Refine
Year of publication
Institute
- Fachbereich Elektrotechnik und Informationstechnik (718) (remove)
Language
- English (718) (remove)
Document Type
- Article (414)
- Conference Proceeding (234)
- Part of a Book (38)
- Book (23)
- Conference: Meeting Abstract (5)
- Patent (2)
- Conference Poster (1)
- Doctoral Thesis (1)
Keywords
- Enterprise Architecture (5)
- MINLP (5)
- Engineering optimization (4)
- Optimization (3)
- Powertrain (3)
- Technical Operations Research (3)
- Telecommunication (3)
- Competence Developing Games (2)
- Energy efficiency (2)
- Engineering education (2)
In this paper, the use of reinforcement learning (RL) in control systems is investigated using a rotatory inverted pendulum as an example. The control behavior of an RL controller is compared to that of traditional LQR and MPC controllers. This is done by evaluating their behavior under optimal conditions, their disturbance behavior, their robustness and their development process. All the investigated controllers are developed using MATLAB and the Simulink simulation environment and later deployed to a real pendulum model powered by a Raspberry Pi. The RL algorithm used is Proximal Policy Optimization (PPO). The LQR controller exhibits an easy development process, an average to good control behavior and average to good robustness. A linear MPC controller could show excellent results under optimal operating conditions. However, when subjected to disturbances or deviations from the equilibrium point, it showed poor performance and sometimes instable behavior. Employing a nonlinear MPC Controller in real time was not possible due to the high computational effort involved. The RL controller exhibits by far the most versatile and robust control behavior. When operated in the simulation environment, it achieved a high control accuracy. When employed in the real system, however, it only shows average accuracy and a significantly greater performance loss compared to the simulation than the traditional controllers. With MATLAB, it is not yet possible to directly post-train the RL controller on the Raspberry Pi, which is an obstacle to the practical application of RL in a prototyping or teaching setting. Nevertheless, RL in general proves to be a flexible and powerful control method, which is well suited for complex or nonlinear systems where traditional controllers struggle.
This paper presents an approach for reducing the cognitive load for humans working in quality control (QC) for production processes that adhere to the 6σ -methodology. While 100% QC requires every part to be inspected, this task can be reduced when a human-in-the-loop QC process gets supported by an anomaly detection system that only presents those parts for manual inspection that have a significant likelihood of being defective. This approach shows good results when applied to image-based QC for metal textile products.
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.
This paper introduces an inexpensive Wiegand-sensor-based rotary encoder that avoids rotating magnets and is suitable for electrical-drive applications. So far, Wiegand-sensor-based encoders usually include a magnetic pole wheel with rotating permanent magnets. These encoders combine the disadvantages of an increased magnet demand and a limited maximal speed due to the centripetal force acting on the rotating magnets. The proposed approach reduces the total demand of permanent magnets drastically. Moreover, the rotating part is manufacturable from a single piece of steel, which makes it very robust and cheap. This work presents the theoretical operating principle of the proposed approach and validates its benefits on a hardware prototype. The presented proof-of-concept prototype achieves a mechanical resolution of 4.5 ° by using only 4 permanent magnets, 2Wiegand sensors and a rotating steel gear wheel with 20 teeth.
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
An experimental command and control information system based on Enterprise Java bean technology
(2002)
Purpose:
MRI plays a leading diagnostic role in assessing the musculoskeletal (MSK) system and is well established for most questions at clinically used field strengths (up to 3 T). However, there are still limitations in imaging early stages of cartilage degeneration, very fine tendons and ligaments, or in locating nerve lesions, for example. 7 T MRI of the knee has already received increasing attention in the current published literature, but there is a strong need to develop new radiofrequency (RF) coils to assess more regions of the MSK system. In this work, an eight-channel transmit/receive RF array was built as a multipurpose coil for imaging some of the thus far neglected regions. An extensive coil characterization protocol and first in vivo results of the human wrist, shoulder, elbow, knee, and ankle imaged at 7 T will be presented.
Methods:
Eight surface loop coils with a dimension ofurn:x-wiley:00942405:media:mp7176:mp7176-math-0001 were machined from FR4 circuit board material. To facilitate easy positioning, two coil clusters, each with four loop elements, were combined to one RF transmit/receive array. An overlapped and shifted arrangement of the coil elements was chosen to reduce the mutual inductance between neighboring coils. A phantom made of body-simulating liquid was used for tuning and matching on the bench. Afterward, the S-parameters were verified on a human wrist, elbow, and shoulder. For safety validation, a detailed compliance test was performed including full wave simulations of the RF field distribution and the corresponding specific absorption rate (SAR) for all joints. In vivo images of four volunteers were assessed with gradient echo and spin echo sequences modified to obtain optimal image contrast, full anatomic coverage, and the highest spatial resolution within a reasonable acquisition time. The performance of the RF coil was additionally evaluated by in vivo B1 mapping.
Results:
A comparison of B1 per unit power, flip angle distribution, and anatomic images showed a fairly homogeneous excitation for the smaller joints (elbow, wrist, and ankle), while for the larger joints, the shoulder and especially the knee, B1 inhomogeneities and limited penetration depth were more pronounced. However, the greater part of the shoulder joint could be imaged.In vivo images rendered very fine anatomic details such as fascicles of the median nerve and the branching of the nerve bundles. High-resolution images of cartilage, labrum, and tendons could be acquired. Additionally, turbo spin echo (TSE) and inversion recovery sequences performed very well.
Conclusions:
This study demonstrates that the concept of two four-channel transmit/receive RF arrays can be used as a multipurpose coil for high-resolutionin vivo MR imaging of the musculoskeletal system at 7 T. Not only gradient echo but also typical clinical and SAR-intensive sequences such as STIR and TSE performed well. Imaging of small structures and peripheral nerves could in particular benefit from this technique.