Productizing Microfluidic Technology for Real-time Lubricating Oil Analysis on Wind Turbines

“海上风电行业操作和维护（O&M）实践的自动化是降低成本的核心。海上风电场地处偏远，这意味着任何对人工干预的需求都会推高运维成本。这使得我们的家庭获得海上风能的成本在英国排名第二。到目前为止，为风力发电场项目所有者和原始设备制造商（oem）提供关键涡轮机部件（如变速箱和传动系统）的关键机器健康信息的润滑油分析过程的自动化一直很困难。这导致仅去年一年全球就有大约3.2万个变速箱发生故障。这种故障本可以通过正确的技术及早发现。早期诊断风力涡轮机部件的潜在故障对涡轮机的运行至关重要。rab - microfluics开发了尖端的微流控芯片实验室技术，可提供润滑油的实时连续测试和分析。我们的“芯片实验室”技术比目前的“将样品送到实验室”方法快1000倍，便宜10倍。分析机油、变速箱、传动系统等中的污染物是一种行之有效的检测问题的方法。这个程序称为油况监测。我们现场实时交付，节省成本，提高设备可靠性。我们通过开发机器学习能力，将硬件技术与数据计算相结合，利用硬件产生的大数据。这为客户提供实时连续监控，早期问题诊断，快速决策，提高效率和节约成本。到目前为止，我们已经收到了不同程度的资金，以实验室为基础的原型来展示这项技术。尽管如此，该项目旨在以此为基础，开发一个现场演示器，让项目所有者和原始设备制造商参与现场试验，并实现我们的技术所能提供的实际价值。这项技术将使我们能够解决风电行业难以触及和难以感知的挑战，利用我们智能和创新地生成的数据来预测涡轮机的行为，并使企业沉浸在工业4.0中。我们推进维护策略的发展，以确保设备可靠性，提高整体设备效率（OEE），并通过扩展涡轮机的可靠性。这可以减少对涡轮机进行物理干预的需求，并有效降低运维成本。这将有可能降低海上风电的电力成本，使海上风电与其他电力来源相比更具竞争力，并对我们的电费产生连锁反应。”

"The automation of Operation and Maintenance (O&M) practices in offshore wind sector is central to driving lower costs. The remote location of offshore wind farms means any requirement for physical human intervention pushes O&M costs upwards. This contributes to making the cost of getting offshore wind energy to our homes the second highest in the UK. Until now, it has been difficult to automate lubricating oil analysis processes that provide wind farm project owners and Original Equipment Manufacturer's (OEMs) crucial machine health information on key turbine components such as the gearbox and drivetrain. This resulted in breakdown of about 32,000 gearboxes globally last year alone. Such breakdowns could have been detected early by the right technology.Diagnosing early, potential failure of component parts in a wind turbine is critical to turbine operations. RAB-Microfluidics has developed cutting edge microfluidic lab-on-a-chip technology to deliver real-time continuous testing and analysis of lubricating oil. Our ""Lab-on-a-Chip"" technology delivers oil analysis 1000x faster and 10x cheaper than the current ""send the sample to the Laboratory"" approach. Analysis of contaminants in engine oil, gearboxes, drivetrains etc. is a well-established method of detecting problems. This procedure is called Oil Condition Monitoring. We deliver this onsite, in real time, saving cost and improving equipment reliability. We combine our hardware technology with data computing by developing machine learning capabilities to utilise the big data generated from our hardware. This offers customers real-time continuous monitoring, early problem diagnosis, rapid decision making, enhanced efficiency and cost savings.To date we have received various levels of funding to demonstrate the technology with laboratory based prototypes. Nonetheless, this project seeks to build on this and develop a field demonstrator to engage project owners and OEMs in field trials and in the reality of the value our technology can provide. This technology will enable us to solve the hard-to-reach and hard-to-sense challenges of the wind sector, using the data we generate intelligently and innovatively to forward model turbine behaviour and immerse businesses in industry 4.0\. We advance evolution of maintenance strategies to secure equipment reliability, increase Overall Equipment Effectiveness (OEE) and by extension reliability of turbines. This can reduce the need for physical intervention on turbines and effectively lower O&M costs. This will potentially reduce electricity costs from offshore wind, making offshore wind more competitive with other sources of electricity and ripple in effect to our electricity bills."