|ijphm_16_023.pdf||6.14 MB||September 24, 2016 - 4:53am|
The thermo-acoustic instabilities arising in combustion processes cause significant deterioration and safety issues in various human-engineered systems such as land and air based gas turbine engines. The phenomenon is described as self-sustaining and having large amplitude pressure oscillations with varying spatial scales of periodic coherent vortex shedding. Early detection and close monitoring of combustion instability are the keys to extending the remaining useful life (RUL) of any gas turbine engine. However, such impending instability to a stable combustion is extremely difficult to detect only from pressure data due to its sudden (bifurcation-type) nature. Toolchains that are able to detect early instability occurrence have transformative impacts on the safety and performance of modern engines. This paper proposes an end-to-end deep convolutional selective autoencoder approach to capture the rich information in hi-speed flame video for instability prognostics. In this context, an autoencoder is trained to selectively mask stable flame and allow unstable flame image frames. Performance comparison is done with a well-known image processing tool, conditional random field that is trained to be selective as well. In this context, an information-theoretic threshold value is derived. The proposed framework is validated on a set of real data collected from a laboratory scale combustor over varied operating conditions where it is shown to effectively detect subtle instability features as a combustion process makes transition from stable to unstable region.