BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Mathematics-informed neural network for 2x2 matrix factorisation a
 nd a new Wiener-Hopf model for aeroengine noise radiation - Xun  Huang (Pe
 king University)
DTSTART:20240702T104500Z
DTEND:20240702T111500Z
UID:TALK214858@talks.cam.ac.uk
DESCRIPTION:In this presentation\, I will discuss two recent advancements 
 in my group's research on Wiener-Hopf modelling and applications. First\, 
 we embed Cauchy-Riemann equations into machine learning architectures usin
 g so-called mathematics-informed neural networks (MINN). By integrating Ca
 uchy integrals and boundary conditions\, the neural network effectively le
 arns to numerically generate 2x2 matrix kernel factorization for Wiener-Ho
 pf analytical models. We validate this approach by comparing machine learn
 ing results with existing analytical solutions using a benchmark case of w
 ave scattering from parallel hard-soft plates.&nbsp\; Second\, we develop 
 a Wiener-Hopf model to sound radiation from an elliptic duct\, which has g
 arnered interest in the context of modern blended-wing-body designs for ec
 o-friendly aviation. We represent the incident and scattered sound fields 
 using Mathieu functions in elliptic cylindrical coordinates and validate t
 he achieved Wiener-Hopf analytic model by comparing with FEM results.&nbsp
 \; Lastly\, I will provide a brief introduction (travel\, venue\, Visa mat
 ters\, etc.) of Hangzhou\, China\, the scenic city Marco Polo once describ
 ed as "greater than any in the world&rdquo\;\, for the upcoming Wiener-Hop
 f workshop in November. My co-authors\, Mr. Sicong Liang and Mr. Ruichen W
 ang\, will attend INI&rsquo\;s workshop and be available to share more inf
 ormation about these topics.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR