1 - 10 of 2745
-
PublicationDetektion von Bindefehlern beim DED-Arc( 2024-08)In dem Beitrag wird aufbauend auf Machine-Learning-Modellen, welche bereits zum Überwachen des Schutzgasschweißen erforscht wurden, ein tiefes neuronales Netz (DNN) zum Monitoring beim DED-Arc von Aluminium vorgestellt. Ziel ist die Detektion von Bindefehlern in den aufgebauten Volumina auf Grundlage von in Echtzeit gemessenen Schweißstromquellensignalen. Es werden Merkmalsvariablen durch Vorverarbeitung extrahiert sowie die Korrelation zwischen den Merkmalsvariablen und den Defekten analysiert. Durch den vorgestellten Algorithmus werden diese automatisiert als Input an ein DNN übergeben. Das entwickelte und trainierte neuronale Netz erkennt anhand signifikanter Merkmale aus den Strom- und Spannungsdaten Bindefehler mit einer Genauigkeit von ca. 90 Prozent.
-
PublicationApplication of AI-based welding process monitoring for quality control in pipe production( 2024-07-29)The paper presents the experimental results into the development of a multi-channel system for monitoring and quality assurance of the multi-wire submerged arc welding (SAW) process for the manufacture of large diameter pipes. Process signals such as welding current, arc voltage and the acoustic signal emitted from the weld zone are recorded and processed to provide information on the stability of the welding process. It was shown by the experiments that the acoustic pattern of the SAW process in a frequency range between 30 Hz and 2.5 kHz contains the most diagnostic information. The on-line quality assessment of the weld seam produced is carried out in combination with methods of artificial intelligence (AI). From the results obtained, it can be concluded that the use of the latest concepts in welding and automation technology, combined with the high potential of AI, can achieve a new level of quality assurance in pipe manufacturing.
-
-
PublicationDigital Twins within the Circular Economy: Literature Review and Concept Presentation( 2024-03-26)Digital twins offer a promising approach to sustainable value creation by providing specific life cycle data and enabling the monitoring and implementation of circular economy strategies throughout the product’s life cycle. By analyzing product, component, and material data, as well as process data, it is possible to create transparency throughout a product’s life cycle, build a data-driven product ecosystem, and establish new business and value creation models, from SMEs to large enterprises. This paper identifies application scenarios, their technological readiness level, and the challenges of digital twins for the circular economy in the manufacturing industry based on a systematic literature review. Gaps such as ensuring a continuous flow of information and taking into account the different levels of digitalization of companies are identified. As a main result, a holistic concept for the scoping of a digital twin for the circular economy is presented. One specific use case for end-of-life decision-making is elaborated upon. It is shown that the circular economy can be supported by digital twin data, especially for the optimal decision on end-of-life vehicles.
-
PublicationQualitätssicherung beim Laser-Pulver-Auftragschweißen( 2024-02-01)In der modernen Fertigungstechnik spielt der Einsatz von korrosionsbeständigem Stahl eine große Rolle. Die kohlenstoffarme Edelstahllegierung 1.4404 (AISI 316L) ist ein häufig eingesetzter Werkstoff in der additiven Fertigung. Hier kann das Laser-Pulver-Auftragschweißen (LPA), engl. Directed Energy Deposition DED-LB, das weit verbreitete Laser Powder Bed Fusion (L-PBF) aufgrund höherer Auftragsraten und seiner Flexibilität in einigen Bereichen ergänzen und sogar ersetzen. Mit interessanten Perspektiven in der Bremsscheibenfertigung für Automobile.
-
PublicationNumerical and experimental assessment of liquid metal embrittlement in externally loaded spot welds( 2024-01-30)Zinc-based surface coatings are widely applied with high-strength steels in automotive industry. Some of these base materials show an increased brittle cracking risk during loading. It is necessary to examine electrogalvanized and uncoated samples of a high strength steel susceptible to liquid metal embrittlement during spot welding with applied external load. Therefore, a newly developed tensile test method with a simultaneously applied spot weld is conducted. A fully coupled 3D electrical, thermal, metallurgical and mechanical finite element model depicting the resistant spot welding process combined with the tensile test conducted is mandatory to correct geometric influences of the sample geometry and provides insights into the sample’s time dependent local loading. With increasing external loads, the morphology of the brittle cracks formed is affected more than the crack depth. The validated finite element model applies newly developed damage indicators to predict and explain the liquid metal embrittlement cracking onset and development as well as even ductile failure.
