Quantified Assessment of Internal Short-Circuit State for 18 650 Batteries Using an Extreme Learning Machine-Based Pseudo-Distributed Model

To facilitate the diagnosis of battery internal short circuit (ISC) using thermal behaviors, this work integrates several thermal effects, including the commonly ignored heat conduction hysteresis and radiation, to elaborate a lumped thermal model. Then, a pseudo-distributed model structure is built up to approximate the characteristics of real batteries by synthesizing multiple isomorphic electrical/thermal submodels with the extreme learning machine network. Besides, three kinds of configurable destructions are conducted to incur ISC consequences. From thermal and electrical model residuals, four ISC features are extracted and the multiclass relevance vector machine is utilized to assess ISC intensity, in which not only qualitative judgments are given but also quantitative confidences can be derived according to the posterior probabilities. Finally, experiments on 18650 Li-ion cells verify the reliability of the synthesized models and suggest that the diagnosis scheme can recognize ISC faults effectively with low grade and state misjudgment rates (14.59% and 3.13%, respectively).

Automated summary

This research proposes a method for diagnosing battery internal short circuit using thermal behaviors. By integrating thermal effects and utilizing a multiclass relevance vector machine to assess short circuit intensity, ISC faults can be effectively recognized.