One of the biggest challenges to growth remains the high costs of constructing wind farms, as well as the ongoing operations and maintenance costs. The industry also still relies heavily on government subsidies and federal tax incentives, which can be unreliable and phased out, depending on which way the winds of the current political climate are blowing. To further its growth, reduce costs, and increase profitability, the wind power industry is increasingly turning to emerging technologies such as AI, ML, edge computing, and IoT sensors and devices such as autonomous drones. These technologies are being combined in new and innovative ways to help wind farms automate costly and time-intensive operational tasks such as turbine inspections and are delivering real-time data insights that can help wind farms lower operational costs and improve efficiency for greater profitability.
Dongfeng Chen examines the required key hardware and software technologies used that enable the drones to fly autonomously, track the blade as they fly, and take HD pictures in motion. In addition to data collected by drones, Dongfeng explains how to use the power of deep learning and computer vision to do blade segmentation, massive foreground image stitching, and autodetection of blade defects. He explains drone autoflight algorithms (global path calculation); visual servoing for local path to support blade tracking; capture HD images in motion and manage high exposure, high reflection, and an outdoor environment; blade segmentation using the deep learning network; massive amounts of image stitching (40–60 images each time) for turbine blades; foreground image stitching using computer vision; and defect detection using the deep learning network.
Though many turbines today are equipped with a variety of IoT sensors measuring vibrations, sounds, and more, wind farm operators still need greater—and earlier—visibility into the condition of blades. For instance, by the time a turbine has degraded to the point where it is vibrating or creating an unusual noise, the damage is already severe. Regular visual inspections of blades are needed to identify cracks or other blade damage that can be fixed with a simple patch while still small. However, if an operator is not alerted to a problem until the blade is vibrating or whistling, they will likely need to shut down the turbine and replace the entire blade. This can cost the operation hundreds of thousands of dollars. This is where emerging technologies such as autonomous drones equipped with AI, ML, and advanced computer vision are making a dramatic impact. Traditionally, visual inspections required shutting down a turbine and sending one or more highly trained technicians up the tower, on ropes, to inspect the blades. A typical inspection could take six to eight hours per turbine. However, by using autonomous drones for visual inspections, wind farm operators are able to complete turbine inspections in as little as 15 minutes. With essentially the click of a button, the autonomous drone can fly itself up the turbine, conduct a detailed, visual inspection, and then land itself without the need for a human pilot. Wind farms first began experimenting with using drones for inspections several years ago, but those had to be manually piloted and required two highly trained operators: one to fly the drone without colliding into the turbine and the other to take photos of the blades. With today’s autonomous drones, only one operator is required, and that person needs only minimal training. The drone launches itself and, using built-in sensors and AI, closely tracks a precise path along each blade. Precision photography and advanced computer vision are used to automatically identify and flag defects such as hairline cracks or chips as small as 1 millimeter by 3 millimeters—all better than the human eye can.
Dongfeng Chen is the engineering director of Clobotics, a global leader in computer vision solutions for the wind power and retail industries. Clobotics has end-to-end solutions that combine computer vision, artificial intelligence/machine learning, and data analytics software with different hardware form factors, including autonomous drones, mobile applications, and other IoT devices to help companies automate time-intensive operational processes, increase efficiencies, and boost the bottom line using real-time, data-driven, and actionable insights. Clobotics has headquarters in Shanghai and Seattle and has expanded its footprint to Beijing, Dalian, and Singapore. Dongfeng currently leads the Clobotics retail research and development team in Shanghai.
Previously, he was a senior architect at Baidu. He recruited, led, and built a team of more than 30 members, including developers, testers, and product managers, and he created the core algorithms for Baidu advertisement and Baidu Kuaixing (online travel booking site), and Baidu Mall (a flash-sale ecommerce platform). He’s an expert in machine learning and distributed systems. His team developed a way to associate the Baidu search pool with paid advertisements, this in turn brought in more than tens of millions of US dollars in revenue, and this technology is still being used until today. In 2010, his team developed China’s first Groupon website for the travel industry; it was the first travel website that offers group bundle deals. Statistics shows the website accounts for 30%–50% of the market share of short-distance travel near Shanghai. This experience gave him a great foundation to build Baidu Kuaixing, Baidu’s online travel booking site, later on. He received his PhD in computer science from North Carolina State University. His thesis topic was on using structured views to optimize query in information integration.
陈东锋 博士 扩博智能高级研发总监。加入扩博智能之前，陈东锋博士曾担任百度高级架构师。任职期间，陈东锋博士管理和带领研发团 队专注于百度电商广告和百度快行业务的软件研发、测试和产品管理。并为百度快行、特卖频道和电 商知心等等项目开发了核心算法。陈东锋博士的工作成果通过知识图谱技术的创新运用把百度搜索池 与电商广告强相关，为百度在电商特卖领域带来从 0 到上亿人民币的持续巨额营收，该核心技术沿用 至今。陈东锋博士带领团队开发的百度快行项目的成功，使得百度汽车票和火车票交易业务在两年内 成为百度 O2O 垂直行业 GMV第一名，用户体验大大提升。
加入百度之前，陈东锋博士是一名经验丰富的连续创业者。2010 年陈东锋博士带领团队开发了国 内第一个旅游行业团购网站，据数据统计该网站占上海周边短途旅游交易额 30-50%市场份额，这也 为陈东锋博士研发百度出行业务提供了借鉴意义。
陈东锋博士拥有北卡罗来纳州立大学(North Carolina State University)计算机科学博士学位。他 的博士论文主题是使用结构化视图来优化信息集成中的查询。
陈东锋博士是扩博智能智慧零售研发负责人，负责产品研发及交付。扩博智能聚焦计算机视觉和机 器学习技术，专注为行业企业用户提供端到端一体化智能服务，能大力提升传统行业运营效率，加快 数字化变革，所服务的行业包括零售和风电。扩博智能总部位于中国上海和美国西雅图，在北京和大 连设有办事处，新加坡设有分公司。
Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?
Join the conversation here (requires login)
©2019, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • firstname.lastname@example.org