Publication Server of Aschaffenburg University
Not a member yet
1531 research outputs found
Sort by
Adaptive self-learning controllers with disturbance compensation for automatic track guidance of industrial trucks
No full textThis paper presents an extended control concept for automatic track guidance of industrial trucks in intralogistic systems. It is based on Reinforcement Learning (RL), a method of Artificial Intelligence (AI). The presented approach is able to adapt itself to different industrial truck variants and to the associated specific vehicle parameters. In order to avoid starting the whole
training of the controller for each truck variant from scratch, the training process is divided into two steps. In the first step, the controller is trained on a simplified linear model using parameters
of a nominal vehicle variant. Based on this, the control parameters are only fine-tuned in the second step using a more complex nonlinear model, representing the real industrial truck. In this
way, the controller is adapted to the actual truck variant and the corresponding parameter values. By using the nonlinear model, it can be ensured that the forklift’s dynamic is approximated
within the entire operating range, even at high steering angles. Moreover, the influence of the disturbance variable of the system (path curvature) is compensated by considering this a priori
knowledge within the control design. Therefore, the
Artificial Neural Networks (ANN) of the RL controller and the observation vector are suitably adjusted. In this way, the occurring path curvatures can be considered in both training steps and the control parameters can be optimized accordingly. Thus, the influence of the disturbance variable can be compensated, which significantly improves the control quality. In order to demonstrate this, the new approach is compared
to an RL control concept, which is not considering the disturbance variable and to a classical
two-degrees-of-freedom (2DoF) control approach
Hommage auf einen bedeutenden Wissenschaftler - das Deutsche Röntgen-Museum
No full textIn diesem Jahr jährte sich der Todestag von Wilhelm Conrad Röntgen, gestorben am 10. Februar 1923, zum hundertsten Mal. Dieser Beitrag ist eine Hommage auf diesen bedeutenden deutschen Wissenschaftler. 1895 entdeckte er eine neue Art von Strahlung, welche in der Lage ist, feste Materialien zu durchdringen. 1901 erhielt Professor Röntgen für diese bahnbrechende Entdeckung den ersten Nobelpreis für Physik. Das Deutsche Röntgen-Museum (DRM) erforscht und dokumentiert das Leben und Werk von W. C. Röntgen und die Auswirkungen seiner Entdeckung auf eine einzigartige und umfassende Weise. Der Standort des DRM in Remscheid ist kein Zufall, denn Röntgens Geburtshaus liegt nur wenige Gehminuten von den Exponaten entfernt. Die Betonung der Vielfalt von Röntgens Erfindung durch das Museum mit einer multimedialen Herangehensweise ermöglicht es den Besuchern, hier ihre ganz persönlichen Entdeckungen zu machen. Jeder Museumsbesuch wird so zu einer einzigartigen Entdeckungsreise durch die Welt der Medizin, Wissenschaft und Technik. Dieser Beitrag würdigt das Lebenswerk von Professor Wilhelm Conrad Röntgen und gibt einen Einblick in die Geschichte der Röntgenstrahlen und ihre Anwendungsgebiete.Poste
Trends im Nachhaltigkeitscontrolling - Empirische Ergebnisse aus der Green Controlling Studie 2022 des ICV
No full textDie vorliegende Studie untersucht Entwicklungen und Trends im Nachhaltigkeitscontrolling, insbesondere hinsichtlich der strategischen Bedeutung der fünf Stufen der Nachhaltigkeit, des Einflusses von Stakeholdergruppen, Zielsetzungen und Instrumenten anhand von drei Studien des Fachkreis Green Controlling for Responsible Business und gibt Implikationen für die Controlling- und Unternehmenspraxis
Learning Analytics Dashboard for Educators: Proposed Project to Design with Pedagogical Background
No full textIn this article, the authors describe a prototype of a Learning Analytics Dashboard (LAD) for educators. It is based on the analysis of pedagogical actions and taking into the process and learning style of students in an online environment based on learning analytics (LA). A description of the Dashboard structure, divided into levels and categories based on available learning analytics, will allow the educator to dive deeper into the online course themselves and explore more. It will also allow them to determine the level of student performance, identify gaps in learning materials, and research student data.
The authors have identified further directions for the development of a LAD for a professor, including modeling algorithms for researching student behavior and learning style using Artificial Intelligence and presenting LA in a visualized form.
