Tiny signals can prevent big accidents

By listening to the electric machine’s magnetic field, it is possible to detect faults that could prevent potential catastrophes for electric vehicles. The new method could also save power producers a great deal of money.

“What we do can be compared to what a doctor does, where the electric motor is our patient,” Hossein said. The same way a doctor does an electrocardiogram check of a person’s heart, says Hossein. patients, we collect the signals from the machine and analyze them.” Ehya, a researcher at HydroCen and NTNU.

Power failure can cause problems

Imagine that you are driving your Tesla on a highway, maybe at 100 to 110 kilometers per hour. Suddenly your car starts to accelerate, the speed increases and you are no longer able to control the car. Then you crash into a rock face.

The dire consequences of a failed electric motor are easy to imagine.

“Several accidents like this have happened since 2010. Imagine what could happen if you had this kind of error on an electric passenger plane. Politicians are pushing the machine. flying all-electric, and Norway is one of the leading countries in electrification.If an engine in an electric-powered aircraft suddenly stops, in a worst case the plane might crash,” Ehya said.

Research on generators in hydroelectric plants

Ehya holds a master’s degree from the University of Tehran but chose Norway and NTNU to further study electric motor monitoring and diagnostics. The doctoral research Ehya has conducted at HydroCen, an Eco-Friendly Energy Research Center in Trondheim, has the potential to create new technological workplaces related to electrification and green transition.

“What we needed was a device that was affordable, easy to use, and could detect errors in advance,” says Ehya.

To date, large generators at Norwegian hydroelectric power plants have been the focus of research on machine learning and troubleshoot with magnetic field measurement. Faults and damage inside the plant’s generators can lead to huge costs for Norway’s hydroelectric plants, as they are forced to halt production to find the fault and fix it.

Like medical check for electric motor

Hydroelectric power plant generators are often installed decades ago with little understanding of the machine’s zero state—that is, how it worked before any failure occurred. This makes troubleshooting with today’s diagnostic tools difficult, says Ehya.

“A lot of methods of finding faults in generators require knowing how they behave when they are ‘healthy.’ But often such precise analyzes are not performed before the generator is put in place. For example, we can measure vibrations in a generator and by doing so determine that something is wrong, but we cannot say exactly what is wrong,” he said. speak.

Anything can happen inside an electric motor. you can get a short circuit in the stator, the fixed part of the motor where the windings are located, or in the rotor itself, the part that moves with the stator creating a magnetic field in the motor. The rotor may be misaligned or other critical components may suffer mechanical damage.

“One electric motor does not give us any indication of failure—until it breaks. That’s why it’s important to conduct periodic checks. The machine has to be stopped to check the fault and carry out maintenance, but if no fault is found during the inspection, the machine will fail,” Ehya said.

Save time and money

With current methods, the machine must be dismantled to either install an internal sensor or check with an external measuring device.

Installing sensors is an extensive undertaking that power plant owners are usually not too eager to undertake. An external test measures vibrations or voltage changes, which can tell us something is wrong, but this device is not very sensitive and is often used when it is too late.

“With our method, we use a very affordable sensor that can be attached to the outside of the machine in a few minutes. This sensor measures the machine’s magnetic field and analyzes it. Then, the researchers can determine if the machine is ‘healthy’ or show no symptoms of failure. They can also determine what the problem is,” Ehya said.

According to researchers at HydroCen, the new technology could save power producers a large amount of money. The cost of stopping and dismantling a generator can quickly run into the tens of thousands of euros, with the risk of losing income when production stops.

Instead, with Ehya’s sensors, the machine can be monitored and analyzed in the cloud using artificial intelligence.

Norwegian production

So far, the new method has been tested on generator at two Norwegian hydroelectric plants, but Ehya and his colleagues envision that it will be useful in the automotive and transportation industries, on Norwegian oil rigs and also in wind power.

The project is currently in the commercialization phase, where the team is collaborating with Rolls Royce, IKM, Statkraft and Captiva. And Ehya has no plans to get the patent out of Norway.

“The Norwegian Research Council has contributed EUR 500,000 to help us continue our work. This is Norwegian oil money and money that Norwegian taxpayers have contributed. If the public my work here can make it possible for us to create jobs and income in Norway, I’ll do it “Ehya said.