Orathai Kruthun
Research Subjects
Orathai Kruthun has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Chodchanok Attaphong
Department of Civil Engineering, School of Engineering King Mongkut's Institute of Technology Ladkrabang Bangkok Thailand
1 shared publication John F. Katers
1 shared publication- Nattaya Morawan1 shared publication
Pasut Groudsorn
1 shared publication- Piampoom Sarikprueck
Department of Electrical Engineering, Faculty of Engineering, King Mongkut's Institute of Technology Ladkrabang, Bangkok, Thailand
1 shared publication Zhaohao Ding
1 shared publication
Latest Publications
- Open Access
- 22 July 2026
- Published by Elsevier in SSRN Electronic Journal
Enhancing SoC Estimation of Lithium-ion Battery Pack using Deep Learning Approaches Considering Battery Internal Resistance
To effectively use lithium-ion battery in various applications, the State of Charge (SoC) and its estimation play a crucial role in improving system reliability and optimizing operational performance to maximize battery lifetime and minimize its degradation. To support this function, it is necessary to achieve accurate SoC estimation with a fast computational time. Therefore, this paper proposes an enhanced SoC estimation approach for lithium-ion battery packs using deep learning techniques combined with the battery internal resistance (BIR) model. The tests consist of discharging tests with constant-current and constant-power loads and charging tests with constant-current and constant-voltage (CC/CV) at ambient temperature. Three different deep learning techniques with feedback, including Recurrent Neural Network (RNN), Long Short-term Memory (LSTM), and Gated Recurrent Unit (GRU), are evaluated compared to the conventional Neural Network (NN). The effectiveness of the proposed models is validated in terms of prediction accuracy using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), computational time, and performance evaluation indices. As a result, deep learning models with BIR can significantly reduce SoC estimation errors while maintaining acceptable computational time efficiency. Furthermore, the proposed LSTM with BIR model provides the most suitable model in terms of prediction accuracy and computational time indicated by the performance evaluation indices among the presented methods.
- 22 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessEnhancing SoC Estimation of Lithium-ion Battery Pack using Deep Learning Approaches Considering Battery Internal Resistance
To effectively use lithium-ion battery in various applications, the State of Charge (SoC) and its estimation play a crucial role in improving system reliability and optimizing operational performance to maximize battery lifetime and minimize its degradation. To support this function, it is necessary to achieve accurate SoC estimation with a fast computational time. Therefore, this paper proposes an enhanced SoC estimation approach for lithium-ion battery packs using deep learning techniques combined with the battery internal resistance (BIR) model. The tests consist of discharging tests with constant-current and constant-power loads and charging tests with constant-current and constant-voltage (CC/CV) at ambient temperature. Three different deep learning techniques with feedback, including Recurrent Neural Network (RNN), Long Short-term Memory (LSTM), and Gated Recurrent Unit (GRU), are evaluated compared to the conventional Neural Network (NN). The effectiveness of the proposed models is validated in terms of prediction accuracy using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), computational time, and performance evaluation indices. As a result, deep learning models with BIR can significantly reduce SoC estimation errors while maintaining acceptable computational time efficiency. Furthermore, the proposed LSTM with BIR model provides the most suitable model in terms of prediction accuracy and computational time indicated by the performance evaluation indices among the presented methods.
- Open Access
- 14 May 2026
- Published by Elsevier in Chemical Engineering Journal Advances
- Vol. 26
Optimization of chemical precipitation for valuable metal recovery from spent lithium nickel manganese cobalt oxide batteries
- 14 May 2026
- Published by Elsevier in Chemical Engineering Journal Advances
- Vol. 26
Open AccessOptimization of chemical precipitation for valuable metal recovery from spent lithium nickel manganese cobalt oxide batteries