakash, T.; Awad, Sary; Aloui, Fethi; Pugazhendhi, Arivalagan
    The transportation sector is a major emitter of carbon dioxide emissions. It is a known fact that carbon dioxide is the cause of global warming which has resulted in extreme weather conditions as well as climate change. In this study a combination of different methods of expediting the CO2 emission from a single cylinder common rail direct injection (CRDI) engine has been explored. The methods include use of low carbon content biofuels (lemon peel oil (LPO) and camphor oil (CMO), inducing hydrogen in the intake manifold and zeolite based after-treatment system. Initial engine operation with the low carbon content biofuel blends resulted in reduced smoke and CO2 emissions. Substitution of the blends with hydrogen further assisted in decrease in emission and improvement in engine efficiency. Later on in the exhaust pipe an after-treatment system containing zeolite was placed. The emissions were found to reduce even further and at full load condition the lowest CO2 (39.7% reduction) and smoke (49% reduction) emissions were observed with LPO blend and hydrogen induction. The NO emission with hydrogen induction increases for both the blends, however, it was seen that the zeolite based treatment system was effective in reducing the emission as well. As compared to baseline diesel, the maximum reduction in NO emission was 23% at full load with LPO blend, hydrogen induction and after-treatment system.
  • Küçük Resim
    Öğe
    Combined effects of nozzle hole variation and piston bowl geometry modification on performance characteristics of a diesel engine with energy and exergy approach
    (Elsevier Ltd., 2022) Praveena, V.; Leenus Jesu Martin, M.; Varuvel, Edwin Geo
    This experimental work aims to address the challenges of waste management. Biomass waste is converted into useful fuel and considered as a replacement to conventional fuel in CI engines. In this context, the grape marc and grape pomace are crushed and further processed to produce grapeseed oil. The grapeseed oil is further trans esterified to produce grapeseed seed oil methyl ester. The present study aims in examining the effect of varying piston shapes and nozzle profile on energy and exergy rates of a CI engine run with grapeseed oil methyl ester (GSME) blended with cerium oxide nano particles. The CeO2 nano particles were suspended in the base fuel at a concentration of 100 ppm and stability tests were conducted. The experiments were performed on a single cylinder, water cooled diesel engine with rated power of 5.2 kW. The research work includes two additional piston shapes namely, toroidal and shallow deep and two additional nozzle profiles viz. 4 hole and 5-hole nozzle. The hemispherical shape and 3-hole nozzle were considered as the standard one. Energy and exergy analysis were done on the experimental data to understand the exergy associated with cooling water, exhaust gas and unaccounted losses. The energy and exergy rates show that increase in nozzle hole number, decreases the destructive availability of the system. The exergetic efficiency of 32.8% is higher proving that toroidal shape and 5-hole nozzle profile is comparatively better and suitable for effective engine operation. HC, CO and smoke emissions reduced considerably by 14.4%–30% by the engine modification. Brake thermal efficiency was improved from 28.2% to 31.02% for CI engine with biodiesel. The paper addresses the gap in fuel modification clubbed with engine modification using biomass waste derived fuel. Exergy and energy analysis further add value to this current experimental work.
