| dc.description.abstract | Rolling bearing fault is one of the most common failures that leads to rotating
equipment’s shutting down. Within this fact, researchers have always considered rolling
bearing faults diagnosis and therefore, the topic has risen as one of the most noticeable
research areas currently. This study was conducted aiming to investigate Machine
Learning methods in classifying bearing’s health conditions. Within the Case Western
Reserve University dataset, statistical features were extracted and then imported as the
input for Support Vector Machine and other classifiers to achieve faults diagnosis.
Finally, performance indicators were conducted to verify all methods. The study achieved
high-accuracy classification results, confirming the possibility of applying Machine
Learning methods in predictive maintenance problems. | en_US |
