Fraunhofer-Institut für Produktionsanlagen und Konstruktionstechnik IPK

Filters

27
Reset filters

Settings
Now showing 1 - 10 of 27
  • Publication
    With synthetic data towards part recognition generalized beyond the training instances
    ( 2024)
    Koch, Paul
    ;
    Schlüter, Marian
    ;
    Krüger, Jörg
    In this work we investigate the effect of using synthetic data, generated in a simulation, in order to pre-train an AI-based image classification for industrial components. After pre-training we use real camera-captured training images to fine-tune the AI with the aim to close the Sim2Real domain gap. We compare our approach to purely using real training images of a single candidate object instance. In an exemplary case study for screw recognition, we found that a given AI classification algorithm dropped its recognition rate from 99.8% to 88.5% when testing the algorithm with known and unknown screw instances of the learned object classes, respectively. Employing our pre-training method on the basis of synthetic data, the drop in recognition rate is decreased from 99% to 96.95%. Thus, our proposed method has only a relative drop of 2.05% when shifting towards a generalized domain (including unknown part instances), while a compared approach on the basis of real camera-captured data showed a drop of 11.3%.
  • Publication
    Implementing human-robot collaboration in highly dynamic environments: Assessment, planning and development
    ( 2024)
    Bastidas Cruz, Arturo
    ;
    Jaya, T.
    ;
    Thiele, Gregor
    ;
    Krüger, Jörg
    Human-robot collaboration (HRC) applications have been slowly making their path in the industry. Although the required hardware and the methods for the planning and development of collaborative robotic applications are mostly already developed, some industrial branches still struggle to implement HRC. This is the case in motorcycle production, where, unlike car production, the assembly line has been optimized for manual work. Based on the use case described above, this paper identifies new requirements of HRC for automated screwing assembly operations in flexible production environments. In order to compensate deviations in the position of the tool relative to the workpiece, a screwing strategy based on force control is proposed. Parameter sensitivity is considered and supported experimentally with a screwing task performed by a cobot, where a method for contact detection between the nutrunner and the screw head is analyzed. This paper brings a guideline for experts from the manufacturing system engineering to implement HRC in highly dynamic assembly environments.
  • Publication
    Concept for a modular system model for energy-efficiency monitoring of factory supply systems
    ( 2024)
    Sigg, Stefan
    ;
    Thiele, Gregor
    ;
    Trapp, Marvin
    ;
    Krüger, Jörg
    Companies in the manufacturing industry are facing the challenges of both reducing energy costs as well as driving decarbonization. As a result, energy efficiency optimization of factory operations is gaining importance. Due to their high share in the energy consumption of a factory, industrial supply technology is of interest for these optimizations. Particularly cooling systems used in factories often offer considerable potential for energy efficiency improvements, some of which can be realized through optimized control strategies. Optimization based on control technology in particular requires a high level of energy consumption transparency in order to identify potentials and measure efficiency improvements. However, industrial supply systems are often complex and interconnected facilities composed of a combination of various individual assets. Consequently, the energy efficiency monitoring and analysis of such systems typically require a high manual effort. To reduce this effort, we propose the development of a modular system model which decomposes complex, interconnected energy systems to individual, recurring assets. The system model consists of a standardized data exchange format, a standardization of structural and behavioral models in the form of a model library for industrial supply systems at different hierarchy levels, and a standardized interface for using the data model on a target platform such as an energy management software. The data model of the data exchange format maps data points such as the control and media interfaces as well as energy performance indicators of the individual assets in a standardized and consistent way. Similar to the concept of digital twins, the knowledge of manufacturers and operators about the system is to be seamlessly combined and utilized. By connecting the interfaces of the individual asset models, an aggregate structural model of a factory supply system is built. The aggregate structural model enables the calculation of consistent and comparative energy performance indicators at equipment and system level. In this way, the implementation of energy efficiency monitoring and the assessment of energy efficiency potentials and improvements is facilitated. The system model concept is demonstrated using an industrial cooling system comprising individual assets such as a cooling tower, a chiller and pumps.
  • Publication
    Data augmentation for inertial sensor based human action recognition using deep learning
    ( 2024)
    Kuschan, Jan
    ;
    Filaretov, Hristo
    ;
    Krüger, Jörg
    Human Activity Recognition (HAR) approaches are predominantly based on supervised deep learning and benefit from large amounts of labeled data - an expensive resource. Data augmentation enriches labeled datasets by adding synthetic data, which is substantially cheaper, and often results in improved model performance, but is very rarely used for sensor data. This work explores data augmentation for inertial-sensor-based HAR by transforming the data through physically interpretable operations. The main studies were conducted on the Opportunity and the Overhead Car Assembly (OCA) datasets. For these experiments, only 20% of the available training data were used, and the experiments were conducted in an 8-fold cross-validation procedure over different subsets of the training data. The results show that simple geometric augmentations can be beneficial in many cases. Timewarping proved to offer the most reliable single augmentation, improving the average F1 score of Opportunity from 0.570 to 0.597 and of OCA Mixed from 0.884 to 0.906. Combining augmentations improved the accuracy in almost all scenarios but to a degree comparable to timewarping. Applying augmentations on all the available training data improved the F1 score compared to the base case with no augmentations, although this effect is more pronounced for datasets with more similar training and test data: for the OCA Mixed variant, the average F1 score improved from 0.917 to 0.933, while for the OCA Leave-One-Out (LOT) variant, the average F1 score did not significantly change. For Opportunity, which similarly to OCA LOT uses a participant-based training-test split, the F1 score improved from 0.684 to 0.697.
  • Publication
    A Practical Approach to Realize a Closed Loop Energy Demand Optimization of Milling Machine Tools in Series Production
    ( 2023)
    Can, Alperen
    ;
    Schulz, Hendrik
    ;
    El-Rahhal, Ali
    ;
    Thiele, Gregor
    ;
    Krüger, Jörg
    Energy efficiency is becoming increasingly important for industry. Many approaches for energy efficiency improvements lead to the purchase of new hardware, which could neglect the sustainability. Therefore, optimizing the energy demand of existing machine tools (MT) is a promising approach. Nowadays energy demand optimization of MT in series production is mainly done manually by the operators, based on implicit knowledge gained by experience. This involves manual checks to ensure that production targets like product quality or cycle time are met. With data analytics it is possible to check these production targets autonomously, which allows optimizing production systems data driven. This paper presents the approach and evaluation of a closed loop energy demand optimization of auxiliary units for milling MT during series production. The approach includes, inter alia, a concept for machine connectivity using edge devices and a concept for validating production targets
  • Publication
    Signal conditioning of a novel ultrasonic transducer with integrated temperature and amplitude sensors
    ( 2023)
    Karbouj, Bsher
    ;
    Krüger, Jörg
    Vibration amplitude of ultrasonic transducer has an impact on the overall process quality, process speed and ultrasonic transducer lifetime in industrial applications. A new ultrasonic transducer design has been developed with integrated sensor disks that have different electrical and mechanical properties. The combination of sensor has been designed for amplitude measurements and is also able to measure the transducer temperature in the real time. This paper deals with the analog signal processing that combines the different "raw" signals from the sensor disks to extract the information such as amplitude and temperature. For this goal, a chain of different signal filters and adjustment elements was used. Reliable amplitude and temperature measurements during real-time operation were obtained by the applied signal processing. The obtained results were validated with an external temperature sensor and a laser vibrometer.
