Bayesian nonparametric modeling of Markov chains for detection of thermoacoustic instabilities

Sihan Xiong, Jihang Li, Asok Ray

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

1 Scopus citations


This paper proposes a Bayesian nonparametric method for detecting thermoacoustic instabilities in gas turbine engines in real-time, where the underlying algorithms are formulated in the symbolic domain and the resulting patterns are constructed from symbolized pressure measurements as probabilistic finite state automata (PFSA) that is built upon a finite-memory Markov model, called D-Markov machine. The Bayesian nonparametric structure is adopted for: (i) automated selection of parameters in the D-Markov machine, and (ii) online sequential testing, to provide a data-driven and coherent statistical analysis of combustion instability phenomena without relying on numerically intensive models of combustion dynamics. The proposed method has been experimentally validated on the time series generated from a laboratory-scale combustion apparatus. The results of instability prediction, derived from the time series, have been compared with those of other existing techniques.

Original languageEnglish (US)
Title of host publication2017 American Control Conference, ACC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9781509059928
StatePublished - Jun 29 2017
Event2017 American Control Conference, ACC 2017 - Seattle, United States
Duration: May 24 2017May 26 2017

Publication series

NameProceedings of the American Control Conference
ISSN (Print)0743-1619


Other2017 American Control Conference, ACC 2017
Country/TerritoryUnited States

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering


Dive into the research topics of 'Bayesian nonparametric modeling of Markov chains for detection of thermoacoustic instabilities'. Together they form a unique fingerprint.

Cite this