发表机构
Korea Institute of Energy Research; University of Science & Technology（韩国能源研究院; 科学技术联合大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出针对工业设备系统的窄而深本体塔，经实验验证，该本体可提升LLM智能体避免任务误判的概率，使中小参数模型达到大模型的任务得分，助力智能体将控制变量调整至目标区间。
AI 中文摘要
大语言模型（LLM）智能体开始用于操作工业能源设备，其运行效果取决于对工厂的相关信息输入。已有的建筑本体命名了多个站点的各类测点，而工业设备系统仅需少量实体，且每个实体需具备丰富知识。本研究提出本体塔（ontology tower），这是针对单一设备系统的窄而深的本体，其知识通过两种方式深化：一是通过物理关系从测点测量值推导得到的量，二是通过纳入知识节点的运行日志经验。在一个由可编程逻辑控制器（PLC）每日运行的真实低湿度空气处理测试工厂中，智能体接收从该本体塔投影的文本，参与一项预注册评估，评估包含从工厂记录中复现的9项任务，使用4个参数规模从90亿到约7500亿的开源模型。该知识使智能体避免每项任务最合理误判的概率提升了约20个百分点，且90亿参数模型的整体任务得分达到了最大模型的水平。运行经验在纳入本体塔或作为记录置于提示词中时会被使用，但在搜索工具后以日志形式留存时很少被使用。在通过不变安全层的实时运行中，智能体在14次运行中有12次将控制变量调整至目标区间。因此，实体数量少但相关知识深的本体可为工业设备系统智能体提供所需知识。
英文摘要
Large language model (LLM) agents are beginning to operate industrial energy equipment, and what they get right depends on what they are told about the plant. Established building ontologies name many kinds of points across many sites, whereas an industrial equipment system needs few entities with much knowledge about each. This study proposes the ontology tower, a narrow-and-deep ontology of a single equipment system whose knowledge deepens in two ways: through quantities derived from the measured points by physical relations, and through lessons from the operating journal incorporated as knowledge nodes. On a real low-humidity air-handling test plant operated daily through a programmable logic controller, agents received a text projected from its tower in a preregistered evaluation of nine tasks replayed from the plant's records, using four open-weight models from 9 to about 750 billion parameters. This knowledge raised the rate at which the agents avoided the most plausible misjudgment of each task by about 20 percentage points, and the overall task score of the 9-billion-parameter model as much as that of the largest. Operating lessons were used when incorporated into the tower or placed in the prompt as records, but seldom when left in the journal behind a search tool. In live runs through an invariant safety layer, the agents brought the controlled variable into its target band in 12 of 14 runs. An ontology narrow in entities but deep in what is known about them can thus supply the knowledge that an agent for an industrial equipment system needs.
Comments28 pages, 6 figures, 3 tables