  • Küçük Resim
    Öğe
    Combustion analysis of higher order alcohols blended gasoline in a spark ignition engine using endoscopic visualization technique
    (Elsevier Ltd, 2022) Vikneswaran, M.; Saravanan, C.G.; Sasikala, J.; Ramesh, P.; Varuvel, Edwin Geo
    The experimental study was carried out on the port fuel injection system installed spark-ignition engine fuelled by 1.5%, 3%, and 5% higher order alcohol such as 1-hexanol and 2-heptanol blended gasoline. In this study, the endoscopic combustion visualization technique was employed to compare and analyze the changes observed in the spatial flame characteristics between the alcohol blends and sole gasoline. The Correlated Colour Temperature (CCT) method was used to predict the flame temperature distribution from the captured flame images. Also, the effect of blending alcohols on engine combustion, performance, and emission characteristics was studied. The endoscopic results revealed that the flame spread region with respect to different CA positions increases with the alcohol blending ratio in the sole gasoline at the early and middle stages of the combustion. Further, the engine characteristics study revealed that 5% hexanol and heptanol blends gave a brake thermal efficiency of 25.8% and 25.7%, respectively, which were higher than sole gasoline, having 24.8% at full load. In addition, it was observed that the early start of combustion (SoC) and a faster burn rate associated with alcohol blends raise the cylinder pressure and heat release rates (HRRs) and thereby result in higher peak pressure and HRR with slight advancement in the CA position. At 8 kW, the CO and HC emission of 5% 1-hexanol and 2-heptanol blends was decreased by about 10.3% and 13.7%, and 9.5% and 8%, respectively, and NO emission decreased slightly with a rise in alcohol concentration in the mix when compared to gasoline. © 2022 Elsevier Ltd
  • 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
    Comparative analysis to reduce greenhouse gas (GHG) emission in CI engine fuelled with sweet almond oil using ammonia/after treatment system
    (Elsevier, 2024) Sonthalia, Ankit; Varuvel, Edwin Geo; Subramanian, Thiyagarajan; Josephin, Femilda J. S.; Alahmadi, Tahani Awad; Pugazhendhi, Arivalaga
    The present study analyses the various techniques to reduce CO 2 emission, a major contributor to GHG emissions. Diesel was replaced with prunus amygdalus dulcis (sweet almond oil) -fuelled single -cylinder compression ignition (CI) engine. Due to the high viscosity of sweet almond oil, a transesterification procedure was used to convert it to biodiesel. In this experiment, the diesel fuel was entirely substituted with biodiesel (B100) in order to evaluate the emissions, combustion characteristics, and performance of the CI engine operating at a consistent 1500 revolutions per minute under varying loads. In comparison to diesel, tailpipe CO 2 emissions were greater when biodiesel was utilized due to its higher carbon content in the molecular structure. However, plantations absorbs CO 2 emissions from atmosphere causing 'net negative CO 2 emission '. No carbon fuel ammonia was introduced into the intake air using sweet almond oil biodiesel as the base fuel in order to reduce exhaust CO 2 emissions. Under various load conditions, ammonia was introduced at varying flow rates ranging from 10 to 30 LPM. It is observed that increase in ammonia flow rate led to reduction in CO 2 emission. CO 2 emission was reduced from 11.2 % for biodiesel to 6.9 % with 30 LPM ammonia. An after -treatment system was designed with calcite/ activated carbon and retrofitted in exhaust pipe and tested with B100 as fuel. The results indicate that calcite reduces CO 2 more effectively than CO 2 capture systems based on activated carbon. CO 2 emission with calcite is 9.6 % and with activated carbon it is 10.2 % at maximum load condition. The utilization of a calcite -based CO 2 capture system in conjunction with biofuel is believed to effectively mitigate the adverse effects of global warming by generating a net negative CO 2 effect and reducing engine out emissions. Based on the experimental results, compared to after treatment system, ammonia addition with biodiesel is more effective in reducing CO 2 emission without much affecting the other parameters.
