| Proj No. | A1122-251 |
| Title | Multi-Modal Machine Learning for Battery State Estimation |
| Summary | Accurate battery state estimation is essential for improving the safety, efficiency, and longevity of modern energy storage systems, particularly in applications such as electric vehicles and renewable energy storage. Traditional estimation methods often rely on simplified models that may not fully capture the complex interactions between electrical, thermal, and material properties, leading to limitations in real-world performance. This project aims to develop an advanced machine learning-based framework for predicting key battery states, including State of Charge (SOC), State of Health (SOH), and degradation trends, under varying operating conditions. By leveraging data-driven techniques such as deep learning, the model will extract meaningful patterns from multi-modal sensor data, enabling enhanced real-time monitoring and predictive maintenance. The selected student will collaborate with research staff and postgraduate researchers to refine model architectures, optimize feature selection, and ensure robust real-world applicability. |
| Supervisor | Ast/P Yang Yun (Loc:S2 > S2 B2C > S2 B2C 105, Ext: +65 67905406) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Water & Energy Research Laboratory (Loc: S2.1-B3-03) |
| Single/Group: | Single |
| Area: | Electrical Power and Energy |
| ISP/RI/SMP/SCP?: |