Scopus

Permanent URI for this collection

https://publica.fraunhofer.de/handle/publica/420000

Browse

Recent Submissions

Now showing 1 - 5 of 4969
  • Publication
    Transfer of Logistics Optimizations to Material Flow Resource Optimizations using Quantum Computing
    ( 2024)
    Pfister, Raphael
    ;
    Schubert, Gunnar
    ;
    Kröll, Markus
    The complexity of industrial logistics and manufacturing processes increases constantly. As a key enabling technology of the upcoming decades, quantum computing is expected to play a crucial role in solving arising combinatorial optimization problems superior to traditional approaches. This study analyzes the current progress of quantum optimization applications in the logistics sector and aims to transfer an existing vehicle routing use case to a newly conceptualized matrix production use case regarding resource-efficient material flows. The simulation of the originating simple model is executed on a local circuit-based quantum simulator that emulates the behavior of real quantum hardware. Using a QAOA algorithm for problem-solving, optimal results have been achieved for all simulated scenarios. The theoretical material flow model is based on multiple assumptions and was created for testing reasons exclusively. For a realistic practical application, the model must therefore first be adapted and extended to include additional features.
  • Publication
    Method for the Derivation of Flexible Process Modules
    ( 2024)
    Berkhan, Patricia
    ;
    Ranke, Daniel
    ;
    Bauernhansl, Thomas
    Matrix production systems are modular, cycle time-independent, and flow-oriented production systems. They combine flexibility plus productivity and consist of flexibly linked and freely accessible process modules. The derivation and design of these process modules in flexible structures is still very time-consuming due to many degrees of freedom and limiting constraints. This paper presents a method for deriving flexible process modules, taking into account the creation of increased automation potentials, flexible order flows, and specialization in processes. The method consists of seven steps to derive harmonized process modules for multiple products. It is suitable for all manufacturing industries to reduce the planning effort. The defined process modules can be further used for layout planning.
  • Publication
    Investigating the Suitability of Time Series Classification Algorithms for Embedded Systems: A Case Study on Bicycle Pedaling Detection
    ( 2024)
    Oberle, Michael
    ;
    Gärtner, Sascha
    ;
    Maier, Florian
    In this paper, we investigate the performance of state-of-The-Art time series classification algorithms for pedaling detection in bicycles, focusing on embedded device implementation. Using accelerometer data from a crank-mounted sensor, we benchmark various algorithms, including Rocket, MiniRocket, CNN, LSTM, and HIVECOTEV2. The Rocket algorithm achieves the highest accuracy, followed by LSTM and CNN. However, considering the memory and complexity constraints of embedded devices, the CNN model emerges as the most suitable option. Surprisingly, MiniRocket underperforms in classifying backward pedaling as a non-pedaling state, warranting further investigation. Our findings contribute valuable insights into the applicability of time series classification algorithms for pedaling detection, paving the way for advancements in user assistance systems for e-bikes and mountain bikes.
  • Publication
    Artificial Intelligence Applications for Resilience in Manufacturing - A Systematic Literature Review
    ( 2024)
    Maier, Florian
    ;
    Puppala, Sivaphani
    ;
    Oberle, Michael
    This review provides a structured literature analysis of Artificial Intelligence (AI) applications in enhancing manufacturing resilience. The research is guided by three primary questions addressing the use cases, technologies, and benefits of AI across the five resilience phases: Prepare, Prevent, Protect, Respond, and Recover. Findings from 78 papers reveal that AI significantly contributes to predictive maintenance, risk mitigation, and quality control, with machine learning and deep learning being the predominant technologies. The study highlights the pivotal role of AI in advancing manufacturing towards proactive, resilient, and adaptable operations. The insights gleaned offer a roadmap for future research and practical AI integration in manufacturing, underscoring the value of AI in driving industrial innovation and efficiency.
  • Publication
    Targeted Data Generation in the Continuous Production of Anode Slurries for Lithium-Ion Battery Cells
    ( 2024)
    Oberdiek, Sven
    ;
    Jalowy, Leah
    ;
    Gonzalez Vazquez, Flavio
    ;
    Risling, Monika orcid-logo
    ;
    Wahl, Katja
    This research paper explores the transition from batch mixing to continuous mixing processes for the production of slurries used in lithium-ion battery cells. The conventional batch mixing methods, prevalent in European industry, suffer from time-consuming cleaning processes, lengthy mixing times, and the inability to monitor paste conditions in real-Time. The study proposes a solution using continuous mixing with a twin-screw extruder, highlighting advantages such as reduced cleaning time, immediate sample characterization, and minimized production risks. The research aims to develop a test setup and procedure to accelerate the understanding of the continuous mixing process, leveraging minimal resources and time, and facilitating the training of artificial intelligence algorithms. The ultimate goal is to create a digital twin encompassing all influencing factors for predictive and prescriptive analytics. The methodology involves literature reviews, expert surveys, and experimental setups, with an emphasis on inline measuring devices. The paper presents results related to relevant product characteristics, influencing factors, and the selection of suitable measuring equipment. The experimental setup includes a database structure, human-machine interface, and visualization of measurement data. The study concludes with insights into the correlation analysis of influencing factors and product characteristics, emphasizing the need for further experiments and the development of algorithms for predictive quality assessments in continuous mixing processes.