  • 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
    Development of artificial neural network and response surface methodology model to optimize the engine parameters of rubber seed oil - Hydrogen on PCCI operation
    (Pergamon-Elsevier Science Ltd, 2023) Varuvel, Edwin Geo; Seetharaman, Sathyanarayanan; Bai, Femilda Josephin Joseph Shobana; Devarajan, Yuvarajan; Balasubramanian, Dhinesh
    Identifying the suitable alternative fuel and optimum blend concentration for diesel engine combustion is critical as most biodiesel emits excess smoke and has a lower thermal efficiency due to its high viscosity and carbon residue. In the previous work, rubber seed oil was tested in a single-cylinder diesel engine, and its performance and emission results were compared with those of pure diesel, an RSO-diesel (70:30 by volume) blend, RSOmethyl ester, RSO-diethyl ether, RSO-ethanol, and RSO-hydrogen in a dual fuel operation. The testing was performed at a constant speed of 1500 rpm, with the engine loads varying at 25% step intervals. Results showed that smoke and nitrogen oxides were significantly reduced for RSO, and engine performance was enhanced when RSO was operated with hydrogen and diethyl ether in dual fuel mode. In this study, the experimental results were employed to develop an artificial neural network and response surface methodology model. Brake thermal efficiency, rate of pressure rise, carbon monoxide, hydrocarbon, oxides of nitrogen, and smoke were predicted using response surface methodology and artificial neural network. Though artificial neural network produced the best R2 values (0.87264-0.99929), mean absolute percentage error was relatively lesser in response surface methodology. Thus, the authors conclude that response surface methodology is the best suitable artificial intelligence tool to optimize the engine for accomplishing desired responses.
  • Küçük Resim Yok
    Öğe
    Early prediction of the remaining useful life of lithium-ion cells using ensemble and non-ensemble algorithms
    (John wiley and sons inc, 2025) Bai, Femilda Josephin Joseph Shobana; Sonthalia, Ankit; Subramanian, Thiyagarajan; Aloui, Fethi; Bhatt, Dhowmya; Varuvel, Edwin Geo
    Lithium-ion cells have become an important part of our daily lives. They are used to power mobile phones, laptops and more recently electric vehicles (both two- and four-wheelers). The chemical behavior of the cells is rather complex and non-linear. For reliable and sustainable use of the cells for practical applications, it is imperative to predict the precise pace at which their capacity will degrade. More importantly, the lifetime of the cells must be predicted at an early stage, which would accelerate development and design optimization of the cells. However, most of the existing methods cannot predict the lifetime at an early stage, since there is a weak correlation between the cell capacity and lifetime. In this study for accurate forecasting of the battery lifetime, the patterns of the parameters such as cell current, voltage, temperature, charging time, internal resistance, and capacity were examined during charging and discharging cycle of the cell. Twelve manually crafted features were prepared from these parameters. The dataset for the features was created using the raw data of the first 100 cycles of 124 cells. Six ensemble and non-ensemble machine learning algorithms, namely, multiple linear regression (MLR), decision tree, support vector machine (SVM), gradient boosting machine (GBM), light gradient boosting machine (LGBM), and extreme gradient boosting (XGBoost), were trained with the features for predicting the life-cycle of the cells. The R2 and root mean squared error (RMSE) values of MLR, decision tree, SVM, GBM, LGBM, and XGBoost were found to be 0.72 and 201, 0.83 and 155, 0.85 and 146, 0.92 and 100, 0.9 and 112, and 0.94 and 95, respectively. The prediction accuracy of lithium-ion cell life-time was found to be the best with the XGBoost algorithm. This shows that only first 100 cycles are required foraccurately predicting the number of cycles the lithium-ion cell can work for. Lastly, the results of the study were compared with the available studies in the literature. Three studies were chosen, and the RMSE of the method proposed in this study was found to be higher than the three studies by 43, 17, and 20. Therefore, the proposed method is a suitable option for predicting the lifetime of lithium-ion cells during the early stages of its development.
