University of Cambridge > > AI4ER Seminar Series > Ushnish Sengupta, Listening for instabilities with probabilistic machine learning

Ushnish Sengupta, Listening for instabilities with probabilistic machine learning

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Rachel Furner.

Thermoacoustic instabilities are a peculiar phenomenon arising from feedback loops between heat release and acoustics. These can be extremely dangerous in high-energy density combustors such as jet engines, gas turbines or rocket engines. I will describe how we are employing probabilistic machine learning techniques to predict the stability of a laboratory-scale combustor from far-field noise data. I will also try to convince you that the uncertainties that we obtain from our Bayesian techniques, in addition to the predictions, makes our diagnostic more trustworthy and leads to better decisions. Finally, there will be a brief glimpse into our attempts at applying these techniques to sensor data from systems far bigger than our little experimental rig.

This talk is part of the AI4ER Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity