Yazar "Chinnathambi, Arunachalam" seçeneğine göre listele
Listeleniyor 1 - 3 / 3
Sayfa Başına Sonuç
Sıralama seçenekleri
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, FarzadLithium-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.Öğe Production of liquid hydrocarbon fuels through catalytic cracking of high and low-density polyethylene medical wastes using fly ash as a catalyst(Elsevier, 2024) Premkumar, P.; Saravanan, C. G.; Nalluri, Premdasu; Seeman, M.; Vikneswaran, M.; Madheswaran, Dinesh Kumar; Bai, Femilda Josephin Joseph Shobana; Chinnathambi, Arunachalam; Pugazhendhi, Arivalagan; Varuvel, Edwin GeoThis study explores the potential of converting High-Density Polyethylene (HDPE) and Low-Density Polyethylene (LDPE) waste into liquid hydrocarbon fuels through catalytic degradation using fly ash. It achieves significant conversion rates, with HDPE reaching over 95% total conversion and a 66.4% oil yield at a catalyst-to-polymer ratio of 0.20, while LDPE shows a 100% conversion rate at ratios of 0.15 and 0.20. The process not only yields hydrocarbons with decreasing density and increasing calorific values, up to 55 MJ/kg for HDPE and 47 MJ/kg for LDPE at optimal conditions but also produces fractions with properties similar to diesel, notably in terms of density and viscosity. The flashpoint and fire point values further affirm these products' potential as viable fuel sources, aligning closely with diesel standards. 1H NMR spectroscopy analysis reveals a composition rich in longchain alkanes and alkenes, indicating the efficient transformation of plastic waste into valuable energy resources. This research presents a promising avenue for recycling plastic waste into alternative fuels, highlighting a sustainable approach to waste management and energy recovery.Öğe Response surface methodology optimization of characteristics of biodiesel powered diesel engine and its effective integration to autonomous microgrid(Elsevier, 2024) Kasimani, Ramesh; Sakthivel, R.; Balasubramanian, Dhinesh; Bai, Femilda Josephin Joseph Shobana; Chinnathambi, Arunachalam; Varuvel, Edwin GeoAn optimum diesel engine load condition with higher thermal efficiency and energy management has been the foremost challenge in the renewable energy research field. Modern trends involve nano additives for obtaining high performing biodiesel blends. Considering the above-mentioned factors, an experimental study along with statistical analysis has been performed with variation of compression ratio (16, 17.5 & 18), ZrO2 nano additive (50, 100 & 150 ppm) and load (50, 75 & 100 %). The optimization was accomplished by diminishing the BSFC, NOx, HC, CO, and increasing the BTE, CO2 using the approach of desirability. From the obtained results, the optimum operating conditions of the engine were found to be 75 % load, 18:1 compression ratio, and 150 ppm ZrO2 nano additive. The actual values at optimized conditions are obtained as BSFC (0.27 kg/kWh), BTE (33.37 %), CO (0.71 %), CO2 (8.69 %), NOx (1270 ppm), HC (62 %) and Smoke (25.20 %) with error less than 5 %. It has been observed that the BSFC of the proposed biodiesel-diesel blend is lower than that of pure diesel in all levels of power output. The biodiesel fuelled diesel engine is integrated as backup power in autonomous microgrid with main power as solar PV system operated at MPPT mode. A hybrid power system based on solar PV and biodiesel generator set up is the better alternative to emission-intensive fossil fuel and intermittent renewable.
