Now showing 1 - 10 of 29
  • Publication
    Holistic Approach for Digitalized Quality Assurance in Battery Cell Production
    In this paper, we introduce a holistic approach to consider quality assurance (QA) for battery cell production (BCP). The framework, the explanation of the individual components as well as their interfaces and dependencies, and a detailed description are presented. Firstly, the level of necessary data (e. g. provided by online and out-of-line measurement systems) for the inspection of quality is presented. The aggregation of the recorded data as well as their tracing are ensured by the realization of a traceability system. Subsequently, by defining a suitable intelligent quality gate system, QA mechanisms are implemented and an active influence on production - e. g. by adaptive process control or identifying and reducing negative influence of cause-effect relationships - is aimed at. Finally, optimization of BCP in terms of product quality and its sustainability will be enabled. The evaluation of the demonstrated approach in practice is outlined based on an exemplary process of BCP.
  • Publication
    Wie Machine Learning auf dem Shopfloor die Produktionsqualität steigert. Intelligente Qualitätsplattform
    Mit der intelligenten Qualitätsplattform (IQP) wurde am Fraunhofer-Institut für Produktionstechnologie IPT eine Management-Plattform zur Nutzung, Überwachung und fortlaufenden Optimierung verschiedener ML-Anwendungen entwickelt. Dazu zählen prädiktive Wartung von Maschinen, Vorhersage der Produktqualität oder das Erkennen von Maschinenauffälligkeiten. Die IQP dient dazu, verschiedene ML-Anwendungen aus unterschiedlichen Produktionsbereichen standardisiert zu integrieren und parallel zu betreiben.
  • Publication
    Elaborating the potential of Artificial Intelligence in automated CAR-T cell manufacturing
    ( 2023-09-21)
    Bäckel, Niklas
    ;
    ;
    Kis, Tamás
    ;
    Nettleton, David F.
    ;
    Egan, Joseph R.
    ;
    Jacobs, John J.L.
    ;
    ;
    This paper discusses the challenges of producing CAR-T cells for cancer treatment and the potential for Artificial Intelligence (AI) for its improvement. CAR-T cell therapy was approved in 2018 as the first Advanced Therapy Medicinal Product (ATMP) for treating acute leukemia and lymphoma. ATMPs are cell- and gene-based therapies that show great promise for treating various cancers and hereditary diseases. While some new ATMPs have been approved, ongoing clinical trials are expected to lead to the approval of many more. However, the production of CAR-T cells presents a significant challenge due to the high costs associated with the manufacturing process, making the therapy very expensive (approx. $400,000). Furthermore, autologous CAR-T therapy is limited to a make-to-order approach, which makes scaling economical production difficult. First attempts are being made to automate this multi-step manufacturing process, which will not only directly reduce the high manufacturing costs but will also enable comprehensive data collection. AI technologies have the ability to analyze this data and convert it into knowledge and insights. In order to exploit these opportunities, this paper analyses the data potential in the automated CAR-T production process and creates a mapping to the capabilities of AI applications. The paper explores the possible use of AI in analyzing the data generated during the automated process and its capabilities to further improve the efficiency and cost-effectiveness of CAR-T cell production.
  • Publication
    Machine Learning for Predictive Quality in Optics Production
    Currently, digitization potentials are not yet fully exploited in optics production. Data is collected along the process chain of glass and plastics molding, but the collected data is often not connected and therefore not suitable for analysis. Furthermore, high manual effort is required to measure the produced lenses or to determine their product quality. Therefore, the objective of this paper is to realize predictive quality by predicting the quality of a lens using machine learning with production data. For that purpose, two use cases from a research factory are considered. These include the prediction of the center thickness in the precision glass molding process and the scrap prediction in the injection molding process of polymer lenses. A procedure was developed containing the necessary steps to realize predictive quality applications with focus on optics production. Following the procedure, two machine learning models were trained including the respective data preprocessing for each use case. Firstly, the successful realization of predictive quality within a research environment showcases the potential of machine learning for optics production and promotes the transfer into the industry. Secondly, the resulting models support the process experts to understand underlying interactions between the input and output variables and are the basis for future research regarding the optimization of process parameters.
