Refine
Year of publication
- 2023 (115) (remove)
Document Type
- Conference Proceeding (115) (remove)
Conference Type
- Konferenzartikel (88)
- Konferenz-Abstract (20)
- Konferenz-Poster (2)
- Konferenzband (2)
- Sonstiges (2)
Keywords
- Biomechanik (9)
- Deep Leaning (7)
- Additive Manufacturing (3)
- RoboCup (3)
- AI-Aided Innovation (2)
- Artificial Intelligence (2)
- Augmented Reality (2)
- Creativity (2)
- Current measurement (2)
- Deep Learning (2)
- Festigkeit (2)
- Kalman Filter (2)
- Künstliche Intelligenz (2)
- Machine Learning (2)
- Materialermüdung (2)
- Mobile Applications (2)
- Rissausbreitung (2)
- Switches (2)
- User Experience (2)
- Visual Programming (2)
- certificate management (2)
- programming (2)
- 100% Renewable (1)
- 3D analysis (1)
- 3D bin picking (1)
- 3D printing (1)
- 3D-Druck (1)
- 4D-Druck (1)
- 4D-Printing (1)
- 5G mobile communication (1)
- AI aided Innovation (1)
- AR (1)
- Academic Advising (1)
- Actuators (1)
- Additive Fertigung (1)
- Additive Tooling (1)
- Adressdaten (1)
- Aluminum (1)
- Anti-Windup (1)
- Artistic Research (1)
- Authentication (1)
- Authorization (1)
- Automated Ideation (1)
- Automation (1)
- Bearings (1)
- Benutzererlebnis (1)
- Bike Path Analysis (1)
- Binary Executable (1)
- Bio-based materials (1)
- Bio-based plastics (1)
- Blockchain (1)
- Blockchains (1)
- Boundary conditions (1)
- Bowtie antenna (1)
- Building energy efficiency (1)
- Business Model Canvas (1)
- Cameras (1)
- Chatbot (1)
- Checkout (1)
- Checkout-Prozess (1)
- Chemical Engineering (1)
- Cleaning (1)
- Collaboration (1)
- Computer Aided Innovation (1)
- Context-based Services (1)
- Convolutional neural networks (1)
- Curricular concepts (1)
- Cybersecurity (1)
- Data breech (1)
- Datenqualität (1)
- Debinding (1)
- Deep Neural Network (1)
- Degradability (1)
- Design Methods (1)
- Design Science (1)
- Design method (1)
- Didaktisches Konzept (1)
- Digital Flex Twin Optimization (1)
- Digitalisierung (1)
- EAP-TLS (1)
- EKF-SLAM (1)
- EMG features (1)
- Easter Package (1)
- Eco-Innovation (1)
- Eco-inventive Principles (1)
- Education (1)
- Electronic Commerce (1)
- Electronic Shopping (1)
- Emotional Communication (1)
- Emotional Interaction (1)
- Empirical Research (1)
- Empirical Studies (1)
- Empirical research (1)
- Energieeffizienz (1)
- Energieverbrauch (1)
- Energy Flexibility (1)
- Energy Flexibility for Companies (1)
- Energy Marketing of Industrial Flexibilities (1)
- Energy Storage Systems (1)
- Energy Transition (1)
- Engineering Creativity (1)
- Engineering Design (1)
- Estimation (1)
- Extrusion (1)
- Failure analysis (1)
- Fault Classification (1)
- Fertigungsautomatisierung (1)
- Fiber reinforcement (1)
- Filament (1)
- Fused Filament Fabrication (1)
- Gait phase detection (1)
- Geschäftsmodell (1)
- Handschrift (1)
- Handswritten Character Recognition (1)
- Harmonic analysis (1)
- Heat pumps (1)
- Helmholtz coil (1)
- Heuristische Evaluation, (1)
- High-Cycle Fatigue (1)
- Hochschuldidaktik (1)
- Hot forging (1)
- Humanoid Robots (1)
- Humanoid robot (1)
- Humanoid robots programming (1)
- Hybrid system (1)
- IDL (1)
- IEC/IEEE 60802 security (1)
- IIoT (1)
- IYL (1)
- Image restoration (1)
- Immersive Technology (1)
- Inclined surface (1)
- Industrial Blockchain (1)
- Inertial measurement unit (1)
- Injection Molds (1)
- Innovation (1)
- Interactive Film (1)
- International Day of Light (1)
- International Year of Light (1)
- Inventive Design (1)
- Inverters (1)
- KI-Labor Südbaden (1)
- Kundendaten (1)
- LXP (1)
- Landau-Lifshitz-Gilbert equations (1)
- Lehre (1)
- Lernzieltaxonomie (1)
- Limiting (1)
- Location-Based Services (1)
- Location-based Services (1)
- Logic gates (1)
- Low-Cycle Fatigue (1)
- Machine learning (1)
- Magnetic sensors (1)
- Magnetismus (1)
- Manufacturing automation (1)
- Martensitic die steel (1)
- Material Extrusion (1)
