THIS ARTICLE/PRESS RELEASE IS PAID FOR AND PRESENTED BY The University of Agder – Read more
This method can streamline the monitoring of wind turbines and electric cars, which can pay off for electricity customers and car owners.
“Effective monitoring and fault diagnosis of the electrical machines in wind turbines and electric vehicles can make their operation more affordable and contribute to making operation and maintenance safer,” says Sveinung Attestog.
He works as a trainee at Agder Energi. He recently received his doctorate from the University of Agder (UiA). His thesis is about troubleshooting electric motors at varying speeds and loads.
Modeling and fault diagnosis using artificial intelligence are keywords in his thesis. But the research is also practically grounded. The mathematical models were tested in the laboratory at UiA.
Electrical machines – such as motors or generators – play a key role in electric vehicles, wind turbines and many other products.
“I’ve been looking at how to effectively troubleshoot electric motors and generators that convert between mechanical and electrical energy, such as electric vehicles and wind turbines,” Attestog says.
The engine he studied is popular because it takes up relatively little space but still has high efficiency and high torque. In technical terms, it is called permanent magnet synchronous motor (PMSM).
More effective monitoring
Today, monitoring and supervision are largely planned according to the calendar. Equipment is checked when it is assumed that it needs maintenance or replacement. For example, cars are checked every two years and wind turbines every year.
But now researchers like Attestog are pushing to find solutions that are independent of the calendar, which can quickly detect wear and remedy problems to avoid accidents.
“The sooner we detect faults, the easier they are to deal with. It is important for both motorists and electricity consumers that an electric car’s engine and a wind turbine’s generator work optimally,” says Attestog.
It is also in the interest of car dealers and electricity companies that the machinery in cars and wind turbines work as best as possible.
Short circuit, wear
Engine failure is usually due to improper use or wear and tear. Short circuits are frequent faults.
“Monitoring and effective fault diagnosis schemes are necessary to detect faults early. This will ensure safe operation, speed up equipment maintenance and reduce downtime and costs,” says Attestog.
Maintenance
All machines must be serviced at regular intervals, especially equipment that is in regular use and equipment that is constantly exposed to harsh weather conditions.
Offshore wind turbines, for example, are exposed to harsh weather and salt water. Electric cars drive on salted winter roads, which causes corrosion on the vehicles.
An engine is also subject to stress and wear depending on the speed and power at which it operates.
Faster solutions
These are among the most important contributions from Attestog’s thesis:
- Developed and tested two solutions that find engine faults faster than before.
- Developed and tested a new artificial intelligence method to search for faults regardless of speed and stress on the engine.
- Simplified engine monitoring by using less equipment, reducing the number of sensors from 12 to 2.
“The advantage of artificial intelligence is that we can detect faults without having to know the details of engine power and performance,” says the researcher.
Artificial intelligence solves problems
Synonyms for artificial intelligence in this context are machine learning and reinforcement learning.
When calculating how an engine should work, the researcher starts with more data about the engine operating without errors than with errors. But artificial intelligence solves this problem, which researchers call unbalanced datasets.
“To put it simply, I coded it so that artificial intelligence is rewarded for detecting errors. Therefore, artificial intelligence emphasizes errors and learns to detect them,” says Attestog.
Reference:
Sveinung Certificate. Modeling and fault detection of permanent magnet synchronous motors in dynamic operations, Doctoral thesis, University of Agder2022.
See more content from Agder University:
