Fraunhofer-Institut für Produktionsanlagen und Konstruktionstechnik IPK

Filters

61
Reset filters

Settings
Now showing 1 - 10 of 61
  • Publication
    PowerGrasp: Development Aspects for Arm Support Systems
    ( 2022)
    Goppold, J.-P.
    ;
    Kuschan, J.
    ;
    Schmidt, H.
    ;
    Krüger, J.
    Exoskeletons can support workers on physically demanding tasks, but in industry they lack of acceptance. This contribution gives an insight into design aspects for upper body exoskeletons, especially how active exoskeletons for industrial applications differ from military and medical use-cases. To overcome typical rigid exoskeleton problems, we suggest the use of modular soft-exosuit support systems and therefore checked different types of soft actuation principles for their eligibility for the use on upper body joints. Most promising approach is using two-layered actuators sting of robust fabric with embedded rubber tubes as pressure chambers. By inflating the tubes, it is possible to vary the stiffness of the chambers, which can be effectively used to generate assisting forces and moments at human joints (shoulder, elbow, wrist, finger).
  • Publication
    PowerGrasp - Design and evaluation of a modular soft-robotic arm exosuit for industrial applications
    ( 2020)
    Goppold, J.-P.
    ;
    Kuschan, J.
    ;
    Thiele, G.
    ;
    Schmidt, H.
    ;
    Krüger, J.
    ;
    Hackbart, R.
    ;
    Kostelnik, J.
    ;
    Liebach, J.
    ;
    Wolschke, M.
    Absence from work caused by overloading the musculoskeletal system lowers the life quality of the worker and gains unnecessary costs for both the employer and the health system. Classical (rigid link) body-worn exoskeletons can help to reduce critical loading but show many disadvantages, preventing exoskeletons from extensive use in industrial environment. The presented PowerGrasp system is a very robust modular softrobotic arm exosuit sting of robust fabric with embedded rubber tubes as pressure chambers and soft-electronics and who's design is capable to overcome the critical limiting factors of classical exoskeletons. By inflating the tubes via pressure-control valves, it is possible to vary the stiffness of the chambers, which can be effectively used to generate assisting forces and moments at human joints. By using a joint based pressure control, it is possible to decrease the physical demand of overhead working for the wearer. Although the system is designed for i ndustrial overhead assembly, it can also be used in rehabilitation, craftsmanship and construction due to its portable and stand-alone concept. For assessing the impact of the PowerGrasp system, the raise of about 50 percent was shown. Finally, an evaluation study of the overall system has been conducted, showing very high user acceptance and usability.
  • Publication
    Networked Visual Servoing as Use-Case for Cloud-based Industrial Robot Control
    ( 2020)
    Vick, A.
    ;
    Krause, C.
    ;
    Krüger, J.
    Nowadays production industry and smart factory is dealing with methods of optimal resource load balancing and new types of flexible service-oriented strategies. It is seen crucial to adapt quickly to changes in manufacturing processes and new products or even integrate new hardware faster than the competition. Flexibility and Scalability can be improved by exchanging only a certain part of hardware and software without the need of touching all the other components. In this paper we present a methodical approach towards a typical use case in modern industrial robotic systems. The system consists of hardware components from different manufacturers which can be controlled and monitored separately by remote services. Those services can be combined to complex applications and integrate value added services. We show the independence and capability of exchangeable added value services running either centralized, decentralized, locally or remote. The experiments demonstrate how a process is improve by simply adding another service according to the Plug-and-Play paradigm. The service ensures the conditions of a computer vision system component to keep the reliability of the overall system workflow. In addition it will be demonstrated how system components could be virtualized in container-based cloud environments to save required on-board resources of the robotic system while keeping the whole system communication secure. Finally, results will be presented for different intercommunication scenarios.
  • Publication
    System identification of a hysteresis-controlled pump system using SINDy
    ( 2020)
    Thiele, G.
    ;
    Fey, A.
    ;
    Sommer, D.
    ;
    Krüger, J.
    Hysteresis-controlled devices are widely used in industrial applications. For example, cooling devices usually contain a two-point controller, resulting in a nonlinear hybrid system with two discrete states. Dynamic models of systems are essential for optimizing such industrial supply technology. However, conventional system identification approaches can hardly handle hysteresis-controlled devices. Thus, the new identification method Sparse Identification of Nonlinear Dynamics (SINDy) is extended to consider hybrid systems. SINDy composes models from basis functions out of a customized library in a data-driven manner. For modeling systems that behave dependent on their own past as in the case of natural hysteresis, Ferenc Preisach introduced the relay hysteron as an elementary mathematical description. In this new method (SINDyHybrid), tailored basis functions in form of relay hysterons are added to the library which is used by SINDy. Experiments with a hysteresis controlled water basin show that this approach correctly identifies state transitions of hybrid systems and also succeeds in modeling the dynamics of the discrete system states. A novel proximity hysteron achieves the robustness of this method. The impacts of the sampling rate and the signal noise ratio of the measurement data are examined accordingly.
  • Publication
    Automated Optical Inspection Using Anomaly Detection and Unsupervised Defect Clustering
    ( 2020)
    Lehr, J.
    ;
    Sargsyan, A.
    ;
    Pape, M.
    ;
    Philipps, J.
    ;
    Krüger, J.
