Lithium-ion battery remaining useful life prediction based on random forest machine learning
Accurately forecasting the Remaining Useful Life (RUL) of lithium-ion batteries is essential for maintaining reliability and maximizing the performance of battery powered systems. Traditional Random Forest Regression (RFR) techniques have demonstrated strong accuracy but often face computational cha...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | |
| التنسيق: | Thesis-Master by Coursework |
| اللغة: | English |
| منشور في: |
Nanyang Technological University
2025
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://hdl.handle.net/10356/182343 |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| المؤسسة: | Nanyang Technological University |
| اللغة: | English |
| الملخص: | Accurately forecasting the Remaining Useful Life (RUL) of lithium-ion batteries is essential for maintaining reliability and maximizing the performance of battery powered systems. Traditional Random Forest Regression (RFR) techniques have demonstrated strong accuracy but often face computational challenges as data dimensionality grows. Random Projection Forests (RPF) offer a promising solution by integrating random projections into the ensemble framework. They retain the predictive capabilities of RFR while significantly reducing computational overhead. This dissertation investigates the application of RPF and RFR algorithms to lithiumion battery RUL prediction, evaluating their accuracy, scalability, and adaptability to complex, high-dimensional data. The findings show that RPF achieves predictive performance comparable to RFR, yet with improved computational efficiency, thereby providing practical guidance for implementing more effective and resource-efficient battery management strategies. |
|---|