TADI: Tool-Augmented Drilling Intelligence via Agentic LLM Orchestration over Heterogeneous Wellsite Data
TADI: Tool-Augmented Drilling Intelligence via Agentic LLM Orchestration over Heterogeneous Wellsite Data
TADI：基于代理大模型编排异构井场数据的工具增强钻井智能
Abstract: We present TADI (Tool-Augmented Drilling Intelligence), an agentic AI system that transforms drilling operational data into evidence-based analytical intelligence. Applied to the Equinor Volve Field dataset, TADI integrates 1,759 daily drilling reports, selected WITSML real-time objects, 15,634 production records, formation tops, and perforations into a dual-store architecture: DuckDB for structured queries over 12 tables with 65,447 rows, and ChromaDB for semantic search over 36,709 embedded documents.
摘要： 我们提出了 TADI（工具增强钻井智能），这是一个将钻井作业数据转化为基于证据的分析智能的代理式人工智能系统。TADI 应用于 Equinor Volve 油田数据集，将 1,759 份每日钻井报告、精选的 WITSML 实时对象、15,634 条生产记录、地层顶界和射孔数据整合到一个双存储架构中：使用 DuckDB 对包含 65,447 行数据的 12 个表进行结构化查询，并使用 ChromaDB 对 36,709 个嵌入文档进行语义搜索。
Twelve domain-specialized tools, orchestrated by a large language model via iterative function calling, support multi-step evidence gathering that cross-references structured drilling measurements with daily report narratives. The system parses all 1,759 DDR XML files with zero errors, handles three incompatible well naming conventions, and is backed by 95 automated tests plus a 130-question stress-question taxonomy spanning six operational categories.
十二种领域专用工具由大语言模型通过迭代函数调用进行编排，支持多步骤的证据收集，将结构化的钻井测量数据与每日报告叙述进行交叉引用。该系统以零错误解析了全部 1,759 份 DDR XML 文件，处理了三种不兼容的井命名规范，并由 95 项自动化测试以及涵盖六大作业类别的 130 个压力测试问题分类体系提供支持。
We formalize the agent’s behavior as a sequential tool-selection problem and propose the Evidence Grounding Score (EGS) as a simple grounding-compliance proxy based on measurements, attributed DDR quotations, and required answer sections. The complete 6,084-line, framework-free implementation is reproducible given the public Volve download and an API key, and the case studies and qualitative ablation analysis suggest that domain-specialized tool design, rather than model scale alone, is the primary driver of analytical quality in technical operations.
我们将代理的行为形式化为一个顺序工具选择问题，并提出了证据基础评分（EGS），作为一种基于测量数据、归因 DDR 引文和所需答案部分的简单基础合规性代理指标。该实现包含 6,084 行代码，且不依赖特定框架；在获取公开的 Volve 数据下载和 API 密钥后即可复现。案例研究和定性消融分析表明，领域专用工具的设计，而非单纯的模型规模，是技术作业中分析质量的主要驱动因素。