Scientists from Perm National Research Polytechnic University (PNRPU) have developed a method for diagnosing the condition of electric drives in motors using machine learning. This new system can determine whether an engine is good or damaged without human intervention.
To train this system to detect errors, the researchers used various machine learning models and created a comprehensive method that combines the performance of multiple models. This method allows the system to consistently reduce the error of previous models, resulting in improved classification accuracy.
The system works by measuring motor currents using sensors and feeding the results to a trained classifier model that determines if there is a fault. This development can be used for fault detection of asynchronous motors of electrical machines, which are widely used in the industry. It is important to note that this system can perform real-time diagnostics without the need to stop the engine, making it more convenient and efficient.
This technology is part of the strategic Priority 2030 program and could be an important step in improving the diagnosis and maintenance of industrial equipment.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
