Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB

Filters

Reset filters

Settings
Now showing 1 - 10 of 25
  • Publication
    Intelligent Information Management in Aquaponics to Increase Mutual Benefits
    ( 2021)
    Karimanzira, Divas
    ;
    Na, Chai
    ;
    Hong, Mu
    ;
    Wei, Yaoguang
    Aquaponics are feedback and two player systems, in which fish and crops mutually benefit from one another and, therefore require close monitoring, management and control. Vast amount of data and information flow from the aquaponics plant itself with its huge amount of smart sensors for water quality, fish and plant growth, system state etc. and from the stakeholder, e.g., farmers, retailers and end consumers. The intelligent management of aquaponics is only possible if this data and information are managed and used in an intelligent way. Therefore, the main focus of this paper is to introduce an intelligent information management (IIM) for aquaponics. It will be shown how the information can be used to create services such as predictive analytics, system optimization and anomaly detection to improve the aquaponics system. The results show that the system enabled full traceability and transparency in the aquaponics processes (customers can follow what is going on at the farm), reduced water and energy use and increased revenue through early fault detection. In this, paper the information management approach will be introduced and the key benefits of the digitized aquaponics system will be given.
  • Publication
    Simulation of Coupled Components within Power-Hardware-in-the-Loop (PHiL) Test Bench
    ( 2020)
    Ruhe, Stephan
    ;
    Fechner, Max
    ;
    Nicolai, Steffen
    ;
    Bretschneider, Peter
    Power Hardware-in-the-Loop (PHiL) becomes more and more an important part at the investigation of dynamics and stability issues of the electrical grids. As derived from Hardware-in-the-Loop (HiL) approach, one of the central PHiL requirements is to feedback measurement signals into the simulation. In PHIL applications, the operational behavior of a connected device is integrated within real-time simulations. With the integration of the Hardware under Test (HuT) into a PHiL test bench, stability issues may arise. Therefore, this paper focuses on the stability investigation and the description of typical PHiL setup and condititions. The frequency domain modelling reveals phenomenon of instability as well as concepts of Interface Algorithm (IA) and Compensation Methods (CM). To investigate the behavior of different devices as HuT, also the HuT is modelled and simulated in the real time environment. In the next step, the analog loopback integrates HuT models into PHiL simulation by using HYPERSIM from OPAL-RT as simulation software (time domain). Analog loopback introduces time delay into the PHiL simulation that would also occur in real PHiL applications with connected devices to build a more realistic environment. The simulation with analog loopback consists of implemented IAs which feedback operational behavior of HuT models into PHiL test bench. In selected simulation approaches, the mentioned technique loops back currents of various loads and inverters. Therefore it is possible to evaluate the feedback of devices with different described methods and their impact on stability and signal fidelity.
  • Publication
    A novel framework for synchrophasor based online recognition and efficient post-mortem analysis of disturbances in power systems
    ( 2020)
    Kummerow, André
    ;
    Monsalve, Cristian
    ;
    Brosinsky, Christoph
    ;
    Nicolai, Steffen
    ;
    Westermann, Dirk
    Synchrophasor based applications become more and more popular in today's control centers to monitor and control transient system events. This can ensure secure system operation when dealing with bidirectional power flows, diminishing reserves and an increased number of active grid components. Today's synchrophasor applications provide a lot of additional information about the dynamic system behavior but without significant improvement of the system operation due to the lack of interpretable and condensed results as well as missing integration into existing decision-making processes. This study presents a holistic framework for novel machine learning based applications analyzing both historical as well as online synchrophasor data streams. Different methods from dimension reduction, anomaly detection as well as time series classification are used to automatically detect disturbances combined with a web-based online visualization tool. This enables automated decision-making processes in control centers to mitigate critical system states and to ensure secure system operations (e.g., by activating curate actions). Measurement and simulation-based results are presented to evaluate the proposed synchrophasor application modules for different use cases at the transmission and distribution level.
  • Publication
    Angewandtes Quantencomputing
    ( 2020)
    Lässig, Jörg
    Quantencomputing ist als Konzept mittlerweile zwar mehrere Jahrzehnte alt und hat von der Idee bis zu den heutigen Noisy Intermediate-Scale Quantum Maschinen verschiedene Phasen stetiger Entwicklung durchlaufen, jedoch insbesondere in den letzten Jahren deutlich an Dynamik gewonnen. Im aktuellen Stadium stehen Quantenrechner zur Verfügung, die zwar noch immer stark limitiert sind, jedoch die Ausführung maßgeschneiderter Algorithmen unterstützen, die bestehende Schwächen dieser Maschinen mit ihrem speziellen Design zu umgehen versuchen. Diese Algorithmen adressieren dabei mit Maschinellem Lernen, kombinatorischer Optimierung und Simulationsanwendungen sowie weiteren potenziellen Anwendungsfeldern Problemstellungen, die praktisch vielfältig relevant und deshalb von breitem, allgemeinen Interesse sind. Das prinzipielle Potenzial des Quantencomputers, in bestimmten Anwendungsfeldern deutlich leistungsfähiger zu sein als klassische Rechner, ruft viel Aufmerksamkeit hervor. Außerdem stellt bereits eine ganze Reihe von prinzipiell für jedermann zugänglichen Softwareframeworks Implementierungen aktueller Quantenalgorithmen zum Test und zur Evaluierung bereit. Der Artikel stellt die bisherige Entwicklung, aktuelle Verfahren sowie weitere Perspektiven der Technologie in Grundzügen dar und informiert über mögliche Anwendungsgebiete aber auch bekannte Grenzen des Quantencomputing-Paradigmas.
  • Publication
    Cyber-physical data stream assessment incorporating Digital Twins in future power systems
    ( 2020)
    Kummerow, André
    ;
    Monsalve, Christian
    ;
    Rösch, Dennis
    ;
    Schäfer, Kevin
    ;
    Nicolai, Steffen
