可验证弃权使AI在供水管网泄漏诊断中具备可问责性
Verifiable abstention makes AI leak diagnosis accountable in urban water distribution networks
另 3 家 · 查看机构详情
- School of Municipal Engineering and Environment, Shenyang Jianzhu University（沈阳建筑大学市政工程与环境学院）
- Guangzhou Institute of Industrial Intelligence（广州工业智能研究院）
- College of Environment, Shenyang University（沈阳大学环境学院）
- Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）
- College of Environmental Science and Engineering, State Environmental Protection Engineering Center for Pollution Treatment and Control in Textile Industry, Donghua University（东华大学环境科学与工程学院（国家环境保护纺织污染防治工程技术中心））
- School of Information Science and Engineering, Shenyang University of Technology（沈阳工业大学信息科学与工程学院）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
该研究针对供水管网泄漏诊断中AI缺乏问责性的问题，提出结合执行器智能体、监督智能体与LLM审计员的可验证弃权决策方法，提升了决策精度与挖掘正确性，为自主水基础设施运营提供可行路径。
中文摘要 AI 辅助
公用事业公司因泄漏损失大量处理后的水，但很少信任人工智能定位器来派遣人员：到处猜测无法为挖掘提供依据。差距在于问责制而非准确性：没有方法能证明何时不应行动。本文将泄漏定位重新表述为可验证弃权下的决策问题。基于物理原理的执行器智能体针对数字孪生对假设（泄漏、需求、传感器、阀门）进行证伪；独立监督智能体结合大语言模型（LLM）审计员，对照可代码验证的合约检查证据，随后认证派遣、要求提供证据或弃权（不执行）。在现场级噪声下，32%的强制基线在已执行事件上达到96%的决策精度；在独立生成的基准测试中，仅对33处泄漏中的4处采取行动，且全部正确；在包含双模拟压力和流量的194个经审计真实泄漏位置记录中，产生5次挖掘派遣，其中3次正确，在全区域精度下实现44%的调查回收率。可问责弃权为自主水基础设施运营提供了可辩护的途径。
英文摘要
Leak localization is usually evaluated as forced-choice prediction, although sparse hydraulic observations may not justify excavation. Here, we quantify a pressure-information limit and use it to recast localization as selective, evidence-gated decision-making. A physics-grounded executor falsifies competing leak, demand, sensor and valve hypotheses in a hydraulic twin. Deterministic code computes every number and every acceptance predicate; an independent large language model auditor may add a rejection but never overturn a failed check. Forced retrieval placed only 95 of 300 leaks in the correct zone. Across 550 mixed events, the gate acted on 223 (214 correct); on a third-party 33-leak benchmark, all four accepted events were correct. In a replay of 194 audited City D repairs, the pressure tier authorized five excavation recommendations, three matching the repaired district, while the district-inflow tier returned the correct district for 85 events. Observability limits with machine-checkable abstention enable auditable utility intervention.
