http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
차량 DTC 데이터 기반 고장 상태 예지 방안에 대한 사례 연구
장명훈(Myounghoon Jang),박한설(Hanseol Park),김지인(Jiin Kim),오정림(Jeongrim Oh),전홍배(Hongbae Jun) (사)한국CDE학회 2020 한국CDE학회 논문집 Vol.25 No.4
Sudden vehicle problems while driving cause great damage to the driver. In this context, it is necessary to monitor important vehicle parts’ condition and take appropriate actions in advance based on condition analysis. This paper implements a model for predicting the occurrence of a certain failure code before 24 hours based on gathered DTC (Diagnostic Trouble Code) data with LSTM (Long Short-Term Memory)-Autoencoder. LSTM is a type of RNN (Recurrent Neural Network) that can solve data long-term dependency problems and is suitable for learning many time-series data to create classification and regression models. In particular, the model is a stacked autoencoder structure consisting of several LSTMs, showing higher accuracy than normal LSTM. The case study shows that the proposed method gives a reasonable performance on predicting the failure code.
DTW 기반 추진 전동기 잔여수명 예측 알고리즘 개발 사례연구
김준석(Junseok Kim),이강복(Gangbok Lee),황회선(Hoesun Hwang),안지수(Jisoo Ahn),오정림(Jeongrim Oh),장명훈(Myounghoon Jang),전홍배(Hongbae Jun) (사)한국CDE학회 2021 한국CDE학회 논문집 Vol.26 No.4
Recently, more detailed fault diagnosis is being performed by analyzing the current status and changes of equipment through condition monitoring data obtained through various sensor data. In addition to fault diagnosis, attempts to predict the remaining useful life (RUL) in the event of a fault are being studied in various ways. RUL prediction is very important as a key indicator that can be used as a reference for equipment replacement time, cost reduction, and accident prevention. In this study, we propose a method for predicting the remaining life of equipment by extracting an abnormal pattern based on data collected from a ship"s propulsion motor. To this end, the dynamic time warping (DTW) algorithm, which is a nonlinear pattern matching technique, and a method applying KNN were presented, and their effectiveness was examined through a simple case study.