用模板统一制造AI的仿真与数据规范，解决真实数据难获取问题。
Template-as-Ontology: Configurable Synthetic Data Infrastructure for Cross-Domain Manufacturing AI Validation
- 一个配置文件同时定义仿真规则和数据分析结构，确保数据一致。
- 在6类制造业场景中验证，关键指标均在设定范围内，参数可控性高。
- 能彻底杜绝AI幻觉，适合需要可靠数据的工业AI研发团队。
基于大语言模型的制造AI代理需大量符合格式的数据进行验证，但生产系统中的MES数据受版权、隐私和厂商限制难以获取。本文提出“模板即本体”原则：一个700-770行的Python配置模块，既作为时间步进式制造仿真器的规格说明，又作为AI分析工具的运行时领域模式，通过单一源消费实现仿真与工具层的结构对齐。我们正式将领域模板定义为带类型的关联配置模式，并证明其结构一致性由单源使用保证。五层流水线（仿真、PostgreSQL、CDC/Iceberg湖仓、星型模式、12个参数化AI工具）生成涵盖4个运营域、66种实体类型、符合MES特征的因果一致数据，映射至ISA-95/IEC 62264标准。在航空航天、制药、汽车、电子、饮料、仓储六类工业模板上验证，相同框架代码下表现一致。校准实验（60次运行，每模板10个种子）确认参数可控性：所有模板中观测到的关键绩效指标均落在配置范围内。受控幻觉实验（72次工具调用，Qwen3-32B）显示：本体约束下的参数不会产生虚构（0%幻觉率），而无约束条件下为43%（Fisher精确检验，p < 10^-12）；0%幻觉率是架构保证，适用于任意模型。该框架为离散制造领域的AI验证提供可复用的数据层。
原文摘要 · Abstract (English)
LLarge language model (LLM)-based AI agents deployed in manufacturing environments require populated, schema-correct data for validation, yet production MES data is proprietary, privacy-encumbered, and vendor-specific. This paper introduces the Template-as-Ontology principle: a single Python configuration module (700-770 lines, 45 validated exports) serves simultaneously as the specification for a time-stepped manufacturing simulator and as the runtime domain schema for AI analytics tools, producing alignment by construction rather than integration. We formally define the domain template as a typed relational configuration schema and prove that structural alignment between simulation and tool layers is guaranteed by single-source consumption. A five-layer pipeline--simulation, PostgreSQL, CDC/Iceberg lakehouse, star schema, and 12 parameterized AI tools--generates causally coherent, MES-shaped data spanning 66 entity types across four operational domains mapped to ISA-95/IEC 62264. We validate the architecture with six industry templates (aerospace, pharma, automotive, electronics, beverages, warehousing) running on identical framework code. Calibration experiments (60 runs, 10 seeds per template) confirm parametric controllability: observed KPIs fall within configured ranges across all templates. A controlled hallucination experiment (72 tool invocations, Qwen3-32B) demonstrates that ontology-constrained parameters eliminate tool-parameter fabrication (0% constrained vs. 43% unconstrained hallucination rate for the evaluated model, Fisher's exact test p < 10^-12); the 0% constrained rate is an architectural guarantee that holds for any model. The framework provides a reusable data layer for discrete manufacturing AI validation.
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。