How AI is Revolutionizing the Wind Power Industry

此演讲使用中文 (This will be presented in Chinese)

YAN KE (上海扩博智能技术有限公司)
16:2017:00 Thursday, June 20, 2019
实施人工智能 (Implementing AI)
Location: 多功能厅5A+B(Function Room 5A+B)

必要预备知识 (Prerequisite Knowledge)

All or one of the following: • Technical ability: Computer vision, deep learning, machine learning, edge computing, cloud computing, etc. • PM skill • Experience in starting a business

您将学到什么 (What you'll learn)

Building end-to-end AI solutions for traditional industries requires more than just AI algorithms, it also requires the ability to collect high quality data using smart hardware, in this case, drones. The audience can see how AI technology is used in the industry. What are the challenges of using AI in the industry and how can we solve them.

描述 (Description)

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 whichever 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 artificial intelligence (AI), machine learning (ML), edge computing, and Internet of Things (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.
Though many turbines today are equipped with a variety 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.

In this talk, Yan discusses the required key technologies used, both hardware and software, that enable the drones to fly autonomously, to track the blade as they fly, and take HD pictures in motion. In addition to data collected by drones, Yan also explains how to use the power of deep learning and computer vision to do blade segmentation, massive foreground image stitching and blade defects auto-detection.

Topics include:
• Drone autoflight algorithms (global path calculation)
• Visual servoing for local path to support blade tracking
• Caption HD images in motion and manage high exposure, high reflection, and outdoor environment
• Blade segmentation using deep learning network
• Massive amount image stitching (40-60 images each time) for turbine blades
• Foreground image stitching using computer vision
• Defect detection using deep learning network

Photo of YAN KE



Dr. Yan Ke is the co-founder and CTO of Clobotics, a computer vison technology based company focusing on providing an end to end solution for enterprise customers, the coverage including but not limited to wind energy, telco, retail. Clobotics is a company headquartered in Shanghai, China, has a branch office in Beijing and a R&D center in Seattle, WA, USA.
Previously, Dr. Ke was the Chief Software Development Officer of EHang, Inc., a technological innovation company specializing in R&D, manufacturing, and sales of intelligent aerial vehicles. He hired, led and developed a group of more than 50 developers, testers, and product managers on the R&D of its drone flight control, mobile and PC apps, and server and cloud services.
Dr. Ke is an expert in data mining, machine learning, computer vision, and distributed systems. Previously, he spent eight years at Microsoft leading the Bing Entity Understanding Group, where he architected and developed the core algorithms for Bing’s Knowledge Pane, Question Answering System, Satori Knowledge Graph, and Web Index Selection. His work in part helped Bing’s world-wide market share grow from 8% to 21%. The success of the Satori project, enabled Microsoft Bing search to have a significantly improvement of user experience, which also servers the Windows 10 Platform, Office and Office 365 cloud services, Microsoft and other related Mobile applications. Satori system also served Cortana as its core technology, as well as become the core AI cognitive services that Microsoft is serving to public.
Dr. Ke has a Bachelor’s in Computer Science, a Master’s in Electrical and Computer Engineering, and a Ph.D. in Computer Science, all from Carnegie Mellon University. His Ph.D. thesis topic was on using computer vision to automatically recognize human actions in videos. He is a recipient of the Intel Research Scholar Award, NSF IGERT Fellowship, Microsoft Technical Leadership Award, multiple Microsoft Gold Star Awards, published over 18 top tier conference and journal papers, and holds 8 U.S. patents.

Leave a Comment or Question

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)