AI Assisted Detection of Shock Motions Inside a Transonic Duct

The general problem of detecting the position of a shock by using a discrete set of real or virtual pressure sensors is studied numerically. A Machine Learning (ML) algorithm is trained by CFD simulations of the transonic flow in a duct with an embedded shock at different positions. The shock detection algorithm is validated by using discrete data collected at different duct locations, for simulating the outputs of a discrete number of pressure sensors placed along the duct. A noise model of the measured pressure values is introduced in order to emulate the sensor outputs and faults.