Abstract:
This work is devoted to the development of mathematical model for analysis of electrochemical impedance spectra of chemical power sources. Due to the complex inner structure of modern chemical batteries a new modelling approach, non-reliant on manual expertise, is required to analyze big quantities of battery data. While the existing mathematical models are predominantly tailored for online battery management, the battery
sorting task is an increasingly important challenge: choosing the best batteries with the
closest impedance characteristics to be assembled into battery packs. Therefore, a
mathematical model based on an autoencoder neural network is proposed as an effective
tool for dimension reduction and removal of outlier batteries. The work shows the advantages of the developed neural network architecture, composed of recurrent and convolutional layers, over the basic convolutional architecture for formalizing and analyzing impedance spectra. The impact of dataset augmentation by equivalent electrical circuits and
utilizing class labels on the accuracy of the autoencoder and its latent space is evaluated.
Implementation of the developed mathematical model is compared with other solutions
for impedance-based management and sorting of lithium-ion power sources.
Fulltext:
PDF file (890 kB)
First page:
PDF file