Digital twin real time monitoring method of turbine blade performance based on numerical simulation. (1st November 2022)

• Record Type: Journal Article
• Authors: Cao, Yu; Tang, Xiaobo; Gaidai, Oleg; Wang, Fang
• Is Part Of: Ocean engineering. Volume 263(2022)
• Publication Date: 2022-11-01
• Subjects: Real time -- Digital twin -- HATT -- Kriging interpolation -- Machine learning; Ocean engineering -- Periodicals; Ocean engineering; Periodicals; 620.4162
• DOI: 10.1016/j.oceaneng.2022.112347
• Languages: English
• ISSNs: 0029-8018

Abstract

Abstract: Due to the limited number of sensor arrangements, the hydrodynamic performance test and detection of marine equipment cannot achieve real time monitoring and complete coverage of the flow field. The digital twin (DT) technology can solve this problem and help achieve real time monitoring and performance evaluation at sea. This paper takes the horizontal axis tidal turbine (HATT) as the research object, studies the applicability of the simulation-based DT real time monitoring method. Firstly, the feasibility of computational fluid dynamics (CFD) simulation of HATT is verified by experiments. Secondly, the simulation database is established under various working conditions. Then the DT method is used to reduce the three-dimensional numerical model to a first-order digital model and the simulation result data can be quickly loaded into the digital model for real time data monitoring. If the monitoring data is not calculated in the database, the Kriging interpolation method is used to reconstruct the database for flow field display quickly. For the data with large deviation of comparison result curves, the optimization algorithm is used along with machine learning. A real time monitoring engineering reference is provided for flow fields distribution and hydrodynamic performance assessment of blades. Highlights: The DT method proposed for HATT has a good performance match with tank experiments and simulations. The hydrodynamic performance test and detection of marine equipment achieve full coverage of the flow field. Digital twin approach allows for rapid real-time monitoring and evaluation. Physical space and digital space through data to achieve the purpose of self-learning.