-
PublicationKI zur Prozessüberwachung im Unterpulverschweißen( 2024-01-15)Beim Unterpulverschweißen sind die Prozessgeräusche ein Indikator für eine gute Fügequalität. Diese Beurteilung kann i.d.R. nur von einer erfahrenen Fachkraft durchgeführt werden. Eine kürzlich entwickelte künstliche Intelligenz kann automatisch das akustische Prozesssignal anhand vortrainierter Merkmale klassifizieren und die Fügequalität anhand des Geräuschs beurteilen. Der Algorithmus, einmal richtig trainiert, kann den Prüfaufwand beim Unterpulverschweißen deutlich reduzieren.
-
PublicationVom prozessorientierten Qualitätsmanagementsystem zum adaptiven Lernpfad( 2024)Verschiedene Rahmenwerke des Qualitätsmanagements betonen die Relevanz kompetenter Mitarbeiter:innen für den Unternehmenserfolg. Unternehmen müssen erfolgskritische Kompetenzen bestimmen und bewerten sowie Maßnahmen zur Kompetenzentwicklung umsetzen. Dieser Beitrag stellt einen Ansatz vor, der Unternehmen dabei unterstützt, anhand von prozessorientierten Skill-Profilen und einer KI-basierten Lernplattform diese Aufgaben zu bewerkstelligen. Im Mittelpunkt stehen dabei adaptive Lernpfade der Beschäftigten. Das Fallbeispiel der FBT Feinblechtechnik GmbH demonstriert die Anwendung des Ansatzes in der Praxis.
-
PublicationIntegrated Consideration of Data Flows and Life Cycle Assessment in Vehicle Dismantling processes( 2024)The pursuit of environmental sustainability and resource conservation has underscored the growing significance of the circular economy paradigm across industries. This transformation is particularly pertinent within the automotive industry, necessitating a profound restructuring of the value chain, with a specific focus on end-of-life considerations. Significant potential for circular economy arises from the thorough examination of end-of-life vehicles and processes, involving strategies such as component reuse, material recycling and primary resource reduction. Providing process-, product-, component-, and material-specific information at the end-of-life of automotive vehicles can improve decision-making regarding circular strategies. It also demands for new digital solutions. This paper addresses an integrated approach of data flow analysis and Life Cycle Assessment (LCA) to enable a comprehensive monitoring of the environmental impact of these processes. First, the use case of end-of-life dismantling processes is presented - including pyrotechnics neutralization, vehicle dehydration, disassembly of reuse components as well as vehicle compaction. Secondly, the data demand respective information and material flows is depicted. As a main result, the LCA data flow model specifically tailored to the end-of-life vehicle dismantling processes is described. This model serves as a fundamental basis for analyzing the environmental impact of end-of-life processes combined with the underlying data flow.
-
PublicationOuter-Loop Admittance and Motion Control Dual Improvement via a Multi-Function Observer( 2024)Safe environment contact, and high-performance motion control are typically conflicting design goals. Admittance control can improve safety and stability in contact with a stiff environment but remains challenging on industrial robots. Typically, high-performance motion control is achieved by low-admittance systems, which can give high transient forces or instability in contact with high-stiffness environments. This article proposes a linear admittance control framework from which a multifunction observer (MOB)-based control scheme that succeeds in directly improving the motion control accuracy by suppressing disturbances, while achieving better loop shaping in the outer-loop admittance control is designed. By using the task space force and position measurement of the robot, combined with linearized position-controlled robot and payload models to design the MOB, the outer-loop controller can render improved interactive dynamics. In addition, a methodology to design the proposed MOB based on the reduced-order model is developed. Furthermore, the bounded-magnitude frequency-domain uncertainty in the linear model is identified at a variety of robot poses. Theoretical evaluations and experiments verify the effectiveness of the proposed MOB-based control method, in contact with a very stiff environment and with a 7-kg payload.