- Mathtrails (1)
- Meters (1)
- Monitoring (1)
- Monocular Depth Estimation (1)
- Myocontrol (1)
- NETCONF security (1)
- Natural fibers (1)
- Neural networks (1)
- New Product Development (1)
- OT security (1)
- Object-Based Services (1)
- Online Magazine (1)
- Online-Shop (1)
- Optics and Photonics (1)
- Optimization (1)
- Optimization with Digital Twins (1)
- Optische Zeichenerkennung (1)
- PCB-printing (1)
- PI control (1)
- PKI (1)
- PROFINET Security (1)
- Parameter estimation (1)
- Performance (1)
- Performance evaluation (1)
- Periodic Table of AI (1)
- Permanent magnet machines (1)
- Physical unclonable function (1)
- Physikdidaktik (1)
- Plasticity model (1)
- Plastizität (1)
- Poisoning (1)
- PolyJet Modelling (1)
- Predictions (1)
- Predictive Maintenance (1)
- Process Design (1)
- Prosthetic control (1)
- Prozessautomation (1)
- Pulse width modulation (1)
- RPA (1)
- RUL (1)
- Radio frequency (1)
- Realtime simulation (1)
- Recommendation (1)
- Renewable Energy Markets (1)
- Robot Applications (1)
- Robot vision systems (1)
- Robotic Process Automation (1)
- Rotors (1)
- Running (1)
- Security (1)
- Selbsttests (1)
- Semiconductor device measurement (1)
- Sensor phenomena and characterization (1)
- Sensors (1)
- Sintering (1)
- Smart Materials (1)
- Soft Robot (1)
- Software (1)
- Software Robot (1)
- Software algorithms (1)
- Sound Synthesis (1)
- Sportmedizin (1)
- Stochastik (1)
- Stromregelung (1)
- Stromzustandsregler (1)
- Sustainable development (1)
- Sweaty (1)
- Synchronmaschine (1)
- TLS (1)
- TRIZ (1)
- TRIZ Inventive Principles (1)
- TSN security (1)
- Target Group Oriented Communication (1)
- Target Group Oriented Design (1)
- Temperature sensors (1)
- Testbed (1)
- Time Sensitive Networking (1)
- Time Synchronization (1)
- TinyML (1)
- Torque (1)
- Transfer learning (1)
- Trust management (1)
- Urformen (1)
- Usability (1)
- Use Case (1)
- VR (1)
- Verifiability (1)
- Virtual Reality (1)
- Virtual experiments (1)
- Visual programming (1)
- Visual programming languages (1)
- Voice User Experience (1)
- Warenkorbabbruch (1)
- Wireless IoT (1)
- Wärmepumpe (1)
- Yolov5 (1)
- accelerometer (1)
- accountability (1)
- accuracy (1)
- acoustic phonons (1)
- artificial intelligence (1)
- athletic performance (1)
- bearing (1)
- bench-marking (1)
- building energy model (1)
- cantilever (1)
- carbon elements (1)
- climate (1)
- crack growth simulation (1)
- credentials (1)
- cryptography (1)
- curriculum learning (1)
- cushioning (1)
- deep reinforcement learning (1)
- degradation stages (1)
- detection (1)
- efficient training (1)
- embedded systems (1)
- energy consumption (1)
- energy efficiency (1)
- energy harvesting (1)
- evaluation (1)
- exchange magnons (1)
- explainability (1)
- fairness (1)
- ferromagnetic resonance (1)
- force controlled robot (1)
- generation Y (1)
- generation Z (1)
- glazing systems (1)
- ground penetrating radar (1)
- heating and cooling (1)
- high-speed cameras (1)
- interactive visualization (1)
- joint torque sensors (1)
- kinetic (1)
- laser triangulation (1)
- learning scenarios (1)
- machine learning (1)
- magnetization dynamics (1)
- magneto-acoustics (1)
- magnetoactive smart materials (1)
- magnetresponsive Werkstoffe (1)
- measurement (1)
- media technology (1)
- metaverse (1)
- millimeter-wave (1)
- mobile applications (1)
- multi-material (1)
- optics and photonics (1)
- orthosis (1)
- performance (1)
- powder filled gripper (1)
- predictive maintenance (1)
- primary authentication (1)
- printed electronics (1)
- repeatability (1)
- research-oriented education (1)
- responsibility (1)
- road and track running (1)
- robot (1)
- robotics (1)
- running shoe (1)
- running shoes (1)
- secure communication (1)
- skin cancer (1)
- skin cancer detection (1)
- smart materials (1)
- solar module (1)
- sparse backpropagation (1)
