What we do is comparable to what a doctor does, where the electric motor is our patient. In the same way a doctor checks an electrocardiogram of a patient’s heart, we collect the signals from the device and analyze them, says Hussein Ihiya, a researcher at HydroCen and NTNU.
Electrical failure can cause malfunction
Imagine that you are driving on the highway in your Tesla, perhaps at a speed of 100-110 kilometers per hour. Suddenly the car starts accelerating and the speed increases and you cannot control the car. Then you drive up against the rock.
The dire consequences of starting an electric motor in failure are easy to imagine.
– There have been several such accidents since 2010. Imagine what would happen if you had such a malfunction in an electric passenger plane. Politicians want all-electric planes, and Norway is one of the leaders in electrification. If an engine in an electric-powered plane stops suddenly, the plane could crash in the worst case, Ihiya says.
Searching for generator in hydroelectric power stations
He received his master’s degree from the University of Tehran, but chose Norway and NTNU to conduct further research on the monitoring and diagnosis of electric motors. Now Ehya’s PhD work at the HydroCen Research Center in Trondheim can create new technical workplaces linked to electricity and green transformation.
What we need is equipment that is affordable, easy to use, and that can detect malfunctions in advance, says Ehya.
Until now, large machines at Norwegian hydroelectric power stations have been the focus of machine learning research and troubleshooting using magnetic field measurements. Faults and damage inside the generators can lead to significant expenses for Norwegian hydroelectric plants, as they are forced to interrupt production to find and repair faults.
Medical examination of electric motors
At the same time, generators are often installed several decades ago with little knowledge of the machine’s zero state, that is, how it works before any errors occur. This makes troubleshooting with current diagnostic tools difficult, according to Ihiya.
– Many methods for detecting faults in generators require knowing how they behave when they are “healthy”. But such accurate analyzes are not often performed before the generators are used. One can, for example, measure the vibrations in the generator, in this way determine that something is wrong, but not say what is wrong.
There are many things that can go wrong inside an electric motor. You can have a short circuit in the stator, the stator of the motor where the coils are located, or in the rotor itself, in the rotor which together with the stator creates the magnetic field in the motor. You can get rotor skew, or mechanical damage to other vital parts.
– The electric motor gives us no sign of failure – until it malfunctions. Therefore, periodic inspections are carried out. Ehya explains that the machine has been stopped to check for defects and perform maintenance, but if the failure cannot be found during the inspection, the machine breaks down.
Saves time and money
With existing methods, the machine must either be disassembled to place a sensor indoors or checked with external measuring equipment.
The first is intense work that power plants don’t often crave. The other measures vibrations or differences in voltage. It is then possible to find out if something is wrong or not, but the device is not very sensitive and is often used when it is already too late.
– With our method, we use an affordable sensor that installs in a few minutes outside the device. Then the sensor measures the machine’s magnetic field and analyzes it. The researchers can then determine if the condition is “healthy” or showing symptoms of failure. Ihiya says they can also say what is wrong.
According to researchers at HydroCen, the new technology could save energy producers significant sums. The costs of stopping and disassembling the generator can quickly add up to several hundred thousand kroner, while at the same time there is a risk of losing income when production is stopped.
With Ehya’s sensors, the device can instead be monitored and data analyzed in the cloud using artificial intelligence.
Norwegian production
So far, the method has been tested on generators at two Norwegian hydroelectric plants, but Ehya and colleagues envision it could be used both in the automobile and transportation industry, in Norwegian oil rigs and in wind power.
The project is now in the commercialization stage where they are collaborating with Rolls Royce, IKM, Statkraft and Captiva. There are no plans for Iran’s IHIA to withdraw patents from Norway.
– The Scientific Research Council contributed five million kroner to enable us to continue our work. This is Norwegian oil money, money contributed by Norwegian taxpayers. If my work here can lead to our ability to create jobs and generate income here in Norway, I will. Aya says it is my way of being able to give back a little bit of support I received here.
The article was first published in Gemini.
comments:
We have changed the comment system for the article. To create a user account, you need to register with BankID.
“Web specialist. Lifelong zombie maven. Coffee ninja. Hipster-friendly analyst.”
