P. Hemachandu
P. Hemachandu has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
T. Sathish
2 shared publications- Ümit Ağbulut
Department of Mechanical Engineering, Faculty of Mechanical Engineering, Yildiz Technical University, Istanbul, Turkey
2 shared publications - A. Prabha
S. A. Engineering College
1 shared publication C Ahamed Saleel
1 shared publicationC. Dhayananth Jegan
1 shared publicationC. Esther Jeyanthi
1 shared publication
Latest Publications
- Open Access
- 1 September 2026
- Published by Institute of Advanced Engineering and Science in International Journal of Power Electronics and Drive Systems (IJPEDS)
- Vol. 17 (3) , 2291-2300
Accurate RUL prediction of EV batteries using random forest and ensemble learning frameworks
Precise remaining useful life (RUL) estimation for lithium-ion batteries is essential for improving the safety, reliability, and maintenance of electric vehicles (EVs). This study proposes a random forest (RF)-based ensemble learning framework using the publicly available Hawaii Natural Energy Institute (HNEI) dataset containing 15,064 charge-discharge cycles. Seven degradation-related features, including cycle index, discharge time, voltage decrement, maximum discharge voltage, minimum charging voltage, time at 4.15 V, and constant-current charging duration, are extracted to characterize battery aging. The proposed RF model is compared with linear regression (LR), long short-term memory (LSTM), and attention-LSTM models using MAE, root mean square error (RMSE), mean absolute percentage error (MAPE), and coefficient of determination (R²). RF demonstrates superior prediction performance, achieving MAE of 5.20, RMSE of 6.83, MAPE of 1.33%, and R² of 0.997. Parity and residual analyses further confirm its strong predictive consistency. The proposed approach provides an accurate, computationally efficient, and interpretable solution for BMS applications, enabling effective battery health monitoring, predictive maintenance, charging optimization, and timely replacement.
- 1 September 2026
- Published by Institute of Advanced Engineering and Science in International Journal of Power Electronics and Drive Systems (IJPEDS)
- Vol. 17 (3) , 2291-2300
Open AccessAccurate RUL prediction of EV batteries using random forest and ensemble learning frameworks
Precise remaining useful life (RUL) estimation for lithium-ion batteries is essential for improving the safety, reliability, and maintenance of electric vehicles (EVs). This study proposes a random forest (RF)-based ensemble learning framework using the publicly available Hawaii Natural Energy Institute (HNEI) dataset containing 15,064 charge-discharge cycles. Seven degradation-related features, including cycle index, discharge time, voltage decrement, maximum discharge voltage, minimum charging voltage, time at 4.15 V, and constant-current charging duration, are extracted to characterize battery aging. The proposed RF model is compared with linear regression (LR), long short-term memory (LSTM), and attention-LSTM models using MAE, root mean square error (RMSE), mean absolute percentage error (MAPE), and coefficient of determination (R²). RF demonstrates superior prediction performance, achieving MAE of 5.20, RMSE of 6.83, MAPE of 1.33%, and R² of 0.997. Parity and residual analyses further confirm its strong predictive consistency. The proposed approach provides an accurate, computationally efficient, and interpretable solution for BMS applications, enabling effective battery health monitoring, predictive maintenance, charging optimization, and timely replacement.
- 5 August 2025
- Published by Wiley in Energy Storage
- Vol. 7 (5)
Energy Management in Photovoltaic‐Based Electric Vehicle Charging Systems With Battery Storage and Vehicle‐to‐Grid Support
The rapid growth of Electric Vehicles (EVs) and the increasing reliance on renewable energy sources (RESs) have highlighted the need for intelligent, storage‐optimized charging infrastructure. However, conventional photovoltaic (PV)‐based EV charging systems often suffer from intermittency, storage inefficiencies, and limited integration with the power grid, leading to increased operational costs and reduced sustainability. To address these challenges, this paper proposes a hybrid energy management (EM) framework that integrates a Pelican Optimization Algorithm (POA) and a Triple‐Memristor Hopfield Neural Network (TMHNN) for optimizing Battery Energy Storage Systems (BESS) and Vehicle‐to‐Grid (V2G) operations in PV‐powered EV charging systems. POA is employed to optimize power flow (PF) and storage scheduling, while TMHNN accurately forecasts energy demand, enabling dynamic coordination between PV generation, energy storage, and EV charging. Simulation results demonstrate that the suggested POA‐TMHNN approach significantly reduces the cost of energy (COE) to $0.0841/kWh and carbon emissions to 173 956 kg, outperforming benchmark methods such as Particle Swarm Optimization with Adaptive Neuro‐Fuzzy Inference System (PSO‐ANFIS), Chicken Search Optimization with Spike Neural Network (CSA‐SNN), Multiobjective Gray Wolf Optimization (MOGWO), Giant Trevally Tunicate Swarm Optimizer (GTTSO), and Multi‐Objective Optimization (MOO) approaches. The findings confirm that the proposed method enhances storage utilization, operational efficiency, and environmental sustainability. This study contributes to the development of intelligent storage‐centric EM systems suitable for next‐generation EV infrastructure.
- 5 August 2025
- Published by Wiley in Energy Storage
- Vol. 7 (5)
Energy Management in Photovoltaic‐Based Electric Vehicle Charging Systems With Battery Storage and Vehicle‐to‐Grid Support
The rapid growth of Electric Vehicles (EVs) and the increasing reliance on renewable energy sources (RESs) have highlighted the need for intelligent, storage‐optimized charging infrastructure. However, conventional photovoltaic (PV)‐based EV charging systems often suffer from intermittency, storage inefficiencies, and limited integration with the power grid, leading to increased operational costs and reduced sustainability. To address these challenges, this paper proposes a hybrid energy management (EM) framework that integrates a Pelican Optimization Algorithm (POA) and a Triple‐Memristor Hopfield Neural Network (TMHNN) for optimizing Battery Energy Storage Systems (BESS) and Vehicle‐to‐Grid (V2G) operations in PV‐powered EV charging systems. POA is employed to optimize power flow (PF) and storage scheduling, while TMHNN accurately forecasts energy demand, enabling dynamic coordination between PV generation, energy storage, and EV charging. Simulation results demonstrate that the suggested POA‐TMHNN approach significantly reduces the cost of energy (COE) to $0.0841/kWh and carbon emissions to 173 956 kg, outperforming benchmark methods such as Particle Swarm Optimization with Adaptive Neuro‐Fuzzy Inference System (PSO‐ANFIS), Chicken Search Optimization with Spike Neural Network (CSA‐SNN), Multiobjective Gray Wolf Optimization (MOGWO), Giant Trevally Tunicate Swarm Optimizer (GTTSO), and Multi‐Objective Optimization (MOO) approaches. The findings confirm that the proposed method enhances storage utilization, operational efficiency, and environmental sustainability. This study contributes to the development of intelligent storage‐centric EM systems suitable for next‐generation EV infrastructure.
- Open Access
- 1 March 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Power Electronics and Drive Systems (IJPEDS)
- Vol. 16 (1) , 431-439
Certain investigations on performance analysis of different converter designs for smart micro-grid systems
This paper proposes a grid-connected hybrid renewable power system. A LUO converter driven by ABC-PI controller is used to produce stable DC-link voltage. To enhance the voltage, a LUO converter is used, and the boosted voltage is regulated by an ABC-PI controller. Using the suggested optimization approach, the power fluctuation is kept at a low value. The execution of the proposed optimization is efficient, as it is simple and robust. It has a limited number of control parameters as compared to other approaches. The suggested method is described in complete detail, together with its converter and control mechanisms. The modeling and experimental results are validated to ensure that the system is feasible. The HRES is analyzed through simulation in MATLAB with converters like boost, SEPIC, and LUO. The results reveal that the LUO converter performs better with a minimum settling time of 0.175 seconds with a source current THD of 1.29%. From the modeling and the simulation results, it has been revealed that the proposed technology provides more reliable and steady power.
- 1 March 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Power Electronics and Drive Systems (IJPEDS)
- Vol. 16 (1) , 431-439
Open AccessCertain investigations on performance analysis of different converter designs for smart micro-grid systems
This paper proposes a grid-connected hybrid renewable power system. A LUO converter driven by ABC-PI controller is used to produce stable DC-link voltage. To enhance the voltage, a LUO converter is used, and the boosted voltage is regulated by an ABC-PI controller. Using the suggested optimization approach, the power fluctuation is kept at a low value. The execution of the proposed optimization is efficient, as it is simple and robust. It has a limited number of control parameters as compared to other approaches. The suggested method is described in complete detail, together with its converter and control mechanisms. The modeling and experimental results are validated to ensure that the system is feasible. The HRES is analyzed through simulation in MATLAB with converters like boost, SEPIC, and LUO. The results reveal that the LUO converter performs better with a minimum settling time of 0.175 seconds with a source current THD of 1.29%. From the modeling and the simulation results, it has been revealed that the proposed technology provides more reliable and steady power.
- 28 February 2024
- Published by Springer Nature in Analog Integrated Circuits and Signal Processing
- Vol. 119 (2) , 215-232
An optimization approach control of EV solar charging system with step-up DC–DC converter
- 28 February 2024
- Published by Springer Nature in Analog Integrated Circuits and Signal Processing
- Vol. 119 (2) , 215-232
An optimization approach control of EV solar charging system with step-up DC–DC converter
- Top Cited Papers
Influences of various metal oxide-based nanosized particles-added algae biodiesel on engine characteristics