TY - JOUR A1 - Augustine, Nitin A1 - Schwab, Maximilian A1 - Klarmann, Steffen A1 - Pfefferer, Christian A1 - Schiendorfer, Alexander T1 - Impact of Blemish Artefacts on Object Detection Models in Autonomous Driving: A Study on Camera Module Manufacturing Defects JF - Procedia Computer Science N2 - With the rise of autonomous driving technology, concerns over the safety of AI-based systems have increased, particularly regarding their effect on human life and infrastructure. The complexity and unpredictable nature of AI-enabled software functions have disrupted traditional safety evaluation methods. In such a scenario, the quality control methods used at the manufacturing environments of sensors used for deploying AI-based perception functions need to be coupled with the downstream functions. This study focuses on investigating the impact of a specific production-related defect called blemish, which is caused by debris on image sensors of camera modules. The research aims to answer two fundamental questions: 1) How can blemish artifacts be mathematically modeled, and what is the process for developing a suitable dataset that incorporates this defect? 2) How can the influence of blemish artifacts on performance of object detection models be traced back to define quality requirements of the camera modules? This work takes a novel perspective by shifting the focus from improving model resilience to improving hardware quality camera modules by studying the effects of manufacturing defects on downstream functions. This research seeks to establish a framework to derive quality targets for front camera module manufacturing which can be extended to other sensors for similar applications. UR - https://doi.org/10.1016/j.procs.2024.01.061 Y1 - 2024 UR - https://doi.org/10.1016/j.procs.2024.01.061 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-46388 SN - 1877-0509 VL - 2024 IS - 232 SP - 616 EP - 625 PB - Elsevier CY - Amsterdam ER - TY - CHAP A1 - Baschin, Anja A1 - Baschin, Michelle A1 - Böselt, Reinhard A1 - Felix, Rudolf A1 - Fernandez, Cesareo A1 - Gehring, Sven A1 - Görtz, Alexander A1 - Harpeng, Lars A1 - Hei, Yuguang A1 - Hildebrandt, Niclas A1 - Hügging, Thomas A1 - Kätzel, Pascal A1 - Kolberg, Kristoffer-Robin A1 - Kuoza, Leonid A1 - Luzius, Lukas A1 - Lisca, Gheorghe A1 - Michailov, Lilia A1 - Multhaup, Werner A1 - Outafraout, Karima A1 - Proch, Fabian A1 - Schiendorfer, Alexander A1 - Simmanek, Marcel A1 - Streubel, Tom T1 - Industrielle Künstliche Intelligenz für sichere Gasnetze T2 - Tagungsband 18. Symposium Energieinnovation 2024 Y1 - 2024 UR - https://www.tugraz.at/events/eninnov2024/nachlese/download-beitraege/stream-a/#c590685 PB - Technische Universität Graz CY - Graz ER - TY - CHAP A1 - Gajek, Carola A1 - Schiendorfer, Alexander A1 - Reif, Wolfgang ED - Amini, Massih-Reza ED - Canu, Stéphane ED - Fischer, Asja ED - Guns, Tias ED - Kralj Novak, Petra ED - Tsoumakas, Grigorios T1 - A Recommendation System for CAD Assembly Modeling based on Graph Neural Networks T2 - Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2022, Proceedings, Part I UR - https://doi.org/10.1007/978-3-031-26387-3_28 KW - Graph Machine Learning KW - Recommendation KW - Computer-aided Design KW - AI-aided Design Y1 - 2023 UR - https://doi.org/10.1007/978-3-031-26387-3_28 SN - 978-3-031-26387-3 SN - 978-3-031-26386-6 SP - 457 EP - 473 PB - Springer CY - Cham ER - TY - CHAP A1 - Schönmann, Alexander A1 - Lodes, Lukas A1 - Schiendorfer, Alexander ED - Dumitrescu, Roman ED - Hölzle, Katharina T1 - KI-Augmentation der Reifegradbewertung von Technologien: Können KI-Sprachmodelle Expertenwissen ersetzen? T2 - Vorausschau und Technologieplanung: 17. Symposium für Vorausschau und Technologieplanung, 14. und 15. September 2023, Berlin UR - https://doi.org/10.17619/UNIPB/1-1821 Y1 - 2023 UR - https://doi.org/10.17619/UNIPB/1-1821 SN - 978-3-947647-32-3 SP - 371 EP - 387 PB - Heinz-Nixdorf-Institut CY - Paderborn ER - TY - CHAP A1 - Lodes, Lukas A1 - Schiendorfer, Alexander ED - Kinnaird, Katherine M. ED - Steinbach, Peter ED - Guhr, Oliver T1 - A Deep Learning Bootcamp for Engineering & Management Students T2 - Proceedings of the Third Teaching Machine Learning and Artificial Intelligence Workshop Y1 - 2023 UR - https://proceedings.mlr.press/v207/lodes23a.html SP - 32 EP - 36 PB - PMLR CY - [s. l.] ER - TY - CHAP A1 - Dachtler, Kristina A1 - Ortner, Michael A1 - Ferri, Massimo A1 - Eberst, Christof A1 - Schiendorfer, Alexander T1 - Data-centric and Goal-oriented AI for Robotic Repair Tasks T2 - ISR Europe 2023, 56th International Symposium on Robotics, in cooperation with Fraunhofer IPA September 26 – 27, 2023 in Stuttgart Y1 - 2023 SN - 978-3-8007-6141-8 N1 - Auch veröffentlicht auf IEEE: https://ieeexplore.ieee.org/document/10363053 PB - VDE Verlag CY - Berlin ER - TY - CHAP A1 - Lodes, Lukas A1 - Schiendorfer, Alexander ED - Do, Phuc ED - Michau, Gabriel ED - Ezhilarasu, Cordelia T1 - Certainty Groups: A Practical Approach to Distinguish Confidence Levels in Neural Networks T2 - Proceedings of the European Conference of the PHM Society 2022 N2 - Machine Learning (ML), in particular classification with deep neural nets, can be applied to a variety of industrial tasks. It can augment established methods for controlling manufacturing processes such as statistical process control (SPC) to detect non-obvious patterns in high-dimensional input data. However, due to the widespread issue of model miscalibration in neural networks, there is a need for estimating the predictive uncertainty of these models. Many established approaches for uncertainty estimation output scores that are difficult to put into actionable insight. We therefore introduce the concept of certainty groups which distinguish the predictions of a neural network into the normal group and the certainty group. The certainty group contains only predictions with a very high accuracy that can be set up to 100%. We present an approach to compute these certainty groups and demonstrate our approach on two datasets from a PHM setting. UR - https://doi.org/10.36001/phme.2022.v7i1.3331 KW - machine Learning KW - classification KW - uncertainty KW - estimaton KW - neural network Y1 - 2022 UR - https://doi.org/10.36001/phme.2022.v7i1.3331 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-31307 SN - 978-1-936263-36-3 SP - 294 EP - 305 PB - PHM Society CY - State College ER - TY - JOUR A1 - Stieber, Simon A1 - Schröter, Niklas A1 - Fauster, Ewald A1 - Bender, Marcel A1 - Schiendorfer, Alexander A1 - Reif, Wolfgang T1 - Inferring material properties from FRP processes via sim-to-real learning JF - The International Journal of Advanced Manufacturing Technology N2 - Fiber reinforced polymers (FRP) provide favorable properties such as weight-specific strength and stiffness that are central for certain industries, such as aerospace or automotive manufacturing. Liquid composite molding (LCM) is a family of often employed, inexpensive, out-of-autoclave manufacturing techniques. Among them, resin transfer molding (RTM), offers a high degree of automation. Herein, textile preforms are saturated by a fluid polymer matrix in a closed mold.Both impregnation quality and level of fiber volume content are of crucial importance for the final part quality. We propose to simultaneously learn three major textile properties (fiber volume content and permeability in X and Y direction) presented as a three-dimensional map based on a sequence of camera images acquired in flow experiments and compare CNNs, ConvLSTMs, and Transformers. Moreover, we show how simulation-to-real transfer learning can improve a digital twin in FRP manufacturing, compared to simulation-only models and models based on sparse real data. The overall best metrics are: IOU 0.5031 and Accuracy 95.929 %, obtained by pretrained transformer models. UR - https://doi.org/10.1007/s00170-023-11509-8 KW - Sequence-to-Image Learning KW - Architecture comparison KW - FRP KW - LCM KW - Transfer Learning KW - Industry 4.0 KW - Digital Twin Y1 - 2022 UR - https://doi.org/10.1007/s00170-023-11509-8 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-32402 SN - 1433-3015 VL - 128 IS - 3-4 SP - 1517 EP - 1533 PB - Springer CY - London ER - TY - CHAP A1 - Bhavnani, Sidhant A1 - Schiendorfer, Alexander ED - Schaus, Pierre T1 - Towards copeland optimization in combinatorial problems T2 - Integration of Constraint Programming, Artificial Intelligence, and Operations Research; 19th International Conference, CPAIOR 2022, Los Angeles, CA, USA, June 20-23, 2022; Proceedings UR - https://doi.org/10.1007/978-3-031-08011-1_4 KW - constraint programming KW - social choice theory KW - OR Y1 - 2022 UR - https://doi.org/10.1007/978-3-031-08011-1_4 SN - 978-3-031-08010-4 SN - 978-3-031-08011-1 N1 - Access provided by Nationallizenz Ebooks Medicine SP - 34 EP - 43 PB - Springer CY - Cham ER - TY - CHAP A1 - Stieber, Simon A1 - Schröter, Niklas A1 - Fauster, Ewald A1 - Schiendorfer, Alexander A1 - Reif, Wolfgang ED - Wani, M. Arif ED - Sethi, Ishwar ED - Shi, Weisong ED - Qu, Guangzhi ED - Raicu, Daniela Stan ED - Jin, Ruoming T1 - PermeabilityNets: Comparing Neural Network Architectures on a Sequence-to-Instance Task in CFRP Manufacturing T2 - Proceedings: 20th IEEE International Conference on Machine Learning and Applications (ICMLA 2021) UR - https://doi.org/10.1109/ICMLA52953.2021.00116 KW - Sequence-to-Instance Learning KW - Architecture comparison KW - CFRP KW - LCM KW - Industry 4.0 KW - Digital Twin Y1 - 2021 UR - https://doi.org/10.1109/ICMLA52953.2021.00116 SN - 978-1-6654-4337-1 SP - 694 EP - 697 PB - IEEE CY - Piscataway ER -