Evaluating performances of 1-D models to predict variable area supersonic gas ejector performances. (15th November 2018)

• Record Type: Journal Article
• Authors: Petrovic, Andrija; Jovanovic, Milos Z.; Genic, Srbislav; Bugaric, Ugljesa; Delibasic, Boris
• Is Part Of: Energy. Volume 163(2018)
• Page Start: 270
• Page End: 289
• Publication Date: 2018-11-15
• Subjects: Variable area nozzle -- Supersonic gas ejector -- Mixture of experts -- Experimental study -- Antlion algorithm; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Energy consumption -- Periodicals; 333.7905
• DOI: 10.1016/j.energy.2018.08.115
• Languages: English
• ISSNs: 0360-5442

Abstract

Abstract: The application of supersonic gas ejector with variable area nozzle can be found in different industries. However, due to different types of variable area nozzle, performance prediction is mainly focused on costly numerical simulations. In this paper, one-dimensional models for performance prediction of variable area gas ejector with specially designed nozzle, were compared. Additionally, operational lines and corresponding modes were analyzed. Two different variable area ejectors were experimentally tested. The first ejector used natural gas as motive fluid, whereas in the second one motive gas was the composition of alkane. Six distinct correlations of ejector component efficiencies were evaluated. Sum of absolute relative errors and coefficient of determination were used as goodness of fit criteria. The results showed that best model has coefficient of determination 0.76 and 0.63 in the case of natural and R2 gas as motive fluids, respectively. In order to improve prediction performances of entrainment ratio, the mixture of experts machine learning technique was used. Moreover, the results of obtained conditional probabilities of models are visualized in space spanned by area and pressure ratios. The presented analysis showed that one model is not generally better than others and can be improved by using an ensemble of models. Highlights: 1-D models of variable area supersonic gas ejectors were analyzed. Two different variable area gas ejectors were experimentally evaluated. Ejector component efficiencies correlations are obtained by an optimization procedure. Six distinct ejector models were compared by goodness of fit criteria. Mixture of Experts machine learning technique was used to improve prediction performances.