Bearing problems must be found as soon as possible in order to keep rotating machinery functioning correctly. Our research focuses on feature selection's possible benefits in enhancing diagnostic prediction models. Vibration data from bearings operating under different conditions was analyzed to extract relevant features using the Random Forest (RF) classifier and the Standard Deviation (STD) parameter. There were three datasets used, each representing a different set of operating conditions and bearing possibilities. The study's encouraging findings demonstrated that the suggested course of action was not only successful but also durable. Bearing flaw, diagnostic, random forest, optimization approach, and standard deviation are a few instances of terms.

Bearing problems must be found as soon as possible in order to keep rotating machinery functioning correctly.