Overview and details of the sessions of this conference. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
Please note that all times are shown in the time zone of the conference. The current conference time is: 17th May 2024, 09:51:54am CEST
Session Chair: Matthias Kreimeyer, University of Stuttgart, Germany
Location:Congress Hall Orlando 2
Presentations
Towards a process for the creation of synthetic training data for AI-computer vision models utilizing engineering data
Sebastian Schwoch, Maximilian Peter Dammann, Johannes Georg Bartl, Maximilian Kretzschmar, Bernhard Saske, Kristin Paetzold-Byhain
Technische Universität Dresden, Germany
Artificial Intelligence-based Computer Vision models (AI-CV models) for object detection can support various applications over the entire lifecycle of machines and plants such as monitoring or maintenance tasks. Despite ongoing research on using engineering data to synthesize training data for AI-CV model development, there is a lack of process guidelines for the creation of such data. This paper proposes a synthetic training data creation process tailored to the particularities of an engineering context addressing challenges such as the domain gap and methods like domain randomization.
Surrogate-based design optimization of the binder cover combining performance and production cost
Pavel Eremeev1,2, Hendrik Devriendt1,2, Alexander De Cock3, Frank Naets1,2
This study integrates surrogate models into combined design optimization of a binder cover, considering production cost and performance constraints. Results reveal that models trained on substantial datasets achieve designs close to the global optimum. Incorporating model variance into constraints prediction in surrogate-based optimization improves robustness and accuracy, especially with noisy functions. This modification enhances the likelihood of obtaining feasible designs, reducing computational demands and showcasing the potential of smaller datasets in predicting local optima.
An AI-based prosthesis framework fostering an adaptive amputee healthcare service
Nicholas Patiniott1, Jonathan C. Borg1, Emmanuel Francalanza1, Joseph P. Zammit1, Pierre Vella1, Alfred Gatt1, Kristin Paetzold-Byhain2
1University of Malta, Malta; 2Technische Universität Dresden, Germany
Despite technological and medical advances, amputations continue to increase. Amputees face significant challenges when acquiring and using prosthetic devices, challenges which are made worse as their emotional needs, aspirations, mobility, prosthesis requirements and problems change over time. These challenges require custom solutions for each individual amputee, a fact that current amputee centered prosthesis services tend to ignore. The work reported in this paper contributes an AI based Prosthesis Development Service Framework to cater for the current and evolving needs of amputees.
Critical component detection in assemblies: a graph centrality approach
Robert Ballantyne, Adam McClenaghan, Oliver Schiffmann, Chris Snider
University of Bristol, United Kingdom
This study examines the use of graph centrality to identify critical components in assembly models, a method typically dominated by computationally intense analyses. By applying centrality measures to simulated assembly graphs, components were ranked to assess their criticality. These rankings were compared against Monte Carlo sensitivity analysis results. Preliminary findings indicate a promising correlation, suggesting graph centrality as a valuable tool in assembly analysis, enhancing efficiency and insight in critical component identification.
Automatic movement pattern analysis for data-driven system optimisation – an example for fattening livestock farming monitoring system
Gurubaran Raveendran, Sören Meyer zu Westerhausen, Johanna Wurst, Roland Lachmayer
Leibniz University Hannover, Germany
This paper introduces a method for analysing motion patterns that can be utilised to optimise data-driven systems. The aim is to use surveillance cameras and artificial intelligence to track multiple objects in a reliable manner, thereby preserving the authenticity of movement patterns for numerous and similar objects. In a case study, this method is applied to optimize lighting conditions in animal husbandry. Furthermore, this approach can be utilized not only in animal husbandry but also in other domains.
