ConvNet-based Remaining Useful Life Prognosis of a Turbofan Engine

Chang Woo Hong, Min Seung Ko, Kyeon Hur

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, the remaining useful life of a turbofan engine is prognosed by using a ConvNet-based deep neural network (DNN). The proposed model is based on ConvNet that uses dilated convolutional neural network (CNN) and the concept of the EfficientNet and builds the model using only the CNN algorithm. Most existing studies predicted the remaining useful life of a turbofan engine by learning sequential data based on CNN-RNN (Recurrent neural network). However, due to the inherent characteristics of the RNN algorithm, it has a disadvantage that the number of parameters increases and the calculation time is particularly longer than that of a CNN-based algorithm. The RNN algorithm has many limitations for quick diagnosis and compact model configuration for actual industry utilization. The experimental results show that the ConvNet-based DNN model is suitable for predicting the remaining useful life of a turbofan engine as the proposed model achieves high accuracy and efficiency while dramatically reducing parameters.

Original languageEnglish
Title of host publication4th IEEE International Conference on Knowledge Innovation and Invention 2021, ICKII 2021
EditorsTeen-Hang Meen
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages190-193
Number of pages4
ISBN (Electronic)9781665423076
DOIs
Publication statusPublished - 2021 Jul 23
Event4th IEEE International Conference on Knowledge Innovation and Invention, ICKII 2021 - Taichung, Taiwan, Province of China
Duration: 2021 Jul 232021 Jul 25

Publication series

Name4th IEEE International Conference on Knowledge Innovation and Invention 2021, ICKII 2021

Conference

Conference4th IEEE International Conference on Knowledge Innovation and Invention, ICKII 2021
Country/TerritoryTaiwan, Province of China
CityTaichung
Period21/7/2321/7/25

Bibliographical note

Funding Information:
ACKNOWLEDGMENT This work was supported by H“ uman Resources Program in Energy Technology” of the Korea Institute of Energy Technology Evaluation and Planning (KETEP) granted financial resource from the Ministry of Trade, Industry & Energy, Republic of Korea. (No.20194030202420)

Publisher Copyright:
© 2021 IEEE.

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Hardware and Architecture
  • Software
  • Safety, Risk, Reliability and Quality
  • Modelling and Simulation

Fingerprint

Dive into the research topics of 'ConvNet-based Remaining Useful Life Prognosis of a Turbofan Engine'. Together they form a unique fingerprint.

Cite this