1 - 5 of 5
-
PublicationKünstliche Neuronale Netze zur Qualitätsprognose von Funktional Gradierten Materialien im laserbasierten Directed Energy Deposition( 2023-09-25)
-
PublicationLearning Factory for Circular Economy and the Corporate Environment( 2023)Especially in times of dwindling resources, the importance of circular economy continues to grow. Challenges often arise in circular material processing due to a lack of easily accessible information. This information paves the way for a simplified and reliable decision-making process in favor of economic advantages at the end of a product lifecycle. In order to facilitate the required cooperation between all relevant partners of such a sustainable value creation system, awareness must first be raised about the respective needs of all stakeholders and benefits of targeted information sharing. To address this problem, the paper describes a Learning Factory that demonstrates how such a targeted information loop can make the idea of the circular economy technically feasible and enable better use of the advantages of processing residual materials. To be able to display the entire value creation system and the interfaces between its members, the Situation Awareness Monitor developed at Fraunhofer IPK is useda tool that combines information about the company's environment as well as internal information. The Interactive Situation Awareness Monitor is used in this mobile Learning Factory, among other things, as a system for detecting deviations and consequently triggering an order for re-manufactured material. The paper describes the setup of a sustainable value creation systems, the approach of a Learning Factory, supported by the function of the interactive Situation Awareness Monitor in this context.
-
PublicationLearning Demonstrator for Anomaly Detection in Distributed Energy Generation( 2022-04-07)Machine learning based anomaly detection methods on process data can be used to secure critical infrastructure. The design and installation of these methods require detailed understanding of both the facilities and the machine learning methods. Therefore, they are mostly incomprehensible for non-experts and thus acting as a barrier hindering the fast spread of such technologies. This article presents the systematic development of a demonstrator which enables presentations of anomaly detection on the example of a simulated wind farm. The specially designed user-interface allows a comprehensive experience. This article documents the use of the demonstrator for experts experienced in energy systems which are interested in the application of machine learning algorithms.
-
PublicationSkalierbare Herstellung von ATMPs( 2022)
-
PublicationNonparametric Inverse Dynamic Models for Multimodal Interactive Robots( 2019)Direct design of a robot's rendered dynamics, such as in impedance control, is now a well-established control mode in uncertain environments. When the physical interaction port variables are not measured directly, dynamic and kinematic models are required to relate the measured variables to the interaction port variables. A typical example is serial manipulators with joint torque sensors, where the interaction occurs at the end-effector. As interactive robots perform increasingly complex tasks, they will be intermittently coupled with additional dynamic elements such as tools, grippers, or workpieces, some of which should be compensated and brought to the robot side of the interaction port, making the inverse dynamics multimodal. Furthermore, there may also be unavoidable and unmeasured external input when the desired system cannot be totally isolated. Towards semi-autonomous robots, capable of handling such applications, a multimodal Gaussian process regression approach to manipulator dynamic modelling is developed. A sampling-based approach clusters different dynamic modes from unlabelled data, also allowing the seperation of perturbed data with significant, irregular external input. The passivity of the overall approach is shown analytically, and experiments examine the performance and safety of this approach on a test actuator.
