Fraunhofer-Institut für Angewandte Informationstechnik FIT

Filters

7 2
Reset filters

Settings
Now showing 1 - 9 of 9
  • Publication
    Determining the Product-Specific Energy Footprint in Manufacturing
    ( 2023)
    Pelger, Philipp
    ;
    Kaymakci, Can
    ;
    Wenninger, Simon
    ;
    Fabri, Lukas
    ;
    Sauer, Alexander
    In the energy transition context, the manufacturing industry moves into the spotlight, as it is responsible for significant proportions of global greenhouse gas emissions. The consequent pressure to decarbonize leads to suppliers needing to report and continuously reduce the energy consumption incurred in manufacturing supplied goods. To track the energy footprint of their products, manufacturing companies need to integrate energy data with process and planning data, enabling the tracing of the product-specific energy consumption on the shop floor level. Since manufacturing processes are prone to disturbances such as maintenance, the energy footprint of each product differs. Meanwhile, the demand for energy-efficiently produced products is increasing, supporting the development of a sustainability-focused procurement by OEMs. This paper addresses this development and outlines the technical requirements as well as how companies can identify product-specific energy consumption. Furthermore, a case study is conducted detailing how to determine the product-specific energy footprint.
  • Publication
    Deriving Digital Energy Platform Archetypes for Manufacturing - A Data-Driven Clustering Approach
    ( 2023)
    Duda, Sebastian
    ;
    Fabri, Lukas
    ;
    Kaymakci, Can
    ;
    Wenninger, Simon
    ;
    Sauer, Alexander
    External factors such as climate change and the current energy crisis due to global conflicts are leading to the increasing relevance of energy consumption and energy procurement in the manufacturing industry. In addition to the growing call for sustainability, companies are increasingly struggling with rising energy costs and the power grid’s reliability, which endangers the competitiveness of companies and regions affected by high energy prices. Appropriate measures for energy-efficient and, not least, energy-flexible production are necessary. In addition to innovations and optimizations of plants and processes, digital energy platforms for the visualization, analysis, optimization, and control of energy flows are becoming essential. Over time, several digital energy platforms emerged on the market. The number and the different functionalities of the platforms make it challenging for classic manufacturing companies to keep track of and select the right digital energy platform. The characteristics and functionalities of digital energy platforms have already been identified and structured in literature. However, classifying existing platforms into archetypes makes it easier for companies to select the platforms providing the missing functionality. To tackle this issue, we conducted an explorative and data-driven cluster analysis based on 47 existing digital energy platforms to identify digital energy platform archetypes and derive implications for research and practice. The results show four different archetypes that primarily differ in terms of energy market integration functionalities: Research-Driven Energy Platforms, Energy Flexibility Platforms, SaaS-Aggregators / Virtual Power Plants, and (Manufacturing) IoT-Platforms. Decision makers in manufacturing companies will benefit from the archetypes in future analyses as decision support in procurement processes and modifications of digital energy platforms.
  • Publication
    Structuring Federated Learning Applications - A Literature Analysis and Taxonomy
    ( 2023)
    Karnebogen, Philip
    ;
    Kaymakci, Can
    ;
    Willburger, Lukas
    ;
    Häckel, Björn
    ;
    Sauer, Alexander
    Ensuring data privacy is an essential objective competing with the ever-rising capabilities of machine learning approaches fueled by vast amounts of centralized data. Federated learning addresses this conflict by moving the model to the data while ensuring that the data itself does not leave a client's device. However, maintaining privacy impels new challenges concerning algorithm performance or fairness of the algorithm's results that remain uncovered from a sociotechnical perspective. We tackle this research gap by conducting a structured literature review and analyzing 152 articles to develop a taxonomy of federated learning applications consisting of nine dimensions and 25 characteristics. Our taxonomy illustrates how different attributes of federated learning affect trade-offs between an algorithm's privacy, performance, and fairness. Despite an increasing interest in the technical implementation of federated learning, our work is one of the first to emphasize an information systems perspective on this emerging and promising topic.
  • Publication
    Structuring the Digital Energy Platform Jungle: Development of a Multi-Layer Taxonomy and Implications for Practice
    ( 2022)
    Duda, Sebastian
    ;
    Bank, Lukas
    ;
    Kaymakci, Can
    ;
    Köberlein, Jana
    ;
    Wenninger, Simon
    ;
    Haubner, Tobias
    ;
    Sauer, Alexander
    ;
    Schilp, Johannes
    Rising and volatile energy prices are forcing production companies to optimize their consumption patterns and reduce carbon emissions to remain competitive. Demand-side management (DSM) or energy flexibility (EF) is a promising option for the active management of electricity demand. With DSM, energy procurement costs can be effectively reduced, for example, by reducing peak loads and taking advantage of volatile energy prices. In addition, renewable energies can be better integrated to reduce carbon emissions while stabilizing the power grid. Although the benefits of DSM for production companies are well known, implementation is not yet widespread. A key barrier is the high requirements of IT systems and the associated effort and complexity involved in setting them up. Companies often lack appropriate IT systems or have historically grown systems that do not allow continuous communication from the machine to the energy market. A variety of different platforms promise solutions to address these challenges. However, when selecting platforms, it is often unclear which aspects and functionalities of a platform are relevant for a company s specific application. To address this gap, we developed a multi-layer taxonomy of digital platforms for energy-related applications in the industry that includes a general, as well as a more specific data-centric and transaction-centric perspective. We develop, revise, and evaluate our taxonomy using insights from literature and analysis of 46 commercially available platforms or platforms developed through research projects. Based on our taxonomy, we derive implications for research and practice. Our results contribute to the descriptive knowledge of digital platforms in energy-related applications. Our taxonomy enables researchers and practitioners to classify such platforms and make informed decisions about their deployment.
  • Publication
    How Sustainable is Machine Learning in Energy Applications? - The Sustainable Machine Learning Balance Sheet
    ( 2022)
    Wenninger, Simon
    ;
    Kaymakci, Can
    ;
    Wiethe, Christian
    ;
    Römmelt, Jörg
    ;
    Baur, Lukas
    ;
    Häckel, Björn
    ;
    Sauer, Alexander
    Information Systems play a central role in the energy sector for achieving climate targets. With increasing digitization and data availability in the energy sector, data-driven machine learning (ML) approaches emerged, showing high potential. So far, research has focused on optimizing ML approaches’ prediction performance. However, this is a one-sided perspective. ML approaches require large computation times and capacities leading to high energy consumption. With the goal of sustainable energy systems, research on ML approaches should be extended to include the application’s energy consumption. ML solutions must be designed in such a way that the resulting savings in energy (and emissions) are greater than the energy consumption caused using the ML solution. To address this need, we develop the Sustainable Machine Learning Balance Sheet as a framework allowing to holistically evaluate and develop sustainable ML solutions which we validated in a case study and through expert interviews.
  • Publication
    A Holistic Framework for AI Systems in Industrial Applications
    ( 2021)
    Kaymakci, Can
    ;
    Wenninger, Simon
    ;
    Sauer, Alexander
    Although several promising use cases for artificial intelligence (AI) for manufacturing companies have been identified, these are not yet widely used. Existing literature covers a variety of frameworks, methods and processes related to AI systems. However, the application of AI systems in manufacturing companies lacks a uniform understanding of components and functionalities as well as a structured process that supports developers and project managers in planning, implementing, and optimizing AI systems. To close this gap, we develop a generic conceptual model of an AI system for the application in manufacturing systems and a four-phase model to guide developers and project managers through the realization of AI systems.
  • Publication
    Integrating Energy Flexibility in Production Planning and Control - An Energy Flexibility Data Model-Based Approach
    ( 2021)
    Bank, Lukas
    ;
    Wenninger, Simon
    ;
    Köberlein, Jana
    ;
    Lindner, Martin
    ;
    Kaymakci, Can
    ;
    Weigold, Matthias
    ;
    Sauer, Alexander
    ;
    Schilp, Johannes
    Production companies face the challenge of reducing energy costs and carbon emissions while achieving the logistical objectives at the same time. Active management of electricity demand, also known as Demand Side Management (DSM) or Energy Flexibility (EF), has been recognized as an effective approach to minimize energy procurement costs for example by reducing peak loads. Additionally, it helps to integrate (self-generated, volatile) renewable energies to reduce carbon emissions and has the ability to stabilize the power grid, if the incentives are set appropriately. Although production companies possess great potential for EF, implementation is not yet common. Approaches to practical implementation for integrating energy flexibility into production planning and control (PPC) to dynamically adapt the consumption to the electricity supply are scarce to non-existent due to the high complexity of such approaches. Therefore, this paper presents an approach to integrate EF into PPC. Based on the energy-oriented PPC, the approach identifies and models EF of processes in a generic energy flexibility data model (EFDM) which is subsequently integrated in the energy-oriented production plan and further optimised on the market side. An application-oriented use case in the chemical industry is presented to evaluate the approach. The implementation of the approach shows that EF can have a variety of characteristics in production systems and a clear, structured, and applicable method can help companies to an automated EF. Finally, based on the results of the use case, it is recommended to introduce EF in production companies stepwise by extending existing planning and scheduling systems with the presented approach to achieve a realization of flexibility measures and a reduction of energy costs.
  • Publication
    Flexible, application-depended HTS automation concept in genomics and proteomics
    ( 2011)
    Cuntz, Timo
    ;
    Brändlin, Ilona
    ;
    Huchler, Roland
    ;
    Fritsche, Michael
    ;
    Brandenburg, Albrecht
    ;
    Zühlke, Dietlind
    A flexible new concept of a HTS-automation center allows any application in the topics of genomics and proteomics. The fundament of this new concept are our fully automated cell culture systems, in which up to five hundred stem cell pools can be cultivated, sorted in MTPs or flasks per month. Based on this automated cell-culture handling the new HTS technique allows a modular set-up of different process steps. Starting with handling of human/animal cells in an incubator, the system is able to count and split the cells in MTPs or flasks. Liquid handling options allow fully automated and precise dosing of biopharmaceutical compounds to the cells in the MTPs. Process modules are including life-cell-imaging, where fluorescent marked cells are detected. This is interesting in the focus of protein localization or co-localization studies. In order to setup stable cell lines, a specific picking robot separates the positive and negative fluorescent cells in different containers. Afterwards they are processed in an integrated incubator. Possible applications in the field of proteomics are the analysis of recombinant expressed proteins after compounds incubation. If the protein won't be secreted, the cells are fully automated lysed and the supernatant analyzed in a specific screening centre or cellular assay like microarrays. As well functional protein-studies are possible e.g. RNAi. In the field of genomics the DNA/RNA can be separated and analyzed under the use of different assays. We realized this flexible application-depended HTS automation center in a version combining cell-culture handling, life-cell-imaging, compound handling, picking cells and separation between cells and supernatant. Operated via an easy to use graphical-user-interface (GUI) and controlled by efficient scheduling module, it's possible to handle the fully automated system in a flexible way to get validated results in HTS. The talk will cover the technological and application aspects of a fully automated system for pharmaceutical and biotechnological researches and will point out the innovative solutions.
  • Publication
    Live cell monitoring - development of an automated cell cultivation and monitoring system
    ( 2008)
    Malthan, Dirk
    ;
    Huchler, Roland
    ;
    Brandenburg, Albrecht
    ;
    Thielecke, Hagen
    ;
    Hildebrandt, Cornelia
    ;
    Zühlke, Dietlind
    The reproducibility and comparability of cell cultures presently suffers from different and user-dependant handling by the technical personnel in the cell culture laboratory. Although there are first automated systems available, those are based upon rigid industrial processes, do not provide optical monitoring and cannot be run under optimal climate conditions. Within a joint project between four Fraunhofer Institutes, a platform technology for reproducible and standardized cell monitoring and cultivation has been established. After the input of a source cell culture flask, the complete cell culture procedure is executed automatically, including optical monitoring, addition of factors, exchange of media, passaging and reformatting. This is only feasible by means of an optical image acquisition of cell cultures and a user-friendly image analysis software that determines cell culture condition in order to control cell culture process accordingly. The cell culture process can thereby also be documented and archived. Finally, the expanded cells (contained in flasks or micro well plates) can be taken out and applied for cell-based screening, toxicity tests or other purposes. The whole cultivation process takes place under cultivation conditions (37 °C, CO2, 98 % humidity) to leave the cell culture in an optimal environment and to avoid stress because of climate changes. The talk will cover both technological and application aspects of the developed system regarding image acquisition, trainable software for user-friendly image analysis, the hygienic concept and performed sample applications.