MagBridge-Battery: A Synthetic Bridge Dataset for Li-ion Magnetometry and State-of-Health Diagnostics

arXiv:2605.20240 · 2026-05-21 공개 · arXiv · PDF

anomaly-detection synthetic-dataset state-of-health magnetometry soh-regression battery-diagnostics pulsebat magbridge-battery

Abstract

Battery health diagnostics today rely overwhelmingly on electrochemical signals measured at the cell terminals. A parallel literature has shown that magnetic sensing can resolve information that terminal-only measurements miss, but method development is limited by the absence, to the best of our knowledge, of public battery magnetic-measurement datasets paired with degradation labels. We release MagBridge-Battery v1.0, a synthetic dataset of 6,760 magnetic-field signatures that bridges real magnetic morphology from the Mohammadi-Jerschow Open Science Framework (OSF) archive with state-of-health (SOH) labels from the PulseBat dataset. The release contains 5,600 PulseBat-conditioned grounded samples, 600 synthetic sensor-anomaly samples derived from clean parents, and 560 low-voltage Regime-B extrapolation samples. A cell-disjoint, parent-child-leakage-free primary benchmark split is verified to contain zero overlapping cells, zero cross-split parent-child pairs, and zero sample-ID overlap. We define three primary benchmark tasks: SOH regression, second-life classification, and anomaly detection, plus an auxiliary anomaly-subtype classification task. A controlled label-shuffle ablation collapses SOH regression from R^2 approximately 0.77 to approximately 0, confirming that the bridge encodes input SOH non-trivially rather than producing label-aligned artifacts. The dataset is released on Zenodo under CC-BY-4.0, and the bridge code and benchmark suite are released under Apache-2.0. This work provides a public benchmark for magnetic-sensing battery diagnostics while paired magnetic-electrochemical measurements remain scarce.

한국어 요약

📋 한 줄 요약

**[배터리 진단 / 합성 데이터셋]** 자기장 형상과 SOH(상태 건강도) 라벨을 결합한 최초의 공개 합성 데이터셋 MagBridge-Battery v1.0과 SOH 회귀·2차수명 분류·이상탐지 벤치마크 공개.

🎯 핵심 기여도

💡 핵심 아이디어

실제 자기장-전기화학 페어 측정이 희소한 현실에서, 실제 자기 형상과 외부 SOH 라벨을 통계적·물리적으로 연결한 "합성 브리지"를 통해 진단 모델 개발에 필요한 표준 벤치마크를 만들 수 있다는 발상.

🔬 기술적 접근법

📊 주요 결과

💭 의의 및 한계

**의의**: 자기 센싱 기반 배터리 진단 연구의 첫 공개 벤치마크로서 후속 알고리즘 비교의 기준점을 제공. **한계**: 합성 데이터의 본질적 한계로 실제 자기 측정-실제 전기화학 신호 페어를 완전 대체하지는 못하며, 실제 디바이스 측정값으로의 도메인 갭 검증이 필요.

🚀 실용적 활용