Search Results (2)

Current 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. Full article

Modern avionics can account for around 30% of the total cost of the aircraft. Therefore, it is essential to reduce the operational cost of avionics during a lifetime. This article addresses the critical scientific problem of creating the appropriate maintenance models for digital avionics systems that significantly increase their operational effectiveness. In this research, we propose the lifecycle cost equations to select the best option for the maintenance of digital avionics. The proposed cost equations consider permanent failures, intermittent faults, and false-positives occurred during the flight. The lifecycle cost equations are determined for the warranty and the post-warranty interval of aircraft operation. We model several maintenance options for each period of service. The cost equations consider the characteristics of the permanent failures and intermittent faults, conditional probabilities of in-flight false-positive and true-positive as well as the cost of different maintenance operations, duration of the flight, and some other parameters. We have demonstrated that a three-level post-warranty maintenance variant with a detector of intermittent faults is the best because it minimizes the total expected maintenance cost several folds compared to other maintenance options. Full article