  • Publication
    Pipeline for ontology-based modeling and automated deployment of digital twins for planning and control of manufacturing systems
    ( 2023-06)
    Göppert, Amon
    ;
    Grahn, Lea
    ;
    Rachner, Jonas
    ;
    ; ;
    The demand for individualized products drives modern manufacturing systems towards greater adaptability and flexibility. This increases the focus on data-driven digital twins enabling swift adaptations. Within the framework of cyber-physical systems, the digital twin is a digital model that is fully connected to the physical and digital assets. A digital model must follow a standardization for interoperable data exchange. Established ontologies and meta-models offer a basis in the definition of a schema, which is the first phase of creating a digital twin. The next phase is the standardized and structured modeling with static use-case specific data. The final phase is the deployment of digital twins into operation with a full connection of the digital model with the remaining cyber-physical system. In this deployment phase communication standards and protocols provide a standardized data exchange. A survey on the state-of-the-art of these three digital twin phases reveals the lack of a consistent workflow from ontology-driven definition to standardized modeling. Therefore, one goal of this paper is the design of an end-to-end digital twin pipeline to lower the threshold of creating and deploying digital twins. As the task of establishing a communication connection is highly repetitive, an automation concept by providing structured protocol data is the second goal. The planning and control of a line-less assembly system with manual stations and a mobile robot as resources and an industrial dog as the product serve as exemplary digital twin applications. Along this use-case the digital twin pipeline is transparently explained.
  • Publication
    Industrial applications of a modular software architecture for line-less assembly systems based on interoperable digital twins
    ( 2023-02-28) ;
    Rachner, Jonas
    ;
    Kaven, Lea
    ;
    ;
    Göppert, Amon
    ;
    In manufacturing, rising demands for customized products have led to increased product variance and shortened product life cycles. In assembly lines, an increased variant diversity impedes the product flow. As a result, the utilization of assembly resources decreases, and production costs grow. An approach to increase the flexibility and adaptability of the assembly system is the implementation of the concept of line-less assembly. In the first step, the assembly line is dissolved. Then, stations are reallocated and linked by automated guided vehicles resulting in a loosely coupled layout, for example, a parallelization and interconnection of multiple lines or a matrix layout. A key requirement for the successful operation and control of a line-less assembly system is the collection and correct interpretation of data. To fully exploit the flexibility and adaptability of the concept of line-less assembly, a software architecture for planning and control must base on an information model allowing the fast integration of all shop floor assets and other data resources. Therefore, a modular data model with standardized interfaces for interoperable data exchange like a digital twin is needed. The aim of this paper is the development and implementation of a software architecture for planning and control of a line-less assembly system. Moreover, the architecture should integrate an interoperable digital twin of the physical system. To satisfy the criteria of interoperability and fast deployment, the digital twins are evolved following the methodology of a digital twin pipeline. Furthermore, a physical demonstrator serves as a testbed for the developed software architecture and digital twins. On the level of production planning and control, relevant industrial applications are identified and implemented in the form of use cases to show the functionality of the line-less assembly system as cyber-physical production system.
  • Publication
    Offering Two-way Privacy for Evolved Purchase Inquiries
    ( 2023)
    Pennekamp, Jan
    ;
    Dahlmanns, Markus
    ;
    Fuhrmann, Fuhrmann
    ;
    Heutmann, Timo
    ;
    ; ; ;
    Schmitt, Robert H.
