Modelling of asset (wind turbine) performance and health using optimized federated and transfer learning frameworks for lower carbon footprint

使用优化的联合和迁移学习框架对资产（风力涡轮机）性能和健康状况进行建模，以降低碳足迹

• 批准号: 2584476
• 金额: --
• 依托单位: Brunel University London
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2021
• 资助国家: 英国
• 起止时间: 2021 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2584476
• 关键词: Modelling; asset; wind; turbine; performance

This research project fits into a global context of sustainable development and protection of the environment and particularly into the UK energy policy for energy control and intelligent energy management. The UK low carbon (0 Carbon) plan has diversified primary energy sources exploited by hybrid energy systems, which needs a management and intelligent control methods. According to the Government Renewable Energy Strategy , The UK is aiming to reduce its carbon dioxide by over 750 million tonnes between now and 2030. To achieve such ambitious objectives, UK aims to increase renewables in the energy mix with 30% of the electricity, 12% of the heat and 10% of the transport energy generated from renewables. UK will invest in various renewable energy sources, but the focus is on wind energy and particularly offshore wind energy. The capacity is predicted to increase from 40GW now to 66GW in 2030 and up to 126GB by 2050 to meet the UK's 2050 Net 0 target.

该研究项目符合可持续发展和环境保护的全球背景，特别是英国能源控制和智能能源管理的能源政策。英国的低碳（0 Carbon）计划使混合能源系统开发的一次能源多样化，这需要一种管理和智能控制方法。根据政府可再生能源战略，英国的目标是从现在到2030年减少超过7.5亿吨的二氧化碳。为了实现这一雄心勃勃的目标，英国的目标是增加可再生能源在能源结构中的比重，其中30%的电力、12%的热能和10%的交通能源来自可再生能源。英国将投资各种可再生能源，但重点是风能，特别是海上风能。预计容量将从现在的40GW增加到2030年的66GW，到2050年将达到126GB，以实现英国2050年的净0目标。