Ensemble Learning and Voltage Reconstruction Based State of Health Estimation for Lithium-Ion Batteries With Twenty Random Samplings

Abstract

Accurate estimation of state of health (SOH) is critical for the safe and efficient operation of lithium-ion batteries in electric transport tools. However, the random charge/discharge behaviors complicate online SOH estimation and discount estimation accuracy. To overcome this difficulty, this study presents an ensemble learning and voltage reconstruction-based SOH estimation framework through the incorporation of individual estimators and with the consideration of limited charging data. First, by analyzing more than 100 000 charging behaviors, the difficulty of feature extraction is addressed based on voltage distribution. Then, a voltage shape fitting method combing mechanistic and prognostic model is developed to reconstruct the constant current charge voltage, and the model parameters are identified by the moth-flame optimization algorithm. Next, the extreme learning machine and random forest are leveraged to estimate SOH preliminarily from the random discontinuous charging points with preferable diversity and high efficiency. On this basis, an induced ordered weighted averaging operator is exploited to efficiently integrate the individual learners and adaptively update the weight of each learner, thereby achieving better estimation than individual ones. The experimental results manifest that the SOH can be reliably estimated within an error of 3.42% using only 20 random samplings.