This paper shows the stages of creating a professor's LAD prototype as a functional part of the adaptive learning system in the HASKI-System to analyze visual information obtained from LA and the possibilities to monitor the learning process, learning progress, student activity, and make decisions on careful intervention in the students’ learning process
Adaptive Learning Path Sequencing Based on Learning Styles within N-dimensional Spaces
No full textPlanning adaptive learning paths for students’ progress throughout a course can be a challenging task, although it can be helpful for their learning progress. Within the HASKI-System, students should be able to get their own, personalized learning paths. In this paper, we present an approach towards the learning path sequencing problem. This idea is based on a novel proposal for arranging learning objects in a multi-dimensional space, bringing the relationship and similarities of these objects into a new relationship. We show, that we can use both, the Ant Colony Optimization Algorithm and the Genetic Algorithm with the idea of the Traveling-Salesman-Problem and get results, that are comparable with a proposed literature-based adaption mechanism. Nevertheless, the learning paths are all personalized based on the Felder & Silverman Learning Style Model and the hyperspace model will allow us later on to include more dimensions for other influencing factors
Drilling Sequence Optimization Using Evolutionary Algorithms to Reduce Heat Accumulation for Femtosecond Laser Drilling with Multi-Spot Beam Profiles
No full textWe report on laser drilling borehole arrays using ultrashort pulsed lasers with a particular focus on reducing the inadvertent heat accumulation across the workpiece by optimizing the drilling sequence. For the optimization, evolutionary algorithms are used and their results are verified by thermal simulation using Comsol and experimentally evaluated using a thermal imaging camera. To enhance process efficiency in terms of boreholes drilled per second, multi-spot approaches are employed using a spatial light modulator. However, as higher temperatures occur across the workpiece when using simultaneous multi-spot drilling as compared to a single-spot process, a subtle spatial distribution and sequence of the multi-spot approach has to be selected in order to limit the
resulting local heat input over the processing time. Different optimization approaches based on evolutionary algorithms aid to select those drilling sequences which allow for the combination of a high efficiency of multi-spot profiles, a low-generated process temperature and a high-component quality. In particular, using a 4 x 4 laser spot array allows for the drilling of 40,000 boreholes in less than 76 s (526 boreholes/s) with a reduced temperature increase by about 35%, as compared to a single spot process when employing an optimized drilling sequence
Analysis of the Impact of Recommendations from Intelligent Expert Systems on Personal Trust and Decision-Making Performance
No full textNaturalistic Driving Studies Data Analysis Based on a Convolutional Neural Network
No full textThe new generation of autonomous vehicles (AVs) are being designed to act autonomously and collect travel data based on various smart devices and sensors. The goal is to enable AVs to operate under their own power. Naturalistic driving studies (NDSs) collect data continuously from real traffic activities, in order not to miss any safety-critical event. In NDSs of AVs, however, the data they collect is influenced by various sources that degrade their forecasting accuracy. A convolutional neural network (CNN) is proposed to process a large amount of traffic data in different formats. A CNN can detect anomalies in traffic data that negatively affect traffic efficiency and identify the source of data anomalies, which can help reduce traffic congestion and vehicular queuing
Early and Accurate Recognition of Highway Traffic Maneuvers Considering Real-World Application : A Novel Framework Using Bayesian Networks
No full textThis paper presents a novel application of artificial cognitive systems to traffic scene understanding and early recognition of highway maneuvers. This is achieved by use of Bayesian networks for knowledge representation, to mimic the human reasoning on situation analysis and to manage inherited uncertainties in the automotive domain, that requires efficient and effective analysis of high volume and frequency data streams. The maneuver recognition uses features, analyzing the observed vehicles behavior and available free space on the target lane. Dynamic Bayesian networks (DBN) capture the motion of the own and surrounding vehicles as a dynamic process, following the trend development of lateral motion features. The static and dynamic models for maneuver recognition are statistically evaluated with real highway driving data sequences. The DBN demonstrates earlier recognition (∼ 1.1 seconds) and higher accuracy (1.12% error rate) with more stable performance than the static models. The system is deployed on an experimental vehicle, where a Divide-and-conquer approach to inference in object-oriented Bayesian networks is introduced and its implementation is shown to require computation time of 0.15 milliseconds and ROM memory ∼ 10 2 kilobytes. The promising performance evaluation results are confirmed by test drives in real highway traffic
ROOT CAUSE ANALYSIS FOR PULP AND PAPER APPLICATIONS
No full textWe propose a methodology for Root Cause Analysis (RCA), allowing fast and flexible decision support for operators, maintenance staff and process engineers in pulp and paper industry. RCA can identify non-obvious process problems and is therefore a powerful complement to normal automatic control. The general methodology is applied to a continuous digester