Refine
Year of publication
Institute
- ECSM European Center for Sustainable Mobility (132) (remove)
Document Type
- Conference Proceeding (62)
- Article (50)
- Part of a Book (8)
- Patent (3)
- Report (3)
- Conference: Meeting Abstract (2)
- Conference Poster (2)
- Book (1)
- Doctoral Thesis (1)
Keywords
- Energy storage (4)
- Power plants (4)
- UAV (4)
- Associated liquids (3)
- Concentrated solar power (3)
- Hybrid energy system (3)
- Obstacle avoidance (3)
- Brake set-up (2)
- Electricity generation (2)
- Freight rail (2)
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.
The first and last mile of a railway journey, in both freight and transit applications, constitutes a high effort and is either non-productive (e.g. in the case of depot operations) or highly inefficient (e.g. in industrial railways). These parts are typically managed on-sight, i.e. with no signalling and train protection systems ensuring the freedom of movement. This is possible due to the rather short braking distances of individual vehicles and shunting consists. The present article analyses the braking behaviour of such shunting units. For this purpose, a dedicated model is developed. It is calibrated on published results of brake tests and validated against a high-definition model for low-speed applications. Based on this model, multiple simulations are executed to obtain a Monte Carlo simulation of the resulting braking distances. Based on the distribution properties and established safety levels, the risk of exceeding certain braking distances is evaluated and maximum braking distances are derived. Together with certain parameters of the system, these can serve in the design and safety assessment of driver assistance systems and automation of these processes.
Die IMechE Railway Challenge wird jährlich in Stapleford, Großbritannien ausgetragen. Im Rahmen der Challenge entwickeln und bauen Studierende eine Lokomotive und vergleichen sich in verschiedenen Disziplinen, darunter eine automatisierte Zielbremsung, optimale Energierückgewinnung beim Bremsen und minimale Geräuschemissionen. Neben diesen und weiteren technischen Wettbewerbsdisziplinen treten die Fahrzeuge und die Teams auch in nicht-technischen Disziplinen wie einer Business Case Challenge an.
This study reviews the practice of brake tests in freight railways, which is time consuming and not suitable to detect certain failure types. Public incident reports are analysed to derive a reasonable brake test hardware and communication architecture, which aims to provide automatic brake tests at lower cost than current solutions. The proposed solutions relies exclusively on brake pipe and brake cylinder pressure sensors, a brake release position switch as well as radio communication via standard protocols. The approach is embedded in the Wagon 4.0 concept, which is a holistic approach to a smart freight wagon. The reduction of manual processes yields a strong incentive due to high savings in manual
labour and increased productivity.
Berücksichtigung von No Fault Found im Diagnose- und Instandhaltungssystem von Schienenfahrzeugen
(2020)
Intermittierende und nicht reproduzierbare Fehler, auch als No Fault Found bezeichnet, treten in praktisch allen Bereichen auf und sorgen für hohe Kosten. Diese sind häufig auf unpräzise Fehlerbeschreibungen zurückzuführen. Im vorliegenden Beitrag werden Anpassungen der Vorgehensweise bei der Entwicklung und Anpassungen des Diagnosesystems vorgeschlagen.
In many instances, freight vehicles exchange load or information with plants that are or will soon be Industry4.0 plants. The Wagon4.0 concept, as developed in close cooperation with e.g. port or mine operations, offers a maximum in railway operational efficiency while providing strong business cases already in the respective plant interaction. The Wagon4.0 consists of main components, a power supply, data network, sensors, actuators and an operating system, the so called WagonOS. The Wagon OS is implemented in a granular, self-sufficient manner, to allow basic features such as WiFi-Mesh and train christening in remote areas without network connection. Furthermore, the granularity of the operating system allows to extend the familiar app concept to freight rail rolling stock, making it possible to use specialised actuators for certain applications, e.g. an electrical parking brake or an auxiliary drive. In order to facilitate migration to the Wagon4.0 for existing fleets, a migration concept featuring five levels of technical adaptation was developed. The present paper investigates the benefits of Wagon4.0-implementations for the particular challenges of heavy haul operations by focusing on train christening, ep-assisted braking, autonomous last mile and traction boost operation as well as improved maintenance schedules