A deep learning-based framework for battery reusability verification: one-step state-of-health estimation of pack and constituent modules using a generative algorithm and graphical representation

As the electric vehicle market continues to surge, the proper assessment of used batteries has become increasingly important. However, current technologies for assessing used batteries, which involve separately estimating the State-of-Health (SoH) of the pack and its individual modules, require multiple times of cycling tests and lead to time inefficiency and power consumption. The proposed DeepSUGAR, a deep learning-based framework for SoH estimation using a generative algorithm based on graphical representation techniques to reveal individual module health, offers the advantage of estimating the status of internal modules replying on battery pack SoH. The cycling profiles of a simultaneously measured 14S7P pack and its constituent modules were analyzed, and a convolutional neural network (CNN) was trained by spatializing cycling curves to estimate SoH. DeepSUGAR, trained on pack data, showed outstanding performance with an RMSE of 5.31 x 10-3 and its applicability was validated by testing with module data, resulting in an RMSE of 7.38 x 10-3. Furthermore, the generated module cycling profiles from pack SoH using the deep generative model were fed into the trained CNN and showed a remarkable performance with an RMSE of 8.38 x 10-3. DeepSUGAR can significantly reduce power consumption, processing cost, and carbon dioxide emissions by integrating module-level diagnosis within the pack-level assessment process. A non-invasive approach to reveal the health of individual modules, replying on the state-of-health of the battery pack, is achieved through generative adversarial networks (GAN) with spatialized battery pack cycling profiles.

Automated summary

This article introduces a deep learning-based framework for assessing the State-of-Health (SoH) of used batteries. The framework, called DeepSUGAR, utilizes a generative algorithm and graphical representation techniques to reveal the health status of internal battery modules. By spatializing cycling curves and training a convolutional neural network (CNN), DeepSUGAR achieves outstanding SoH estimation performance. Additionally, the generated module cycling profiles can be estimated accurately using the trained CNN. By integrating module-level diagnosis within the pack-level assessment process, DeepSUGAR significantly reduces power consumption, processing cost, and carbon dioxide emissions.