Micro turbojets are used for propelling radio-controlled aircraft, aerial targets and personal air vehicles. When compared to full-scale engines, they are characterized by relatively low efficiency and durability. In this context, the degraded performance of gas path components could lead to an unacceptable reduction in the overall engine performance. In this work, a data-driven model based on a conventional Artificial Neural Network (ANN) and an extreme learning machine (ELM) was used for estimating the performance degradation of the micro turbojet. The training datasets containing the performance data of the engine with degraded components were generated using the validated GSP model and the Monte Carlo approach. In particular, compressor and turbine performance degradation were simulated for three different flight regimes. It was confirmed that component degradation had a similar impact in flight than at sea level. Finally, the datasets were used in the training and testing process of the ELM algorithm with four different input vectors. Two vectors had an extensive number of virtual sensors, and the other two were reduced to just fuel flow and Exhaust Gas Temperature. Even with the small number of sensors, the high prediction accuracy of ELM was maintained for takeoff and cruise but was slightly worse for variable flight conditions.

Microturbines can be used not only in models and education but also to propel UAVs. However, their wider adoption is limited by their relatively low efficiency and durability. Validated simulation models are required to monitor their performance, improve their lifetime, and design engine control systems. This study aims at developing a numerical model of a micro gas turbine for prediction and prognostics of engine performance. To build a reliable zero-dimensional model, the available compressor and turbine maps were scaled to the available test bench data with the least squares method, to meet the performance of the engine achieved during bench and flight tests. A steady-state aeroengine model was implemented in GSP and compared with experimental operating points. The selected flight data was then used as input for the transient engine model. The exhaust gas temperature (EGT) and fuel flow were chosen as the two key parameters to validate the model, comparing the numerical predicted values with the experimental ones. The observed difference between the model and the flight data was lower than 3% for both EGT and fuel flow.

Alternative fuels containing biocomponents produced in various technologies are introduced in aviation to reduce its carbon footprint but there is little data describing their impact on the performance and emissions of engines. The purpose of the work is to compare the performance and gas emissions produced from two different jet engines: the GTM-140 microturbine and the full-size DGEN380 turbofan, powered by blends of Jet A-1 and one of two biocomponents: 1) ATJ and 2) HEFA produced from used cooking oil (UCO) in various concentrations. The acquired data will be used to develop an engine emissivity model to predict gas emissions. Blends of the mineral fuel with synthetic components were prepared in various concentrations, and their physicochemical parameters were examined in the laboratory. Measurements of emissions from both engines were carried out in selected operating points using the Semtech DS gaseous analyzer and the EEPS spectrometer. The impact of tested blends on engine operating parameters is limited, and their use does not carry the risk of a significant decrease in aircraft performance or increase in fuel consumption. Increasing the content of biocomponents causes a noticeable rise in the emission of CO and slight increase for some other gasses (HC and NOx), which should not, however, worsen the working conditions of the ground personnel. This implies that there are no contraindications against using tested blends for fuelling gas-turbine engines.