    Neural networks have proven to be extraordinarily successful in many computer vision applications. But the approaches used to train neural networks require large datasets of annotated images, which requires a solid amount of human time to prepare those datasets. To facilitate the adoption of machine learning based technologies in industrial computer vision applications, this paper presents a two-step unsupervised learning approach for anomaly detection with further defect clusterization. In the first stage, the defects are not explicitly learned, but are interpreted as an anomaly or novelty based on the dataset of defect-free samples. In a second stage, the anomalies detected in the first stage are clustered in unsupervised manner and classified into meaningful categories by experts with process knowledge (e.g. critical or non-critical defect). This paper presents a first small dataset containing one industrial object with a complex shape. The object is made of aluminiu m and is shown both free of defects and defective. Based on this, recommendations are given for an acquisition setup for a large, extensive dataset. Most of the existing papers are studying the approaches for uniform surface (texture) inspection. The specifics of this research is to identify defects on rigid bodies, which exhibit highly non uniform texture in the image. State of the art methods were evaluated and improved to increase the classification accuracy. With a fine-tuned ResNet-18 it was possible to achieve 100% accuracy for defective and defect-free images.
  • Publication
    Process data based Anomaly detection in distributed energy generation using Neural Networks
    ( 2020)
    Klein, M.
    ;
    Thiele, G.
    ;
    Fono, A.
    ;
    Khorsandi, N.
    ;
    Schade, D.
    ;
    Krüger, J.
    The increasing share of renewable energies in the total energy supply includes a growing number of small, decentralized energy generation which also provides control energy. These decentralized stations are usually combined to a virtual power plant which takes over the monitoring and control of the individual participants via an Internet connection. This high degree of automation and the large number of frequently changing subscribers creates new challenges in terms of detecting anomalies. Quickly adaptable, variable and reliable methods of anomaly detection are required. This paper compares two approaches using Neural Networks (NN) with respect to their ability to detect anomalous behavior in real process data of a combined heat and power plant. In order to include process dynamics, one approach includes specifically engineered features, while the other approach uses Long-Short-Term-Memory (LSTM). Both approaches are able to detect rudimentary anomalies. For more demanding anomalies, the respective strengths and weaknesses of the two approaches become apparent.
  • Publication
    Automated continuous learn and improvement process of energy efficiency in manufacturing
    ( 2020)
    Can, A.
    ;
    Fisch, J.
    ;
    Stephan, P.
    ;
    Thiele, G.
    ;
    Krüger, J.
    Optimizing the energy efficiency of machine tools automatically is promising. There are several metrics to be considered when it comes to automated optimization approaches in serial production which are especially quality, technical availability, and cycle time. These are not supposed to be impaired whereas they are indicated as a central obstacle. The measurements and the machine data show the actions happening in the machine which also leads to the data-driven traceability of machine states. This article presents a method to formulate the necessary expert knowledge to optimize the energy efficiency of a machine tool and is basically done by a decision tree which leads to a set of rules which will be explained in this article. This set of rules coordinate an optimization algorithm, which technically manipulates selected variables under the given rules. The development and is a result of a research which was done at the serial production of camshafts at the MB plant in Berlin.
  • Publication
    Robust system identification for hysteresis-controlled devices using SINDy
    ( 2020)
    Schreck, G.
    ;
    Thiele, G.
    ;
    Fey, A.
    ;
    Krüger, J.
    For advanced control of technical systems reliable system identification methods are essential. The data-driven framework Sparse Identification of Nonlinear Dynamics (SINDy) by Kutz and Brunton is extended in order to tackle hysteresis-controlled systems. In order to gain robustness, a so called proximity hysteron is introduced. This paper presents this extension and documents experiments with simulations of an academic example and an industrial chiller system. A proof of concept is followed by experiments which show that strong nonlinearities as well as inadequate sampling rates can critically impair the algorithm.
  • Publication
    Energy optimal set-points for coupled systems using their topology
    ( 2020)
    Thiele, G.
    ;
    Claus, R.
    ;
    Johanni, T.
    ;
    Krüger, J.
    Energy efficiency is an emerging topic for companies in the industrial sector. The optimization of existing machines by advanced control is increasingly approached. For interconnected systems, we present a general procedure to include topology knowledge in an automated set-point optimization routine. This paper demonstrates an exemplary algorithm, applied to a parallel connection of two chillers for test purposes.
  • Publication
    Towards Learning 3d Object Detection and 6d Pose Estimation from Synthetic Data
    ( 2019)
    Rudorfer, M.
    ;
    Neumann, L.
    ;
    Krüger, J.
    Deep Learning-based approaches for 3d object detection and 6d pose estimation typically require large amounts of labeled training data. Labeling image data is expensive and particularly the 6d pose information is difficult to obtain, as it requires a complex setup during image acquisition. Training with synthetic data is therefore very attractive. Large amounts of synthetic, labeled data can be generated, but it is not yet fully understood how certain aspects of data generation affect the detection and pose estimation performance. Our work therefore focuses on creating synthetic training data and investigating the effects on detection performance. We present two methods for data generation: rendering object views and pasting them on random background images, and simulating realistic scenes. The former is computationally simpler and achieved better results, but the detection performance is still very sensitive to small changes, e.g. the type of background images.