For advanced lean premixed gas turbine combustors that have high inlet air temperatures, autoignition may occur during the fuel/air mixing process, which can cause flame-holing inside the premixing device and burn the hardware. An experimental study was performed using a setup that mimics the fuel/air mixing process of lean-premixed combustors. In the present experiment, the preheated air was injected into a quartz tube, and a fuel jet was injected concentrically into the hot turbulent air coflow. The quartz tube allows for direct observation of the autoignition behavior, which develops when the fuel and air mix as they flow inside the tube. This paper presents a study combining machine learning methods and physical analysis that is aimed at predicting autoignition in such flows. A model for the prediction of autoignition of a fuel jet in a flow configuration referred to as a ‘confined turbulent hot coflow’ (CTHC) is developed using machine learning techniques based on binary logistic regression and support vector machine. Key factors that impact the autoignition phenomenon are identified by analyzing the underlying physics and are used to form the feature vector of the model. The model is trained using data from experiments and is validated by an additional set of data, which are selected randomly. The results show that the model predicts the autoignition event with satisfactory accuracy and quick turnaround. The trained model parameters in turn provide insights into the quantitative contribution of different factors that impact the autoignition event. Thus, the machine-learning based method can form an alternative to CFD modeling in some cases.


Prediction of the Autoignition of a Fuel Jet in a Confined Turbulent Hot Coflow Using Machine Learning Methods

Division / Sponsor:
International Gas Turbine Institute (IGTI)

Paper Proceedings: https://asmedigitalcollection.asme.org/GT/GT2020/volume/84058

Turbo Expo - Virtual Conference

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.