    ;
    Wehrle, Klaus
    Dynamic and flexible business relationships are expected to become more important in the future to accommodate specialized change requests or small-batch production. Today, buyers and sellers must disclose sensitive information on products upfront before the actual manufacturing. However, without a trust relation, this situation is precarious for the involved companies as they fear for their competitiveness. Related work overlooks this issue so far: existing approaches protect the information of a single party only, hindering dynamic and on-demand business relationships. To account for the corresponding research gap of inadequately privacy-protected information and to deal with companies without an established trust relation, we pursue the direction of innovative privacy-preserving purchase inquiries that seamlessly integrate into today's established supplier management and procurement processes. Utilizing well-established building blocks from private computing, such as private set intersection and homomorphic encryption, we propose two designs with slightly different privacy and performance implications to securely realize purchase inquiries over the Internet. In particular, we allow buyers to consider more potential sellers without sharing sensitive information and relieve sellers of the burden of repeatedly preparing elaborate yet discarded offers. We demonstrate our approaches' scalability using two real-world use cases from the domain of production technology. Overall, we present deployable designs that offer two-way privacy for purchase inquiries and, in turn, fill a gap that currently hinders establishing dynamic and flexible business relationships. In the future, we expect significantly increasing research activity in this overlooked area to address the needs of an evolving production landscape.
  • Publication
    Product-specific Identifiers and Data Aggregation for Enabling Traceability in Battery Cell Production
    In the context of the ongoing energy transition from fossil fuels to renewable energies, suitable energy storage systems play a major role. An important aspect here is sustainable battery cell production itself, but also the generation of transparency about the battery life cycle, e. g. in form of a battery passport. To remain competitive and to ensure sustainable production, high product quality with low scrap rates during production has to be achieved. This is possible with process optimization and digitalization. One underlying requirement lies in a traceability system. To enhance quality of battery cells as well as to minimize scrap, tracing at the finest granularity serves as a key enabler. A broadly applied traceability solution has not yet been fully explored and central challenges lie in the linking of continuous and discrete production steps ' both from a digital and physical perspective. In this paper, we propose a concept for realizing a traceability system in battery cell production based on a product-specific identifier (ID) and the underlying data aggregation. The procedure for tracing an ID through the production steps of a battery cell, the assignment of relevant production data and the prototypical implementation, are presented. For this purpose, concept for battery cell production is introduced, which uses an object-oriented approach to link the different stages of the product ID with the respective production progress. The data generated in the process is aggregated and stored in a database, with the ID enabling unique assignment. Existing dependencies between individual entities of components to be traced and the assignment of corresponding data are shown by means of entity-relationship diagrams. Finally, the application of the concept and the validation are demonstrated using the first processes of electrode production.
  • Publication
    Building Blocks for an Automated Quality Assurance Concept in High Throughput Battery Cell Manufacturing
    The increasing demand for sustainable energy raises the request for battery cells. Industry and research are faced with challenges like complex processes, complex machinery, and many intra-process interactions within the field of battery cell production. Major problems, such as low process stability and quality fluctuations, lead to high scrap rates. Result is a reduced sustainability in the production process. To address these challenges, the main content of this paper is a conceptual design of a virtual Quality Gate (QG) system, for quality assurance and quality prediction. The concept of virtual QG combines physical and digital elements. On the physical side actuators, sensors, and measurement technologies are included to provide the raw data. The digital side of virtual QG includes necessary elements for data acquisition, data processing, data analysis and information provision for the decision-making process in the real world. Focus of the presented approach is illustrating how to select the appropriate location of QG for quality decisions in conjunction with the derivation of necessary decisions, process information and evaluation of measurement technology that is needed.
  • Publication
    ICNAP Study Report 2021
    2021 was an exciting year for ICNAP: despite the COVID-19-related challenges, the community managed to hold its ground with its 24 partners from the indus­try. Now it is taking big steps towards 30 partners. At ICNAP, we are convinced that only a strong coopera­tion between research partners, producing companies and digital enablers can meet the challenges of today. Even more, this is relevant when regarding the inter-disciplinary topic of Networked, Adaptive Production. ICNAP is the ideal platform for networking and collabo­ration within this area. A great response from industry confirms this view. Particularly noteworthy are the five ICNAP studies that were conducted in 2021. When deciding on the topics of these studies, we rely on the competencies and necessities of our industrial partners: all topics are exclu­sively determined by a voting process including all com­munity members. This ensures the industrial relevance of the ICNAP research topics. After a short introduction, this report presents the results of those studies, realized in a collaborative effort within the ICNAP community. With this report we hope to bring ICNAP a little closer to you. More information can be found at www.icnap.de.