The Gappy POD algorithm for reconstructing the core temperature of energy storage battery packs and its comparison with BP neural network prediction ability

Real time monitoring of core temperature in energy storage battery packs is of great significance for preventing and controlling thermal runaway of batteries. To overcome the problem of incomplete temperature data acquisition caused by the inability to arrange multiple temperature measurement points inside the battery pack in industrial practice. This article introduces the Gappy POD reconstruction algorithm into the real-time monitoring of the core temperature of energy storage batteries, predicting the internal core temperature by monitoring the surface temperature of the battery pack. This article simulates battery temperature rise by building a simplified simulated energy storage battery experimental platform, tested the stability and real-time reconstruction ability of the Gappy POD algorithm under stable and drastic changes in operating conditions. Compared the reconstruction ability of the Gappy POD algorithm with the prediction ability of the BP（Back Propagation ) neural network, and explored the reconstruction and prediction capabilities of the Gappy POD algorithm and BP neural network under different database size training conditions. The research in this article indicates that the Gappy POD reconstruction algorithm has high prediction accuracy, strong algorithm stability, and low dependence on database data volume, this provides a foundation for the practical application of algorithms in thermal management of energy storage batteries.