스마트 제조를 위한 베어링 결함 예지 정비 데이터셋 구축

Abstract

In manufacturing sites, bearing fault in eletrically driven motors cause the entire system to shut down. Stopping the operationof this environment causes huge losses in time and money. The reason of this bearing defects can be various factors such aswear due to continuous contact of rotating elements, excessive load addition, and operating environment. In this paper, a motordriving environment is created which is similar to the domestic manufacturing sites. In addition, based on the establishedenvironment, we propose a dataset for bearing fault detection by collecting changes in vibration characteristics that varydepending on normal and defective conditions. The sensor used to collect the vibration characteristics is Microphone G.R.A.S. 40PH-10. We used various machine learning models to build a prototype bearing fault detection system trained on the proposeddataset. As the result, based on the deep neural network model, it shows high accuracy performance of 92.3% in the timedomain and 98.3% in the frequency domain.