TY - CHAP A1 - Thoma, Andreas A1 - Fisher, Alex A1 - Braun, Carsten T1 - Improving the px4 avoid algorithm by bio-inspired flight strategies T2 - DLRK2020 - „Luft- und Raumfahrt – Verantwortung in allen Dimensionen“ Y1 - 2020 U6 - https://doi.org/10.25967/530183 N1 - Deutscher Luft- und Raumfahrtkongress 2020, 1. bis 3. September 2020 – Online, „Luft- und Raumfahrt – Verantwortung in allen Dimensionen“ ER - TY - CHAP A1 - Wu, Ziyi A1 - Kemper, Hans T1 - The optimal 48 V – battery pack for a specific load profile of a heavy duty vehicle T2 - 8. Internationale Fachtagung Kraftwerk Batterie : 26. – 27. April 2016, Münster, Deutschland Y1 - 2016 ER - TY - CHAP A1 - Neu, Eugen A1 - Janser, Frank A1 - Khatibi, Akbar A. A1 - Orifici, Adrian C. T1 - In-flight vibration-based structural health monitoring of aircraft wings T2 - 30th Congress of the internatonal council of the aeronautical sciences : 25.-30. September 2016, Daejeon, Korea N2 - This work presents a methodology for automated damage-sensitive feature extraction and anomaly detection under multivariate operational variability for in-flight assessment of wings. The method uses a passive excitation approach, i. e. without the need for artificial actuation. The modal system properties (natural frequencies and damping ratios) are used as damage-sensitive features. Special emphasis is placed on the use of Fiber Bragg Grating (FBG) sensing technology and the consideration of Operational and Environmental Variability (OEV). Measurements from a wind tunnel investigation with a composite cantilever equipped with FBG and piezoelectric sensors are used to successfully detect an impact damage. In addition, the feasibility of damage localisation and severity estimation is evaluated based on the coupling found between damageand OEV-induced feature changes. Y1 - 2016 ER - TY - CHAP A1 - Dinghofer, Kai A1 - Hartung, Frank T1 - Analysis of Criteria for the Selection of Machine Learning Frameworks T2 - 2020 International Conference on Computing, Networking and Communications (ICNC) N2 - With the many achievements of Machine Learning in the past years, it is likely that the sub-area of Deep Learning will continue to deliver major technological breakthroughs [1]. In order to achieve best results, it is important to know the various different Deep Learning frameworks and their respective properties. This paper provides a comparative overview of some of the most popular frameworks. First, the comparison methods and criteria are introduced and described with a focus on computer vision applications: Features and Uses are examined by evaluating papers and articles, Adoption and Popularity is determined by analyzing a data science study. Then, the frameworks TensorFlow, Keras, PyTorch and Caffe are compared based on the previously described criteria to highlight properties and differences. Advantages and disadvantages are compared, enabling researchers and developers to choose a framework according to their specific needs. Y1 - 2020 U6 - https://doi.org/10.1109/ICNC47757.2020.9049650 N1 - 2020 International Conference on Computing, Networking and Communications (ICNC), 17-20 February 2020, Big Island, HI, USA SP - 373 EP - 377 PB - IEEE CY - New York, NY ER - TY - CHAP A1 - Kreyer, Jörg A1 - Müller, Marvin A1 - Esch, Thomas T1 - A Map-Based Model for the Determination of Fuel Consumption for Internal Combustion Engines as a Function of Flight Altitude N2 - In addition to very high safety and reliability requirements, the design of internal combustion engines (ICE) in aviation focuses on economic efficiency. The objective must be to design the aircraft powertrain optimized for a specific flight mission with respect to fuel consumption and specific engine power. Against this background, expert tools provide valuable decision-making assistance for the customer. In this paper, a mathematical calculation model for the fuel consumption of aircraft ICE is presented. This model enables the derivation of fuel consumption maps for different engine configurations. Depending on the flight conditions and based on these maps, the current and the integrated fuel consumption for freely definable flight emissions is calculated. For that purpose, an interpolation method is used, that has been optimized for accuracy and calculation time. The mission boundary conditions flight altitude and power requirement