26 October 2020
The new T-Touch Connect Solar by Tissot
CSEM helped develop the watch’s ecosystem by creating a unique photovoltaic dial and providing expertise for a customized, ultra-low-power operating system....
Failure of components within wind turbines is a costly exercise, but thanks to Artificial Intelligence (AI), breakdowns are becoming a thing of the past. Together, data scientists at Proxima Solutions and CSEM have developed a series of AI algorithms that offer early detection of anomalies in wind turbine behaviors, allowing quick corrective maintenance measures to be taken to prevent machinery breakdowns. The algorithms were tested at BKW wind farms across Europe with great success and are integrated in commercial solutions.
A defect in a wind turbine component, such as the failure of an air blowing fan within a cooling system of a converter, can shut down energy production for weeks and calls for costly on-site repair work. Now, thanks to a joint project carried out by Proxima Solutions and CSEM, multiple AI algorithms have been developed that can early detect anomalies in components, so expensive machinery breakdowns and production downtime can be avoided. The algorithms can detect, for example, repetitive errors that cannot be remotely acknowledged. Their application was designed over one year based on the feedback and technical knowledge of technicians in the field. This collected knowledge was then reviewed by wind experts who co-operated with data scientists, so they could extract the right information and covert this via the AI algorithms into useful insights.
The system was proven effective through a series of pilot tests undertaken at BKW's wind farms in France, Germany, Italy, and Switzerland. “In 2020, the algorithms enabled us to identify potential anomalies across our wind turbine fleet. With the help of our responsive field technicians, we were able to prevent machinery failures and turbine shutdowns, which might have caused significant financial losses,” says Arthur Chevalier, Technical and Commercial Manager at BKW Wind Service GmbH.
“Many functional failures in wind turbines take time to develop. Within that development period, “symptoms” such as anomalous temperature values or vibrations, can be observed in the sensor signals readings”
notes Baptiste Schubnel, Data Scientist at CSEM.
“Our software continuously analyzes readings from SCADA sensors in order to detect mechanical problems before they lead to major shutdowns.”
The innovative solution consists of two components: first, an AI algorithm creates a digital twin of the wind turbine, which continuously provides its expected signal values under the actual operating conditions.
Secondly, another algorithm compares these values with the real-time signal readings from the wind turbine in the field and flags any suspicious discrepancies. It also suggests possible diagnostics to link those discrepancies to the most probable underlying problems.
Finally, this whole process was grown organically based on the direct outputs of technical discussions between the field technicians, wind engineers and data scientists. The more anomalies are detected, the richer the root causes analyses are and the better the outputs will be.
Hailed as a breakthrough, this solution combines leading-edge data science methods with the technical knowledge of wind turbine engineers.
The solution is available on the market for wind farm operators.
“We have integrated the predictive algorithms in Wind-Log, our digital platform for the asset management of wind farms. Our customers benefit from the predictive recommendations to increase availability and energy production of their assets”
says Giuseppe Madia, Managing Director of Proxima Solution GmbH.
“Of course, artificial intelligence won’t replace technicians and operators. Our objective is to support them while improving efficiency.”