Equipment Vibration Condition Monitoring Technology Based on Spectrum Image Deep Learning Models

We created a system that predicts failures in advance by analyzing the equipment spectrum for rotating operated Hyundai and Kia Motors. In case of analysis through existing rotation speed order tracking, if or specifications change, it is often useless. To this end, we extracted trained images various ways, made possible to know what kind failure there when new received. For easy use, (1) facility maintenance history management (2) image collection program (3) learning (4) automatic (5) result UI mailing service were developed separately.