NeuralFMU:FMU与神经网络的结构集成
NeuralFMU: Towards Structural Integration of FMUs into Neural Networks
摘要:
本文涵盖了两个主要主题:第一,介绍了一个新的开源库,称为FMI.jl集成到Julia编程环境,通过提供加载,参数化和模拟FMU的可能性。此外,引入了对该库的扩展FMIFlux.jl,其允许将FMU集成到神经网络拓扑中以获得NeuralFMU。行业典型的黑盒模型和数据驱动的机器学习模型的这种结构组合将两种建模方法的不同优势结合在一个单一的开发环境中。这允许使用先进的数据驱动建模技术,用于难以基于第一原理建模的物理效应。
英文摘要:
This paper covers two major subjects: First, the presentation of a new open-source library called FMI.jl for integrating FMI into the Julia programming environment by providing the possibility to load, parameterize and simulate FMUs. Further, an extension to this library called FMIFlux.jl is introduced, that allows the integration of FMUs into a neural network topology to obtain a NeuralFMU. This structural combination of an industry typical black-box model and a data-driven machine learning model combines the different advantages of both modeling approaches in one single development environment. This allows for the usage of advanced data driven modeling techniques for physical effects that are difficult to model based on first principles.
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。