Next generation predictive maintenance for wind turbine blade/hub/rotor through novel online condition monitoring/root cause analysis: MONTURWIND

通过新颖的在线状态监测/根本原因分析对风力涡轮机叶片/轮毂/转子进行下一代预测性维护：MONTUWIND

• 批准号: 10041137
• 金额: $ 52.86万
• 依托单位: SENSONICS LIMITED
• 依托单位国家: 英国
• 项目类别: Collaborative R&D
• 财政年份: 2023
• 资助国家: 英国
• 起止时间: 2023 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=10041137
• 关键词: Next; generation; predictive; maintenance; wind

Wind energy capacity is set to grow tenfold by 2050 in order to mitigate climate change. Unfortunately, wind turbine (WT) operation and maintenance (O&M) cost is twice as high as photovoltaic and fossil fuel power plants due to high frequency of very expensive unplanned repairs.The major areas of issue are rotating components of turbine rotor and drivetrain including blades, hub, low-speed shaft, main rotor bearing, gearbox and generator. Repair costs are increased by high crane hire cost, or even more expensive jack-up vessel charter costs (~£90k/day) for offshore WTs.WTs are equipped with condition monitoring (CM) systems to detect drivetrain faults, however no system in the market or in development monitors blades (a glass / carbon polymer structure), and hub, low-speed shaft without embedded sensors or non-destructive testing / inspection techniques. Embedded sensors are difficult to retrofit and maintain. Inspection requires shutdown in order to carry out non-destructive testing or manual inspections. Optical and IR cameras, robotic and drone solutions exist but they are expensive, cumbersome or limited in types of faults that can be detected. Manual inspections present health and safety problems due to tower climbs and rope access work.The project will develop a radically novel automatic online CM / root cause analysis system capable of detecting blade / hub / shaft dangerous faults without embedded sensors. Technology is underpinned by sophisticated signal processing and AI to deliver a cost effective, easily retrofitted solution. Blade / shaft / hub fault detection unlocks access to a \>$4.23 billion market opportunity. Based on projected sales, the industry will save £893 million over five years by enabling inexpensive planned repairs rather than costly replacements and preventing fault re-occurrence by root cause detection / elimination. System sales will generate cumulative PBIT £10.5M (5 years), ROI 14.3 and PBIT 378M (10 years).

到2050年，风能容量将增长十倍，以减缓气候变化。不幸的是，由于非常昂贵的计划外维修频率高，风力涡轮机（WT）的操作和维护（O&M）成本是光伏和化石燃料发电厂的两倍。问题的主要领域是涡轮机转子和传动系统的旋转部件，包括叶片、轮毂、低速轴、主转子轴承、齿轮箱和发电机。海上WT的高起重机租用成本或甚至更昂贵的自升式船舶租赁成本（约90 k英镑/天）增加了维修成本。WT配备有状态监测（CM）系统以检测传动系统故障，但是市场上或开发中的系统都没有监测叶片（玻璃/碳聚合物结构）和轮毂、低速轴，而没有嵌入式传感器或非破坏性测试/检查技术。嵌入式传感器难以改造和维护。检查需要停机，以便进行无损检测或手动检查。存在光学和IR相机、机器人和无人机解决方案，但它们昂贵、笨重或可检测的故障类型有限。由于塔架攀爬和绳索进入工作，手动检查会带来健康和安全问题。该项目将开发一种全新的自动在线CM /根本原因分析系统，能够在无需嵌入式传感器的情况下检测叶片/轮毂/轴的危险故障。技术以复杂的信号处理和人工智能为基础，提供具有成本效益且易于改造的解决方案。叶片/轴/轮毂故障检测开启了42.3亿美元的市场机会。根据预测的销售额，该行业将在五年内节省8.93亿英镑，因为它可以实现廉价的计划维修而不是昂贵的更换，并通过根本原因检测/消除来防止故障再次发生。系统销售将产生累计PBIT 1050万英镑（5年），ROI 14.3和PBIT 3.78亿英镑（10年）。