Search

Analysis of aircraft trajectory data is used in different applications of aviation research. Areas such as Maintenance, Repair and Overhaul (MRO) and Air Traffic Management (ATM) benefit from a more detailed understanding of the trajectory, thus requiring the trajectory to be divided into the different flight phases. Flight phases are mostly computed from the aircrafts internal sensor parameters, which are very sensitive and have scarce availability to the public. This is why identification on publicly available data such as Automatic Dependent Surveillance Broadcast (ADS-B) trajectory data is essential. Some of the flight phases required for these applications are not covered by state-of-the-art flight phase identification on ADS-B trajectory data. This paper presents a novel machine learning approach for more detailed flight phase identification. We generate a training dataset with supervised simulation data obtained with the X-plane simulator. The model combines K-means clustering with a Long Short-Term Memory (LSTM) network, the former allows the segmentation to capture transitions between phases more closely, and the latter learns the dynamics of a flight. We are able to identify a larger variety of phases compared to state of the art and adhere to the International Civil Aviation Organisation (ICAO) standard.

The digital transformation poses a major challenge to the aviation industry with its diverse fields of operations and its mostly historically evolved organizational structure. But there is a lot of potential in the individual organizations for increasing efficiency and reducing obstacles for interoperability by establishing different digitalization concepts. In the past, research has been conducted on various technologies such as assistance systems, automation or inspection and image processing methodologies in the field of composite repair. However, digitalizing individual process steps using a new technology does not necessarily mean that it will also result in a more efficient overall process. For more efficient processes and the implementation of the vision of a digital twin, the digitalization and consideration of the respective holistic process is necessary. Data consistency, which should run like a thread through all process stages is a key factor and requires a corresponding data management concept. The repair process for fiber-reinforced composite structures, see Figure 1, is the basis for the development of a vision for a digital transformation in this work. The reason for this is, that the tasks in this process are usually carried out manually. The resulting media disruptions during the technical execution as well as during the final documentation limit the usability of information. This leads to an additional effort for information interpretation during the process execution and inhibits the potential for a data-based learning and improvement process. In the first part of this paper, the individual process steps are presented according to the current state of the art. This is followed by a process modification doing research regarding suitable technology concepts, which could be used to allow the complete digitalization of the process flow. Based on this, a corresponding data management system for the modified process will is designed, that enables an interaction between the process itself and the digital twin.