of the ICE form the basis for this calculation. The mathematical fuel consumption model is embedded in a parent program. This parent program presents the simulated fuel consumption by means of an example flight mission for a representative airplane. The focus of the work is therefore on reproducing exact consumption data for flight operations. By use of the empirical approaches according to Gagg-Farrar [1] the power and fuel consumption as a function of the flight altitude are determined. To substantiate this approaches, a 1-D ICE model based on the multi-physical simulation tool GT-Suite® has been created. This 1-D engine model offers the possibility to analyze the filling and gas change processes, the internal combustion as well as heat and friction losses for an ICE under altitude environmental conditions. Performance measurements on a dynamometer at sea level for a naturally aspirated ICE with a displacement of 1211 ccm used in an aviation aircraft has been done to validate the 1-D ICE model. To check the plausibility of the empirical approaches with respect to the fuel consumption and performance adjustment for the flight altitude an analysis of the ICE efficiency chain of the 1-D engine model is done. In addition, a comparison of literature and manufacturer data with the simulation results is presented. Y1 - 2020 U6 - https://doi.org/10.25967/490162 N1 - 68. Deutscher Luft- und Raumfahrtkongress 30.09.-02.10.2019, Darmstadt PB - DGLR CY - Bonn ER - TY - CHAP A1 - Finger, Felix A1 - de Vries, Reynard A1 - Vos, Roelof A1 - Braun, Carsten A1 - Bil, Cees T1 - A comparison of hybrid-electric aircraft sizing methods T2 - AIAA Scitech 2020 Forum N2 - The number of case studies focusing on hybrid-electric aircraft is steadily increasing, since these configurations are thought to lead to lower operating costs and environmental impact than traditional aircraft. However, due to the lack of reference data of actual hybrid-electric aircraft, in most cases, the design tools and results are difficult to validate. In this paper, two independently developed approaches for hybrid-electric conceptual aircraft design are compared. An existing 19-seat commuter aircraft is selected as the conventional baseline, and both design tools are used to size that aircraft. The aircraft is then re-sized under consideration of hybrid-electric propulsion technology. This is performed for parallel, serial, and fully-electric powertrain architectures. Finally, sensitivity studies are conducted to assess the validity of the basic assumptions and approaches regarding the design of hybrid-electric aircraft. Both methods are found to predict the maximum take-off mass (MTOM) of the reference aircraft with less than 4% error. The MTOM and payload-range energy efficiency of various (hybrid-) electric configurations are predicted with a maximum difference of approximately 2% and 5%, respectively. The results of this study confirm a correct formulation and implementation of the two design methods, and the data obtained can be used by researchers to benchmark and validate their design tools. Y1 - 2020 U6 - https://doi.org/10.2514/6.2020-1006 N1 - AIAA Scitech 2020 Forum, Driving aerospace solutions for global challenges, Orlando, 06. - 10. January 2020 ER - TY - CHAP A1 - Nikolovski, Gjorgji A1 - Reke, Michael A1 - Elsen, Ingo A1 - Schiffer, Stefan T1 - Machine learning based 3D object detection for navigation in unstructured environments T2 - 2021 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops) N2 - In this paper we investigate the use of deep neural networks for 3D object detection in uncommon, unstructured environments such as in an open-pit mine. While neural nets are frequently used for object detection in regular autonomous driving applications, more unusual driving scenarios aside street traffic pose additional challenges. For one, the collection of appropriate data sets to train the networks is an issue. For another, testing the performance of trained networks often requires tailored integration with the particular domain as well. While there exist different solutions for these problems in regular autonomous driving, there are only very few approaches that work for special domains just as well. We address both the challenges above in this work. First, we discuss two possible ways of acquiring data for training and evaluation. That is, we