- system authenticity (1)
- temperature sensor (1)
- thinned ASIC in foil (1)
- three-dimensional kinematic (1)
- transversal skills (1)
- trust (1)
- ultrafast laser interaction with materials (1)
- understandability (1)
- vacuum (1)
- vibration (1)
- virtual worlds (1)
Institute
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (46)
- Fakultät Maschinenbau und Verfahrenstechnik (M+V) (34)
- Fakultät Wirtschaft (W) (25)
- IMLA - Institute for Machine Learning and Analytics (14)
- ivESK - Institut für verlässliche Embedded Systems und Kommunikationselektronik (13)
- IBMS - Institute for Advanced Biomechanics and Motion Studies (ab 16.11.2022) (12)
- INES - Institut für nachhaltige Energiesysteme (12)
- Fakultät Medien (M) (ab 22.04.2021) (10)
- IUAS - Institute for Unmanned Aerial Systems (3)
- POIM - Peter Osypka Institute of Medical Engineering (2)
3D Bin Picking with an innovative powder filled gripper and a torque controlled collaborative robot
(2023)
A new and innovative powder filled gripper concept will be introduced to a process to pick parts out of a box without the use of a camera system which guides the robot to the part. The gripper is a combination of an inflatable skin, and a powder inside. In the unjammed condition, the powder is soft and can adjust to the geometry of the part which will be handled. By applying a vacuum to the inflatable skin, the powder gets jammed and transforms to a solid shaped form in which the gripper was brought before applying the vacuum. This physical principle is used to pick parts. The flexible skin of the gripper adjusts to all kinds of shapes, and therefore, can be used to realize 3D bin picking. With the help of a force controlled robot, the gripper can be pushed with a consistent force on flexible positions depending of the filling level of the box. A Kuka LBR iiwa with joint torque sensors in all of its seven axis’ was used to achieve a constant contact pressure. This is the basic criteria to achieve a robust picking process.
In recent years, predictive maintenance tasks, especially for bearings, have become increasingly important. Solutions for these use cases concentrate on the classification of faults and the estimation of the Remaining Useful Life (RUL). As of today, these solutions suffer from a lack of training samples. In addition, these solutions often require high-frequency accelerometers, incurring significant costs. To overcome these challenges, this research proposes a combined classification and RUL estimation solution based on a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) network. This solution relies on a hybrid feature extraction approach, making it especially appropriate for low-cost accelerometers with low sampling frequencies. In addition, it uses transfer learning to be suitable for applications with only a few training samples.
In 4D printing an additively manufactured component is given the ability to change its shape or function under the influence of an external stimulus. To achieve this, special smart materials are used that are able to react to external stimuli in a specific way. So far, a number of different stimuli have already been investigated and initial applications have been impressively demonstrated, such as self-folding bodies and simple grippers. However, a methodical specification for the selection of the stimuli and their implementation was not yet in the foreground of the development.
The focus of this work is therefore to develop a methodical approach with which the technology of 4DP can be used in a solution- and application-oriented manner. The developed approach is based on the conventional design methodology for product development to solve given problems in a structured way. This method is extended by specific approaches under consideration of the 4D printing and smart materials.
