AI Case Study

Siemens Gamesa Renewable Energy reduces inspection time of wind turbine blades by 75% by using non-destructive testing

Siemens Gamesa has implemented Fujitsu's deep learning technology which analyses images taken from ultrasonic scans to assess for potential defects in wind turbine blades. This speeds up the time-consuming process by pinpointing potential issues which need additional human inspection, purportedly by 75%.

Industry

Energy

Renewable Energy

Project Overview

"Fujitsu and Siemens Gamesa jointly worked on a solution that leverages AI deep learning, image and signal processing techniques during the inspection process. AI analyzes images generated from Non-Destructive Testing data scans to identify patterns that may indicate manufacturing defects, such as wrinkling, that could cause the blades to fail during operation. Fujitsu has significantly accelerated Siemens Gamesa’s post manufacturing quality assurance (QA) process through the co-creation of an Artificial Intelligence solution1 that uses deep learning capabilities to significantly reduce inspection times for newly-manufactured wind turbine blades. Siemens is using the new Fujitsu AI solution to speed up the inspection process for the fiberglass blades, which are up to 75 meters long. Inspection time to thoroughly check every centimeter of the entire length of a new blade is reduced to just one and a half hours. As a result, highly-skilled inspectors are freed up from a monotonous but necessary task that could previously take six hours."

Reported Results

Decreases windmill turbine blade inspection time by 75%, resulting in "significant cost savings".

Technology

According to Fujitsu's press release: "The deep learning component of this new AI framework leverages the super-human ability of deep neural networks to process image data to detect relevant patterns, based on a unique set of technologies developed by Fujitsu Laboratories of Europe. This involves converting real-world data analysis challenges into an image analysis format, automating and accelerating the detection of relevant patterns in NDT ultrasound scan data, which may be indicative of manufacturing defects. Specialist manual inspection can therefore be rapidly targeted to potential defects, translating into an 80 percent reduction in the product area requiring an expert technician’s attention.

Dr Adel Rouz, Executive Vice President of Fujitsu Laboratories of Europe, explains the significance of this innovative technology approach: “We developed a generic machine learning engine for pattern detection, using a process that translates any raw data analysis problem into one involving image pattern recognition. Working with manufacturers, we can rapidly tune the solution to a specific application, thanks to its ability to learn from just a few training examples. This significantly minimizes the amount of annotated data needed from a manufacturer’s domain specialists, accelerating the entire set-up process."

Function

Strategy

Strategic Planning

Background

According to Fujitsu they have "developed an innovative AI technology that significantly improves manufacturing quality control and defect detection by automatically analyzing and diagnosing Non-Destructive Testing (NDT) ultrasonic scan data in just minutes, helping to pinpoint potential defects more rapidly and efficiently than existing processes". This technology is to be applied for Siemens Gamesa's quality assurance process for its wind turbine blades, a time-consuming process.

Benefits

Cost - Job automation

Data

"Images generated from Non-Destructive Testing data scans".