用智能代理+物理约束，自动整理分散的电池老化数据，构建可复现的基准测试
BatteryLake: Agentic, Physics-Grounded Curation of Heterogeneous Battery Aging Data and Benchmarking
- LLM代理基于原文提取元数据，仅当证据充分时才输出结果
- 通过26项规则验证数据，包含统计与物理合理性检查
- 发布41个数据集基准，支持多种任务和模型评估，开源可用
公开的电池老化数据集是先进健康管理的关键资源，但其实际应用常受限于格式不统一、结构不明确及元数据散落在多个库和论文中。现有整理方式多为人工操作，难以复现，通用数据整合工具又缺乏电化学时序数据的领域语义理解。本文提出BatteryLake，一个受控的数据湖仓架构，通过智能体驱动、物理基础的清洗框架，将原始公共数据转化为可直接用于基准测试的资产，主要贡献包括：第一，利用大模型代理从文献中提取元数据并生成数据转换器，所有输出均基于原文证据，无依据时则保持空白；第二，引入人机协作机制，将验证过程转化为选择性预测，并通过26项标准——涵盖数据模式、统计特性与物理合理性——筛选合格数据；第三，发布涵盖41个数据集的开放基准，来自超过25家机构，支持标准化的SOH与RUL任务、三种划分协议及八类基线模型。平台、基准与清洗流程均已开源，地址为https://tianwen1209.github.io/batterylake/。
原文摘要 · Abstract (English)
Public battery aging datasets are a critical asset for advanced health management, but their practical use is often limited by inconsistent formats, unclear schemas, and metadata scattered across repositories and publications. Current curation remains largely manual and hard to reproduce, while general-purpose data integration tools miss the domain-specific semantics of electrochemical time-series data. We present BatteryLake, a governed data lakehouse that turns raw public battery data into benchmark-ready assets through an agentic, physics-grounded curation framework, with three contributions. First, LLM agents extract metadata and synthesize dataset-specific converters, grounding every output in verbatim evidence and abstaining when none supports a value. Second, a human-in-the-loop mechanism frames verification as selective prediction and gates admitted data through 26 schema, statistical, and physical-plausibility rules. Third, we release an open benchmark of 41 datasets from over 25 institutions, with standardized SOH and RUL tasks, three split protocols, and eight baseline model families. The platform, benchmark, and curation protocol are publicly available at https://tianwen1209.github.io/batterylake/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。