首页>
外国专利>
Method to construct a Digital Twin by combining Reduced Order Models, Measurement Data and Machine Learning Techniques for a Multiphysical Engineering System
Method to construct a Digital Twin by combining Reduced Order Models, Measurement Data and Machine Learning Techniques for a Multiphysical Engineering System
展开▼
机译:通过组合减少订单模型,测量数据和机器学习技术来构建数字双胞胎的方法,用于多职业工程系统
展开▼
页面导航
摘要
著录项
相似文献
摘要
An object of the present invention is to provide a digital twin construction method capable of real-time monitoring, driving improvement, and response in the event of an accident in an industrial site by combining the order reduction model of a multi-physical system, field data, and artificial intelligence techniques. The digital twin construction method according to the present invention includes a network definition step of defining a multiphysical facility system as a network composed of a combination of element facilities; A component model establishment step of establishing a relational expression-based 0-D model for each component facility; A system model establishment step, which reflects the additional relational expressions by machine learning from 3-D CAE ROM or data for the core element equipment to make the closure of all the relations for the system; a system ROM building step of building a system ROM for the system model established in the system model establishing step, from the calculation results for the conditions sampled in the operating variable parameter space; a system ROM correction step of minimizing the error between the model prediction value and the measurement data for the element equipment and system; and a real-time algorithm building step of constructing an algorithm for identifying an expected system state or optimal driving condition in a virtual driving condition based on the real-time monitoring result.
展开▼