  • Publication
    Redundancy Concepts for Real-Time Cloud- and Edge-based Control of Autonomous Mobile Robots
    ( 2022)
    Nouruzi-Pur, Jan
    ;
    Lambrecht, Jens
    ;
    Nguyen, The Duy
    ;
    Vick, Axel
    ;
    Krüger, Jörg
    Deploying navigation algorithms on an edge or cloud server according to the Software-as-a-Service paradigm has many advantages for autonomous mobile robots in indus-trial environments, e.g. cooperative planning and less onboard energy consumption. However, outsourcing corresponding real-time critical control functions requires a high level of reliability, which cannot be guaranteed either by modern wireless networks nor by the outsourced computing infrastructure. This work introduces redundancy concepts, which enable real-time capability within these uncertain infrastructures by providing redundant computation nodes, as well as robot-controlled switching between them. Redundancies can vary regarding their physical location, robot behavior during the switchover process and degree of activeness while quality of service concerning the primary controller is sufficient. In the case that fallback redun-dancies are not continuously active, when a disturbance occurs an initial state estimation of the robot pose has to be provided and an activation time has to be anticipated. To gain some insights on expected behavior, redundant computation nodes are deployed locally on the robot and on an outsourced computation node and consequently evaluated empirically. Quantitative and qualitative results in simulation and a real environment show that redun-dancies help to significantly improve the robot-trajectory within an unreliable network. Moreover, resource-saving redundancies, which are not continuously active, can robustly take over control by using an estimated state.
  • Publication
    Contact Information Flow and Design of Compliance
    ( 2022)
    Haninger, Kevin
    ;
    Radke, Marcel
    ;
    Hartisch, Richard
    ;
    Krüger, Jörg
    Identifying changes in contact during contact-rich manipulation can detect task state or errors, enabling improved robustness and autonomy. The ability to detect contact is affected by the mechatronic design of the robot, especially its physical compliance. Established methods can design physical compliance for many aspects of contact performance (e.g. peak contact force, motion/force control bandwidth), but are based on time-invariant dynamic models. A change in contact mode is a discrete change in coupled robot-environment dynamics, not easily considered in existing design methods.Towards designing robots which can robustly detect changes in contact mode online, this paper investigates how mechatronic design can improve contact estimation, with a focus on the impact of the location and degree of compliance. A design metric of information gain is proposed which measures how much position/force measurements reduce uncertainty in the contact mode estimate. This information gain is developed for fully- and partially-observed systems, as partial observability can arise from joint flexibility in the robot or environmental inertia. Hardware experiments with various compliant setups validate that information gain predicts the speed and certainty with which contact is detected in (i) monitoring of contact-rich assembly and (ii) collision detection.
  • Publication
    Inertial Measurement Unit based Human Action Recognition Dataset for Cyclic Overhead Car Assembly and Disassembly
    ( 2022)
    Kuschan, Jan
    ;
    Filaretov, Hristo
    ;
    Krüger, Jörg
    Motion datasets in industrial environments are essential for the research on human-robot interaction and new exoskeleton control. Currently, a lot of Activities of Daily Living (ADL) datasets are available for researchers, but only a few target an industrial context. This paper presents a dataset for a semi-industrial Overhead Car Assembly (OCA) task consisting of synchronized video and 9-Degrees of Freedom (DOF) Inertial Measurement Unit (IMU) data. The dataset was recorded with a soft-robotic exoskeleton equipped with 4 IMUs covering the upper body. It has a minimum sampling rate of 20 Hz, lasts approximately 360 minutes and comprises of 282 cycles of a realistic industrial assembly task. The annotations consist of 6 mid-level actions and an additional Null class. Five different test subjects performed the task without specific instructions on how to assemble the used car shielding. In this paper, we describe the dataset, set guidelines for using the data in supervised learning approaches, and analyze the labeling error caused by the labeler onto the dataset. We also compare different state-of-the-art neural networks to set the first benchmark and achieve a weighted F1 score of 0.717.
  • Publication
    Low-Cost Embedded Vision for Industrial Robots: A Modular End-of-Arm Concept
    ( 2020)
    Kroeger, Ole
    ;
    Wollschläger, Felix
    ;
    Krüger, Jörg
    In this work we present our first prototype of a modular, low-cost end-of-arm concept for industrial robot applications. The goal is a faster, more flexible and cost-effective alternative compared to current industrial solutions. We use an embedded single-board computer and three cameras as a sensor base for the new system. The scope of robot application is supposed to as wide as possible (e.g. object detection, bin picking, assembly tasks and quality control tasks). We discuss some industry and low-cost-hardware solutions, introduce our system and deliver a proof of concept. Furthermore we use the system to accomplish a vision based pick and place task.