在数字孪生构建中整合韧性与人类监督 into LLM辅助建模工作流
On Integrating Resilience and Human Oversight into LLM-Assisted Modeling Workflows for Digital Twins
AI总结:
本文提出三种关键设计原则,用于将韧性与人类监督整合到LLM辅助的数字孪生建模工作流中,通过FactoryFlow框架的研究,探讨了如何通过正交化结构建模与参数拟合、限制模型IR到参数化预验证库组件以及使用密度保持的IR来提高建模的鲁棒性和可解释性。
摘要:
LLM辅助建模有潜力快速从粗略描述和传感器数据构建复杂的可执行数字孪生。然而,LLM幻觉的韧性、人类监督以及实时模型适应性仍然是具有挑战性的且常常相互冲突的要求。我们提出了三种关键的设计原则,用于将韧性和监督整合到此类工作流中,这些原则源于我们在FactoryFlow框架上的工作,该框架是一个开源的LLM辅助框架,用于构建制造系统的基于模拟的数字孪生。首先,正交化结构建模和参数拟合。结构描述(组件、连接)是通过LLM从粗略的自然语言转换为中间表示(IR),并进行人工可视化和验证,然后算法转换为最终模型。相比之下,参数推断则在传感器数据流上持续运行,并具有专家可调的控制。第二,限制模型IR到参数化、预验证的库组件的连接,而不是单体模拟代码,从而实现可解释性和错误韧性。第三,最重要的是使用密度保持的IR。当IR描述从紧凑的输入急剧扩展时,幻觉错误会成比例累积。我们提出了Python作为密度保持IR的案例:循环以简洁的方式表达规律性,类捕捉层次结构和组成,结果仍然保持高度可读性,同时利用LLM强大的代码生成能力。一个关键贡献是详细表征了LLM诱导的错误在不同详细程度和复杂度的模型描述中的表现,揭示了IR选择如何关键地影响错误率。这些见解为构建鲁棒和透明的LLM辅助模拟自动化工作流提供了可操作的指导。
英文摘要:
LLM-assisted modeling holds the potential to rapidly build executable Digital Twins of complex systems from only coarse descriptions and sensor data. However, resilience to LLM hallucination, human oversight, and real-time model adaptability remain challenging and often mutually conflicting requirements. We present three critical design principles for integrating resilience and oversight into such workflows, derived from insights gained through our work on FactoryFlow - an open-source LLM-assisted framework for building simulation-based Digital Twins of manufacturing systems. First, orthogonalize structural modeling and parameter fitting. Structural descriptions (components, interconnections) are LLM-translated from coarse natural language to an intermediate representation (IR) with human visualization and validation, which is algorithmically converted to the final model. Parameter inference, in contrast, operates continuously on sensor data streams with expert-tunable controls. Second, restrict the model IR to interconnections of parameterized, pre-validated library components rather than monolithic simulation code, enabling interpretability and error-resilience. Third, and most important, is to use a density-preserving IR. When IR descriptions expand dramatically from compact inputs hallucination errors accumulate proportionally. We present the case for Python as a density-preserving IR : loops express regularity compactly, classes capture hierarchy and composition, and the result remains highly readable while exploiting LLMs strong code generation capabilities. A key contribution is detailed characterization of LLM-induced errors across model descriptions of varying detail and complexity, revealing how IR choice critically impacts error rates. These insights provide actionable guidance for building resilient and transparent LLM-assisted simulation automation workflows.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。