International Journal of Turbomachinery, Propulsion and Power

13 pages, 3568 KiB

Open AccessArticle

Predictive Modeling of NOx Emissions from Lean Direct Injection of Hydrogen and Hydrogen/Natural Gas Blends Using Flame Imaging and Machine Learning

by Iker Gomez Escudero and Vincent McDonell

Int. J. Turbomach. Propuls. Power 2024, 9(4), 33; https://doi.org/10.3390/ijtpp9040033 - 3 Oct 2024

Viewed by 610

Abstract

This research paper explores the use of machine learning to relate images of flame structure and luminosity to measured NOx emissions. Images of reactions produced by 16 aero-engine derived injectors for a ground-based turbine operated on a range of fuel compositions, air pressure drops, preheat temperatures and adiabatic flame temperatures were captured and postprocessed. The experimental investigations were conducted under atmospheric conditions, capturing CO, NO and NOx emissions data and OH* chemiluminescence images from 27 test conditions. The injector geometry and test conditions were based on a statistically designed test plan. These results were first analyzed using the traditional analysis approach of analysis of variance (ANOVA). The statistically based test plan yielded 432 data points, leading to a correlation for NOx emissions as a function of injector geometry, test conditions and imaging responses, with 70.2% accuracy. As an alternative approach to predicting emissions using imaging diagnostics as well as injector geometry and test conditions, a random forest machine learning algorithm was also applied to the data and was able to achieve an accuracy of 82.6%. This study offers insights into the factors influencing emissions in ground-based turbines while emphasizing the potential of machine learning algorithms in constructing predictive models for complex systems. Full article

► Show Figures

Figure 1

20 pages, 4974 KiB

Open AccessFeature PaperArticle

Prediction of Fan Array Performance with Polynomial and Support Vector Regression Models

by Philipp Ostmann, Martin Rätz, Martin Kremer and Dirk Müller

Int. J. Turbomach. Propuls. Power 2024, 9(4), 32; https://doi.org/10.3390/ijtpp9040032 - 3 Oct 2024

Viewed by 374

Abstract

The increasing utilisation of demand-controlled ventilation strategies leads to the frequent operation of fans under part-load conditions. To accurately predict the energy demand of a ventilation system with a fan array in the early design stages, models that calculate reliable results across the whole operating range are required. We present the comparison of a polynomial and a machine learning approach through support vector regression (SVR) to predict the fan performance over a wide range of typical operating points. For fitting and validation, we use experimental data. We investigate the extrapolation performance of both approaches. The SVR model achieves a slightly better representation of the experimental data with a lower error, especially when only sparse data are available. Both approaches yield similar results when the evaluation is conducted within the experimentally captured domain but deviates outside the domain. At operating points that are far from the experimentally captured domain, the polynomial models yield fan efficiencies that are physically plausible, while the SVR models drastically overpredict the fan efficiency. To rate the influence of such deviations towards modelling the actual energy demand, both approaches are applied to an operation simulation of a simplified office building. Both approaches yield similar results despite differing extrapolation capabilities. Full article

► Show Figures

Graphical abstract

12 pages, 6000 KiB

Open AccessFeature PaperArticle

Development and Design Validation of an Inflow-Settling Chamber for Turbomachinery Test-Benches

by Michael Henke, Stefan Gärling, Lena Junge, Lars Wein and Hans-Ulrich Fleige

Int. J. Turbomach. Propuls. Power 2024, 9(4), 31; https://doi.org/10.3390/ijtpp9040031 - 24 Sep 2024

Viewed by 400

Abstract

At Leibniz University of Hannover, Germany, a new turbomachinery test facility has been built over the last few years. A major part of this facility is a new 6 MW compressor station, which is connected to a large piping system, both designed and built by AERZEN. This system provides air supply to several wind tunnel and turbomachinery test rigs, e.g., axial turbines and axial compressors. These test rigs are designed to conduct high-quality aerodynamic, aeroelastic, and aeroacoustic measurements to increase physical understanding of steady and unsteady effects in turbomachines. One primary purpose of these investigations is the validation of aerodynamic and aeroacoustic numerical methods. To provide precise boundary conditions for the validation process, extremely high homogeneity of the inflow to the investigated experimental setup is imminent. Thus, customized settling chambers have been developed using analytical and numerical design methods. The authors have chosen to follow basic aerodynamic design steps, using analytical assumptions for the inlet section, the “mixing” area of a settling chamber, and the outlet nozzle in combination with state-of-the-art numerical investigations. In early 2020, the first settling chamber was brought into operation for the acceptance tests. In order to collect high-resolution flow field data during the tests, Leibniz University and AERZEN have designed a unique measurement device for robust and fast in-line flow field measurements. For this measurement device, total pressure and total-temperature rake probes, as well as traversing multi-hole probes, have been used in combination to receive high-resolution flow field data at the outlet section of the settling chamber. The paper provides information about the design process of the settling chamber, the developed measurement device, and measurement data gained from the acceptance tests. Full article

(This article belongs to the Special Issue Selected Papers from the 10th EVI-GTI International Conference on Gas Turbine Instrumentation)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Int. J. Turbomach. Propuls. Power, Volume 9, Issue 4 (December 2024) – 3 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI