Wind turbine sensor placement optimisation for digital twin development (OSP)

该项目将专注于开发一个最先进的整体监控系统，该系统可以收集，分析和解释从海上风电场获取的所有组件级数据，并远程做出运营和维护（O&M）决策。将开发先进的机器学习算法，以改善可以使用SCADA数据获取的信息。这将告知SCADA可以用于取代更昂贵的仪器的地方，以及部署传感器以开发更具信息性的预测状态监测系统的关键所在。将开发一个结合基于物理的模型分析和采集数据后处理的数字孪生模型。这将促进更好的O&M规划，从而提高维护流程的效率，降低O&M成本，减少技术人员离岸的需求，从而最大限度地提高OWT的可用性，并最终降低能源成本。（交易名称为Transmission Dynamics - TD），一家屡获殊荣的工程公司，拥有超过20年的设计和制造定制监测系统的经验，以测量在具有挑战性的环境中的关键参数，与Unasys有限公司（UNASYS），英国海洋可再生能源创新和研究旗舰中心--海上可再生能源弹射器（OREC）。该联盟的特点是提供项目所需的供应链的关键要素，以及在相邻部门的开发能力。该联盟将与美国的一个团队合作，由塔夫茨大学领导，该大学已批准一个名为“基于物理的数字双胞胎的最佳传感器放置”的项目，该项目将于2021年1月开始。他们的重点将是开发一个新的SPDT贝叶斯同化框架（BAF）的负载推断（LI），模型不确定性（MU），基础非线性（FN），和最佳传感器放置（OSP）的结构疲劳监测。这两个联盟将交换SCADA数据进行模型验证，并将共同制定一个路线图，以整合和商业化他们的技术，为全球开采开发世界领先的解决方案。该项目是两国之间的第一个此类双边合作，努力为未来更强大的合作铺平道路。

This project will focus on developing a state-of-the-art, holistic monitoring system that can collect, analyse, and interpret all component level data acquired from an offshore wind farm and make Operations & Maintenance (O&M) decisions remotely. Advanced machine learning algorithms will be developed to improve the information that can be acquired using SCADA data. This will inform where SCADA can be used in place of more expensive instrumentation, and where it is critical to deploy sensors in order to develop a more informative predictive condition monitoring system.A digital twin combining physics based model analysis and post-processing of acquired data will be developed. This will facilitate better O&M planning leading to more efficient maintenance processes, reduced O&M costs and a reduced need for technicians going offshore, thus maximising the availability of OWTs and ultimately reducing the levelized cost of energy.The project brings together JR Dynamics Ltd (trading as Transmission Dynamics - TD), an award-winning engineering company with over 20 years' experience of designing and manufacturing bespoke monitoring systems to measure critical parameters in challenging environments, with Unasys Limited (UNASYS), experts at developing digital models, and the Offshore Renewable Energy Catapult (OREC), the UK's flagship innovation and research centre for offshore renewables. The consortium features key elements of the supply chain required to deliver the project, as well as the capacity to exploit in adjacent sectors.The consortium will work in collaboration with a team in the U.S., led by Tufts University, who have an approved project titled "Optimal Sensor Placement for Physics-Based Digital Twins" commencing in January 2021\. Their focus will be to develop a new SPDT Bayesian Assimilation Framework (BAF) for load inference (LI), model uncertainty (MU), foundation nonlinearities (FN), and optimal sensor placement (OSP) for structural fatigue monitoring. The two consortia will exchange SCADA data for model validation and will work together to develop a roadmap for integrating and commercialising their technologies to develop a world leading solution for global exploitation.This project is the first of it's kind bilateral collaboration between the two countries, striving to pave the way for stronger future collaboration.