Sammendrag
Industrial revolution 4.0 has enabled the advent of new technological advancements,
including the introduction of information technology with physical devices. The implementation
of information technology in industrial applications has helped streamline industrial processes and
make them more cost-efficient. This combination of information technology and physical devices
gave birth to smart devices, which opened up a new research area known as the Internet of Things
(IoT). This has enabled researchers to help reduce downtime and maintenance costs by applying
condition monitoring on electrical machines utilizing machine learning algorithms. Although the
industry is trying to move from scheduled maintenance towards predictive maintenance, there is
a significant lack of algorithms related to fault prediction of electrical machines. There is quite a
lot of research going on in this area, but it is still underdeveloped and needs a lot more work. This
paper presents a signal spectrum-based machine learning approach toward the fault prediction
of electrical machines. The proposed method is a new approach to the predictive maintenance of
electrical machines. This paper presents the details regarding the algorithm and then validates the
accuracy against data collected from working electrical machines for both cases. A comparison
is also presented at the end of multiple machine learning algorithms used for training based on
this approach.
Vis fullstendig beskrivelse