A Time-Series Data Generation Method to Predict Remaining Useful Life

Processes

Gilseung Ahn¹  Hyungseok Yun²  Sun Hur²  Siyeong Lim³ 

[1] Data Analytic Team 1, Hyundai Motors Company, Seoul 06797, Korea;Department of Industrial and Management Engineering, Hanyang University, Ansan 15588, Korea;Korean Research Institute for Human Settlements, Sejong 30147, Korea;

关键词: remaining useful life prediction;    data generation;    symbolic aggregate approximation;    run-to-failure;   

DOI  :  10.3390/pr9071115

来源: DOAJ

【 摘 要 】

Accurate predictions of remaining useful life (RUL) of equipment using machine learning (ML) or deep learning (DL) models that collect data until the equipment fails are crucial for maintenance scheduling. Because the data are unavailable until the equipment fails, collecting sufficient data to train a model without overfitting can be challenging. Here, we propose a method of generating time-series data for RUL models to resolve the problems posed by insufficient data. The proposed method converts every training time series into a sequence of alphabetical strings by symbolic aggregate approximation and identifies occurrence patterns in the converted sequences. The method then generates a new sequence and inversely transforms it to a new time series. Experiments with various RUL prediction datasets and ML/DL models verified that the proposed data-generation model can help avoid overfitting in RUL prediction model.

【 授权许可】

Unknown