Fault Trend Prediction of Centrifugal Blowers Considering Incomplete Data

You Zhang, Congbo Li, Ying Tang, Feng Zhou, Xu Zhang

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

1 Scopus citations

Abstract

Centrifugal blowers have high failure frequency due to the harsh working environment, and it is urgent to perform fault trend prediction for predictive maintenance. Centrifugal blowers often have missing data due to sensor failures and unstable network connections, which will lose a lot of useful information. To enhance the prediction accuracy and stability, a fault trend prediction method considering incomplete data is proposed. The tensor decomposition is used to fill the missing data to obtain the complete data of the centrifugal blower. Based on the filled complete data, the deep belief network (DBN) is used to construct a health indicator that can characterize the health status of the centrifugal blower. The fault prediction model built by Informer is developed to predict the degradation trend of health indicators to realize the fault trend prediction of the centrifugal blower. Experimental results demonstrate that the prediction model established by the filled data can predict the fault earlier than missing data. The proposed Informer method has superior prediction performance than other methods.

Original languageEnglish (US)
Title of host publication2023 IEEE 19th International Conference on Automation Science and Engineering, CASE 2023
PublisherIEEE Computer Society
ISBN (Electronic)9798350320695
DOIs
StatePublished - 2023
Event19th IEEE International Conference on Automation Science and Engineering, CASE 2023 - Auckland, New Zealand
Duration: Aug 26 2023Aug 30 2023

Publication series

NameIEEE International Conference on Automation Science and Engineering
Volume2023-August
ISSN (Print)2161-8070
ISSN (Electronic)2161-8089

Conference

Conference19th IEEE International Conference on Automation Science and Engineering, CASE 2023
Country/TerritoryNew Zealand
CityAuckland
Period8/26/238/30/23

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Fault Trend Prediction of Centrifugal Blowers Considering Incomplete Data'. Together they form a unique fingerprint.

Cite this