Health State Evaluation for Production Systems by Aggregating Multi-source Data based Hidden Markov Model

Modern production systems are the carriers that advanced manufacturing technologies can be realized. Accurate health state evaluation is the basis for ensuring stable operation of the production system and developing a maintenance strategy However, the most existing health evaluation techniques of p...

Full description

Saved in:
Bibliographic Details
Published in2020 11th International Conference on Prognostics and System Health Management (PHM-2020 Jinan) pp. 439 - 443
Main Authors Ci, Huipeng, Yao, Yongchao, He, Wenhai, Gong, Linshu, Zhu, Xianming
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2020
Subjects
Data models
Degradation
Gears
Health state evaluation
Hidden Markov model
Hidden Markov models
Multi-source data
Production system
Production systems
Quality assessment
Task analysis
Online AccessGet full text

Cover

More Information
Summary:Modern production systems are the carriers that advanced manufacturing technologies can be realized. Accurate health state evaluation is the basis for ensuring stable operation of the production system and developing a maintenance strategy However, the most existing health evaluation techniques of production systems are based on the single source data. The multi-source data based hidden Markov model is proposed to evaluate health state (including machine performance data, process quality data, etc.). The operational features-based health definition of the production system of production systems is proposed. The modeling process of hidden Markov model based on multi-source data is given, and the multi-performance degradation law of production system is revealed. And taking the pre-grinding gear hob production system as an example, the accuracy and superiority of this proposed approach are verified.
ISSN:2166-5656
DOI:10.1109/PHM-Jinan48558.2020.00085