06 Fakultät Luft- und Raumfahrttechnik und Geodäsie
Permanent URI for this collectionhttps://elib.uni-stuttgart.de/handle/11682/7
Browse
3 results
Search Results
Item Open Access Uncertainty quantification for full-flight data based engine fault detection with neural networks(2022) Weiss, Matthias; Staudacher, Stephan; Mathes, Jürgen; Becchio, Duilio; Keller, ChristianCurrent state-of-the-art engine condition monitoring is based on a minimum of one steady-state data point per flight. Due to the scarcity of available data points, there are difficulties distinguishing between random scatter and an underlying fault introducing a detection latency of several flights. Today’s increased availability of data acquisition hardware in modern aircraft provides continuously sampled in-flight measurements, so-called full-flight data. These full-flight data give access to sufficient data points to detect faults within a single flight, significantly improving the availability and safety of aircraft. Artificial neural networks are considered well suited for the timely analysis of an extensive amount of incoming data. This article proposes uncertainty quantification for artificial neural networks, leading to more reliable and robust fault detection. An existing approach for approximating the aleatoric uncertainty was extended by an Out-of-Distribution Detection in order to take the epistemic uncertainty into account. The method was statistically evaluated, and a grid search was performed to evaluate optimal parameter combinations maximizing the true positive detection rates. All test cases were derived based on in-flight measurements of a commercially operated regional jet. Especially when requiring low false positive detection rates, the true positive detections could be improved 2.8 times while improving response times by approximately 6.9 compared to methods only accounting for the aleatoric uncertainty.Item Open Access Steady-state fault detection with full-flight data(2022) Weiss, Matthias; Staudacher, Stephan; Becchio, Duilio; Keller, Christian; Mathes, JürgenAircraft engine condition monitoring is a key technology for increasing safety and reducing maintenance expenses. Current engine condition monitoring approaches use a minimum of one steady-state snapshot per flight. Whilst being appropriate for trending gradual engine deterioration, snapshots result in a detrimental latency in fault detection. The increased availability of non-mandatory data acquisition hardware in modern airplanes provides so-called full-flight data sampled continuously during flight. These datasets enable the detection of engine faults within one flight by deriving a statistically relevant set of steady-state data points, thus, allowing the application of machine-learning approaches. It is shown that low-pass filtering before steady-state detection significantly increases the success rate in detecting steady-state data points. The application of Principal Component Analysis halves the number of relevant dimensions and provides a coordinate system of principal components retaining most of the variance. Consequently, clusters of data points with and without engine fault can be separated visually and numerically using a One-Class Support Vector Machine. High detection rates are demonstrated for various component faults and even for a minimum instrumentation suite using synthesized datasets derived from full-flight data of commercially operated flights. In addition to the tests conducted with synthesized data, the algorithm is verified based on operational in-flight measurements providing a proof-of-concept. Consequently, the availability of continuously sampled in-flight measurements combined with machine-learning methods allows fault detection within a single flight.Item Open Access A model to assess the importance of runway and taxiway particles to aircraft engine compressor deterioration(2024) Scarso, Stefano; Staudacher, Stephan; Mathes, Jürgen; Schwarz, NormanDuring service, civil turbofans experience environmentally induced deterioration. Predicting this in a digital service twin model is computationally challenging due to the need to model both deterioration mechanisms and environmental conditions. For compressor erosion, a key challenge is to model particle ingestion throughout a flight mission (FM). During ground operations, these particles may be airborne or deposited on runways and taxiways. This work assesses the impact of the latter on turbofan core compressor deterioration during a mission. The airflow field in front of the engine intake is approximated using potential flow theory. Comparisons with measurements show that the predicted air velocity near the engine is underestimated since the inlet ground vortices generated from viscous effects are neglected. The forces acting on the particles are derived from the flow field. It turns out that most particles are lifted from the ground during take-off (TO). Yet only smaller particles below ≈50 µm are ingested into the engine intake. A deterioration model based on flat plate erosion experiments is used to compute mission severity, assuming all particles are similar to medium Arizona Road Dust. The results indicate that the engine’s distance from the ground, power setting, and the number of particles on the ground are key parameters influencing the impact of runway and taxiway particles. Considering the underestimation of the airflow field and thus the number of particles ingested, it is concluded that runway and taxiway particles play a major role in turbofan compressor deterioration.