Use of Convolutional Neural Network Image Classification and High-Speed Ion Probe Data Towards Real-Time Detonation Characterization in a Water-Cooled Rotating Detonation Engine

Abstract

Abstract As rotating detonation engine (RDE) technologies progress in maturity, the importance of monitoring methods progressing towards development of active control becomes more critical. High-speed processing of experimental RDE data on a time scale approaching real-time diagnostics will likely only be accomplished through the use of machine learning. This study aims to develop and deploy a real-time monitoring technique which integrates flame image classification by a convolutional neural network (CNN) and ionization current signal analysis with the goal of determining detonation wave number, direction, frequency, and individual wave speeds throughout experimental RDE operational windows. Wave mode identification through single image CNN classification bypasses the need to evaluate sequential images and offers instantaneous identification of the wave mode present in the RDE annulus. The output of the existing CNN is utilized alongside a correlation of ion probe data to generate diagnostic outputs. The diagnostic acquires live data using a modified experimental setup as well as Pylon and PyDAQmx libraries within a Python data acquisition environment. Lab-deployed diagnostic results are presented across a variety of wave modes, operating conditions, and data quality, currently executed at 3–4 Hz with a variety of iteration speed optimization options to be considered as future work. These speeds exceed that of conventional techniques and offer a proven structure for real-time RDE monitoring, which will play a vital role in the development of active control, necessary for the extension of operational capabilities and RDE technology maturation toward industrial integration.