Operando state monitoring of diversified lithium-ion batteries via laser-excited ultrasonic sensing with transformer networks.

Emerging contact-based and immersion-based piezoelectric ultrasonic techniques encounter challenges in achieving accurate battery state monitoring under high-rate operations, where temperature fluctuations distort ultrasound and couplant contamination compromises practical applicability. Here, we propose air-coupled (couplant-free), noncontact laser-excited ultrasonic sensing (LEUS) with transformer networks for operando battery state estimation. The unique LEUS system pioneers a dual-laser design that uses a ring-shaped pulsed laser and a continuous laser to generate and detect high-quality ultrasound with a 10-fold increase in amplitude and a signal-to-noise ratio of 30 dB (16 dB higher than typical configurations), thereby enabling precise tracking of internal changes associated with state of charge (SoC) and state of health (SoH). By transforming ultrasonic signals into time-frequency scalograms, transformer networks autonomously extract discriminative features, eliminating manual feature engineering while achieving accurate prediction with mean errors below 5.7% for SoC and 2.1% for SoH. Through transfer learning, the base model generalizes rapidly to unseen chemistries, high-rate cycling, reducing training time and cost with minimal ultrasonic data. Extensive validation on over 100,000 ultrasonic signals from 40 commercial batteries, spanning two chemistries, three capacities, and 13 protocols, demonstrates the method's robustness and reliability for operando battery state monitoring, paving the way for next-generation battery-management systems.