To illustrate the developed method, it is implemented in practice using a problem definition in the form of an application example. In this example, which represents the recovery of an object from a difficult-to-access environment, the individual functions of positioning, gripping and extraction are implemented using 4D printing. The material extrusion process is used for additive manufacturing of all components of the example. Finally, the functions are successfully tested. The developed approach offers an innovative and methodical approach to systematically solve technical complex problems using 4DP and smart materials.
This paper presents a system that uses a multi-stage AI analysis method for determining the condition and status of bicycle paths using machine learning methods. The approach for analyzing bicycle paths includes three stages of analysis: detection of the road surface, investigation of the condition of the bicycle paths, and identification of substrate characteristics. In this study, we focus on the first stage of the analysis. This approach employs a low-threshold data collection method using smartphone-generated video data for image recognition, in order to automatically capture and classify surface condition and status.
For the analysis convolutional neural networks (CNN) are employed. CNNs have proven to be effective in image recognition tasks and are particularly well-suited for analyzing the surface condition of bicycle paths, as they can identify patterns and features in images. By training the CNN on a large dataset of images with known surface conditions, the network can learn to identify common features and patterns and reliably classify them.
The results of the analysis are then displayed on digital maps and can be utilized in areas such as bicycle logistics, route planning, and maintenance. This can improve safety and comfort for cyclists while promoting cycling as a mode of transportation. It can also assist authorities in maintaining and optimizing bicycle paths, leading to more sustainable and efficient transportation system.
As cyber-attacks and functional safety requirements increase in Operational Technology (OT), implementing security measures becomes crucial. The IEC/IEEE 60802 draft standard addresses the security convergence in Time-Sensitive Networks (TSN) for industrial automation.We present the standard’s security architecture and its goals to establish end-to-end security with resource access authorization in OT systems. We compare the standard to our abstract technology-independent model for the management of cryptographic credentials during the lifecycles of OT systems. Additionally, we implemented the processes, mechanisms, and protocols needed for IEC/IEEE 60802 and extended the architecture with public key infrastructure (PKI) functionalities to support complete security management processes.
Ensuring that software applications present their users the most recent version of data is not trivial. Self-adjusting computations are a technique for automatically and efficiently recomputing output data whenever some input changes.
This article describes the software architecture of a large, commercial software system built around a framework for coarse-grained self-adjusting computations in Haskell. It discusses advantages and disadvantages based on longtime experience. The article also presents a demo of the system and explains the API of the framework.
Neural networks have a number of shortcomings. Amongst the severest ones is the sensitivity to distribution shifts which allows models to be easily fooled into wrong predictions by small perturbations to inputs that are often imperceivable to humans and do not have to carry semantic meaning. Adversarial training poses a partial solution to address this issue by training models on worst-case perturbations. Yet, recent work has also pointed out that the reasoning in neural networks is different from humans. Humans identify objects by shape, while neural nets mainly employ texture cues. Exemplarily, a model trained on photographs will likely fail to generalize to datasets containing sketches. Interestingly, it was also shown that adversarial training seems to favorably increase the shift toward shape bias. In this work, we revisit this observation and provide an extensive analysis of this effect on various architectures, the common L_2-and L_-training, and Transformer-based models. Further, we provide a possible explanation for this phenomenon from a frequency perspective.
Cast aluminum cylinder blocks are frequently used in gasoline and diesel internal combustion engines because of their light-weight advantage. However, the disadvantage of aluminum alloys is their relatively low strength and fatigue resistance which make aluminum blocks prone to fatigue cracking. Engine blocks must withstand a combination of low-cycle fatigue (LCF) thermal loads and high-cycle fatigue (HCF) combustion and dynamic loads. Reliable computational methods are needed that allow for accurate fatigue assessment of cylinder blocks under this combined loading. In several publications, the mechanism-based thermomechanical fatigue (TMF) damage model DTMF describing the growth of short fatigue cracks has been extended to include the effect of both LCF thermal loads and superimposed HCF loadings. This approach is applied to the finite life fatigue assessment of an aluminum cylinder block. The required material properties related to LCF are determined from uniaxial LCF tests. The additional material properties required for the assessment of superimposed HCF are obtained from the literature for similar materials. The predictions of the model agree well with engine dyno test results. Finally, some improvements to the current process are discussed.