evaluate a semi-automated annotation of recorded LIDAR data and we examine synthetic data generation. Using these datasets we train and test different deep neural network for the task of object detection. Second, we propose a possible integration of a ROS2 detector module for an autonomous driving platform. Finally, we present the performance of three state-of-the-art deep neural networks in the domain of 3D object detection on a synthetic dataset and a smaller one containing a characteristic object from an open-pit mine. KW - 3D object detection KW - LiDAR KW - autonomous driving KW - Deep learning KW - Three-dimensional displays Y1 - 2021 SN - 978-1-6654-7921-9 U6 - https://doi.org/10.1109/IVWorkshops54471.2021.9669218 N1 - 2021 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops), 11-17 July 2021, Nagoya, Japan. SP - 236 EP - 242 PB - IEEE ER - TY - CHAP A1 - Schuba, Marko A1 - Höfken, Hans-Wilhelm A1 - Linzbach, Sophie T1 - An ICS Honeynet for Detecting and Analyzing Cyberattacks in Industrial Plants T2 - 2021 International Conference on Electrical, Computer and Energy Technologies (ICECET) N2 - Cybersecurity of Industrial Control Systems (ICS) is an important issue, as ICS incidents may have a direct impact on safety of people or the environment. At the same time the awareness and knowledge about cybersecurity, particularly in the context of ICS, is alarmingly low. Industrial honeypots offer a cheap and easy to implement way to raise cybersecurity awareness and to educate ICS staff about typical attack patterns. When integrated in a productive network, industrial honeypots may not only reveal attackers early but may also distract them from the actual important systems of the network. Implementing multiple honeypots as a honeynet, the systems can be used to emulate or simulate a whole Industrial Control System. This paper describes a network of honeypots emulating HTTP, SNMP, S7communication and the Modbus protocol using Conpot, IMUNES and SNAP7. The nodes mimic SIMATIC S7 programmable logic controllers (PLCs) which are widely used across the globe. The deployed honeypots' features will be compared with the features of real SIMATIC S7 PLCs. Furthermore, the honeynet has been made publicly available for ten days and occurring cyberattacks have been analyzed KW - Conpot KW - honeypot KW - honeynet KW - ICS KW - cybersecurity Y1 - 2022 SN - 978-1-6654-4231-2 SN - 978-1-6654-4232-9 U6 - https://doi.org/10.1109/ICECET52533.2021.9698746 N1 - 2021 International Conference on Electrical, Computer and Energy Technologies (ICECET). 09-10 December 2021. Cape Town, South Africa. PB - IEEE ER - TY - CHAP A1 - Christian, Esser A1 - Montag, Tim A1 - Schuba, Marko A1 - Allhof, Manuel T1 - Future critical infrastructure and security - cyberattacks on charging stations T2 - 31st International Electric Vehicle Symposium & Exhibition and International Electric Vehicle Technology Conference (EVS31 & EVTeC 2018) Y1 - 2018 SN - 978-1-5108-9157-9 SP - 665 EP - 671 PB - Society of Automotive Engineers of Japan (JSAE) CY - Tokyo ER - TY - CHAP A1 - Walter, Peter A1 - Elsen, Ingo A1 - Müller, Holger A1 - Kraiss, Karl-Friedrich T1 - 3D object recognition with a specialized mixtures of experts architecture T2 - IJCNN'99. International Joint Conference on Neural Networks. Proceedings N2 - Aim of the AXON2 project (Adaptive Expert System for Object Recogniton using Neuml Networks) is the development of an object recognition system (ORS) capable of recognizing isolated 3d objects from arbitrary views. Commonly, classification is based on a single feature extracted from the original image. Here we present an architecture adapted from the Mixtures of Eaqerts algorithm which uses multiple neuml networks to integmte different features. During tmining each neural network specializes in a subset of objects or object views appropriate to the properties of the corresponding feature space. In recognition mode the system dynamically chooses the most relevant features and combines them with maximum eficiency. The remaining less relevant features arz not computed and do therefore not decelerate the-recognition process. Thus, the algorithm is well suited for ml-time applications. Y1 - 1999 SN - 0-7803-5529-6 U6 - https://doi.org/10.1109/IJCNN.1999.836243 SN - 1098-7576 N1 - Washington, DC 10-16.07.1999 SP - 3563 EP - 3568 PB - IEEE CY - New York ER -