    Reliable and secure grid operations become more and more challenging in context of increasing IT/OT convergence and decreasing dynamic margins in today's power systems. To ensure the correct operation of monitoring and control functions in control centres, an intelligent assessment of the different information sources is necessary to provide a robust data source in case of critical physical events as well as cyber-attacks. Within this paper, a holistic data stream assessment methodology is proposed using an expert knowledge based cyber-physical situational awareness for different steady and transient system states. This approach goes beyond existing techniques by combining high-resolution PMU data with SCADA information as well as Digital Twin and AI based anomaly detection functionalities.
  • Publication
    Hardware/Software architecture to investigate resilience in energy management for smart grids*
    ( 2020)
    Lenk, Steve
    ;
    Arnoldt, Alexander
    ;
    Rösch, Dennis
    ;
    Bretschneider, Peter
    In the age of digitization, for critical infrastructures arises new challenges due to the amount of data to handle, the increasing automation level and threats to cybersecurity. Resilience of critical systems, i. e., to be prepared for and to prevent threats, to protect systems against them, to respond to threats and to recover from them, rises in priority. Here, we present a hardware-software architecture design for energy management systems as part of critical energy infrastructures, which is scalable, distributable, parallelizable and adaptable. Therefore, it is capable to handle the increasing amount of data but it also allows an in-depth monitoring. This enables the investigation of the impact of diverse threat scenarios like technical errors, human failure and cyber attacks. Thus, it is the basis for developing resilient algorithms, improved communications channels and monitoring mechanisms for energy management systems.
  • Publication
    Object Detection in Sonar Images
    ( 2020)
    Karimanzira, Divas
    ;
    Renkewitz, Helge
    ;
    Shea, David
    ;
    Albiez, Jan
    The scope of the project described in this paper is the development of a generalized underwater object detection solution based on Automated Machine Learning (AutoML) principles. Multiple scales, dual priorities, speed, limited data, and class imbalance make object detection a very challenging task. In underwater object detection, further complications come in to play due to acoustic image problems such as non-homogeneous resolution, non-uniform intensity, speckle noise, acoustic shadowing, acoustic reverberation, and multipath problems. Therefore, we focus on finding solutions to the problems along the underwater object detection pipeline. A pipeline for realizing a robust generic object detector will be described and demonstrated on a case study of detection of an underwater docking station in sonar images. The system shows an overall detection and classification performance average precision (AP) score of 0.98392 for a test set of 5000 underwater sonar frames.
  • Publication
    Digital-Twin based Services for advanced Monitoring and Control of future power systems
    ( 2020)
    Kummerow, André
    ;
    Nicolai, Steffen
    ;
    Brosinsky, Christoph
    ;
    Westermann, Dirk
    ;
    Naumann, Andre
    ;
    Richter, Marc
    As real-time applications in information technology (IT) and operational technology (OT) advance, new innovative concepts become possible. IT/OT convergence opens new pathways to design and operate intelligent cyber-physical systems, such as the Digital Twin (DT) concept, which has been discovered as key technology by several industries. This paper describes how centralized and decentralized DTs can help to monitor and control future power systems with special consideration of their interaction in case of corrupted communication from cyber-attacks. While the virtual representation of substations is regarded from the edge computing perspective the control room of the interconnected power system represents the centralized perspective. The concepts allows to have a system wide perspective, while also keeping detailed information at hand. The future system operator in the control room will benefit from services provided by DTs analytical and control features, rising resilience to cyber-physical anomalies and enhance situational awareness.
  • Publication
    Analysis of a coordinated infrastructure development for supplying battery and fuel cell electric vehicles
    ( 2020)
    Monsalve, Cristian
    ;
    Ruhe, Stephan
    ;
    Kharboutli, Samir
    ;
    Nicolai, Steffen
    The integration of electric vehicles has been proposed as one viable alternative for reducing CO2 emissions in the mobility sector. However, the effects of the integration of electric vehicles in distribution grids must be assessed to support the decision-making for planning future electrical grids. In this sense, this paper evaluates the technical effects of the integration of electric charging and H2-filling infrastructure in distribution grids for at different development scenarios of battery electric vehicles (BEV) and fuel cell electric vehicles (FCEV). Considering that zero-emission electric vehicles (ZEEV) will play a relevant role as suitable technology for reduction CO2 emission, it is required to determine the required measures that need to be performed in order to ensure the security and reliability of the electrical system. Thereby, the main contribution of this paper is a technical evaluation of the German distribution grids under different market developme nt scenarios for ZEEV until 2050, which allows determining the impact and reinforcements measures required for a sustainable integration of H2-filling and charging infrastructure in Germany. On the other hand, it provides some recommended actions to be considered in the development plans for network operators and political frameworks.
  • Publication
    Application of various balancing methods to DCNN regarding acoustic data
    ( 2020)
    Schneider, Dominic
    ;
    Schneider, Manuel
    ;
    Schweigel, Maria
    ;
    Wenzel, Andreas
    This paper describes the application and effects of different balancing methods on the learning behaviour and quality of a DCNN using acoustic data. The aim is to show to what extent these methods have positive as well as negative effects on the use case of the audio data. The evaluation is based on synthetic audio data with multiclass characteristics, because an overlay of effects should be avoided. This serves as preliminary work in order to apply the methodology to the measurement data for the classification of knife sharpness in forage harvesters in later investigations. According to applied balancing methods, the data are represented to the DCNN. The performance and quality shall be measured by formal qualification criteria. It turned out that SMOTE gives the best and most robust results. It shows a higher convergence compared to the other methods. Furthermore the worst results are produced with untreated raw data.