Ushnish Sengupta, Listening for instabilities with probabilistic machine learning

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

• Ushnish Sengupta, Engineering Dept.
• Thursday 11 July 2019, 13:00-14:00
• Newnham Terrace Seminar Room, Darwin .

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.

This talk is included in these lists:

• AI4ER Seminar Series
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge talks
• Chris Davis' list
• Interested Talks
• Newnham Terrace Seminar Room, Darwin
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.