Reinforcement learning–based fault-tolerant control with application to flux cored wire system

Dapeng Zhang, Zhiwei Gao

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)
8 Downloads (Pure)

Abstract

Background:
Processes and systems are always subjected to faults or malfunctions due to age or unexpected events, which would degrade the operation performance and even lead to operation failure. Therefore, it is motivated to develop fault-tolerant control strategy so that the system can operate with tolerated performance degradation.

Methods:
In this paper, a reinforcement learning-based fault-tolerant control method is proposed without need of the system model and the information of faults.

Results and Conclusions:
Under the real-time tolerant control, the dynamic system can achieve performance tolerance against unexpected actuator or sensor faults. The effectiveness of the algorithm is demonstrated and validated by the rolling system in a test bed of the flux cored wire.
Original languageEnglish
Pages (from-to)349-359
Number of pages11
JournalMeasurement and Control
Volume51
Issue number7-8
Early online date26 Jul 2018
DOIs
Publication statusPublished - 1 Sep 2018

Fingerprint Dive into the research topics of 'Reinforcement learning–based fault-tolerant control with application to flux cored wire system'. Together they form a unique fingerprint.

Cite this