  • Küçük Resim
    Öğe
    Eco-friendly perspective of hydrogen fuel addition to diesel engine: An inclusive review of low-temperature combustion concepts
    (Elsevier Ltd, 2024) Nguyen, Van Nhanh; Ganesan, Nataraj; Ashok, Bragadeshwaran; Balasubramanian, Dhinesh; Anabayan K.; Lawrence, Krupakaran Radhakrishnan; Tamilvanan A.; Le, Duc Trong Nguyen; Truong, Thanh Hai; Tran, Viet Dung; Cao, Dao Nam; JS, Femilda Josephin; Varuvel, Edwin Geo
    Hydrogen is a probable alternative fuel for both stationary and automotive engine applications due to its properties like high energy content and persistent availability. However, using hydrogen only as a fuel for engines was almost impossible; thus, hydrogen co-combusting with diesel and several biomass-based biofuels will be advisable. As viscosity plays a significant role in combustion, the application of biodiesel was classified as high viscous fuel and low viscous fuel for investigation with hydrogen in compression ignition engines. The present study aims to reconnoitre the prospects of using hydrogen-enriched diesel-biodiesel blends with advanced combustion technology. The present work also examines advanced combustion technologies, including reactivity-controlled compression ignition (RCCI), homogenous charge compression ignition (HCCI), and laser ignition technology. This review shed light on the properties of hydrogen-enriched biodiesel blends, engine operating parameters, and their impact on engine characteristics. This comprehensive review offered a distinct view to the academics for improving the performance, combustion, and emission characteristics of CI engines fuelled with hydrogen-enriched biodiesel-diesel. Further, the review progressed with the aforesaid operating conditions and advanced combustion technology. © 2024 Hydrogen Energy Publications LLC
  • Küçük Resim
    Öğe
    Effect of alloying elements and ceramic coating on the surface temperature of an aluminum piston in a diesel engine
    (HINDAWI LTD, 2022) Vengatesan, S.; Yadav, Paras; Varuvel, Edwin Geo
    The engine piston is subjected to very high temperature during the combustion process, and it is very difficult to control the stability of the geometry at elevated temperature. The stability of the engine piston was analysed by finite element method with steady-state conditions for three different types of approach to control it, where the influence of the alloying element of aluminum piston, influence of surface coating, and its impact on the thickness variation followed by the influence of holes on the coating surface have been analysed in detail. It is observed that the coating with holes shows good agreement with requirement compared to the influence of the alloying element and coated piston. The conduction mode of heat transfer is controlled, and also, the heat transfer to the adjacent components is facilitated by holes on the coated piston.
  • Küçük Resim
    Öğe
    Effect of amyl alcohol addition in a CI engine with Prosopis juliflora oil - an experimental study
    (Taylor and Francis, 2021) Duraisamy, Boopathi; Velmurugan, Kandasamy; Venkatachalapathy, V. S.Karuppannan; Subramanian, Thiyagarajan; Varuvel, Edwin Geo
    This study aims to replace diesel with Prosopis Juliflora seed oil (JPO) in a compression ignition (CI) engine. The high viscosity of JPO promotes inferior performance and combustion. Brake thermal efficiency of JPO is 28.3%, which is less compared to 30.7% for diesel. This also leads to higher brakespecific energy consumption, HC, CO, and smoke emissions. JPO was converted to its biodiesel (Prosopis Juliflora methyl ester) (JPME) through the transesterification process. The physical properties were improved posttransesterification process. Brake thermal efficiency was improved to 29.3% for JPME. Higher NOx emission with reduced HC, CO, and smoke emissions was observed with JPME in comparison with JPO. The test engine employed for the investigations has a single-cylinder configuration with the maximum power of 5.2 kW enabled with water cooling. Furthermore, amyl alcohol was added with JPME in various proportions of 5%, 10%, 15%, and 20% by volume and experiments were conducted. The addition of amyl alcohol in the volume mentioned earlier has improved the thermal efficiency at higher loads; added to this NO and smoke emission were lowered simultaneously for all the loading conditions. Except with the 5% volume of amyl alcohol, HC and CO emissions have increased for all other volume compositions. JPME with 20% volume amyl alcohol exhibits the highest peak pressure and heat release rate. The brake thermal efficiency of JPME + A20 is on par with diesel. NO and smoke were reduced by 7% and 29%, respectively, for JPME + A20 in comparison with diesel. The study shows that the addition of 20% amyl alcohol with JPME has performance and emission characteristics similar to diesel. Further increase in amyl alcohol led to poor cold starting condition and may also lead to knocking. Hence, it was concluded to use only up to 20% of amyl alcohol to avoid any operational complications.