LSTM-based PdM Platform for Automobile SCU Inspection Equipment

Abstract

With the recent rapid development of the Industrial Internet of Things(IIoT), factory automation has become an important issue. Accordingly, research on Predictive Maintenance(PdM) technology is being conducted to improve the Remaining Useful Lifetime(RUL) of equipment in factory automation. PdM technology predicts the condition of equipment based on Artificial Intelligence(AI) and based on this, repairs equipment before problems occur to improve the lifespan of the equipment. In this paper, we intend to apply PdM to inspection equipment that inspects Shift-by-wire Control Unit(SCU), a type of electric vehicle transmission. The proposed technology is to perform equipment condition prediction based on Long Short-Term Memory(LSTM) and visualize the prediction results through monitoring program development. As a result of the simulation, it was confirmed that the prediction results through the LSTM model follow the trend of the actual values.