@article{MillerEngelmannKauppetal., author = {Miller, Eddi and Engelmann, Bastian and Kaupp, Tobias and Schmitt, Jan}, title = {Advanced Cascaded Scheduling for Highly Autonomous Production Cells with Material Flow and Tool Lifetime Consideration using AGVs}, series = {Journal of Machine Engineering}, journal = {Journal of Machine Engineering}, issn = {2391-8071}, language = {en} } @inproceedings{SeitzSchmittEngelmann, author = {Seitz, Philipp and Schmitt, Jan and Engelmann, Bastian}, title = {Evaluation of proceedings for SMEs to conduct I4.0 projects}, series = {Procedia Cirp}, volume = {86}, booktitle = {Procedia Cirp}, pages = {257 -- 263}, language = {en} } @inproceedings{SchirmerKranzSchmittetal., author = {Schirmer, Fabian and Kranz, Philipp and Schmitt, Jan and Kaupp, Tobias}, title = {Anomaly Detection for Dynamic Human-Robot Assembly: Application of an LSTM-based autoencoder to interpret uncertain human behavior in HRC}, series = {Companion of the 2023 ACM/IEEE International Conference on Human-Robot Interaction}, booktitle = {Companion of the 2023 ACM/IEEE International Conference on Human-Robot Interaction}, doi = {10.1145/3568294.3580100}, pages = {881 -- 883}, language = {en} } @inproceedings{MillerKauppSchmitt, author = {Miller, Eddi and Kaupp, Tobias and Schmitt, Jan}, title = {Cascaded Scheduling for Highly Autonomous Production Cells with AGVs}, series = {Manufacturing Driving Circular Economy: Proceedings of the 18th Global Conference on Sustainable Manufacturing, October 5-7, 2022, Berlin ; Lecture Notes in Mechanical Engineering}, booktitle = {Manufacturing Driving Circular Economy: Proceedings of the 18th Global Conference on Sustainable Manufacturing, October 5-7, 2022, Berlin ; Lecture Notes in Mechanical Engineering}, editor = {Kohl, Holger and Seliger, G{\"u}nther and Dietrich, Franz}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-28838-8}, doi = {https://doi.org/10.1007/978-3-031-28839-5_43}, pages = {383 -- 390}, abstract = {Highly autonomous production cells are a crucial part of manufacturing systems in industry 4.0 and can contribute to a sustainable value-adding process. To realize a high degree of autonomy in production cells with an industrial robot and a machine tool, an experimental approach was carried out to deal with numerous challenges on various automation levels. One crucial aspect is the scheduling problem of tasks for each resource (machine tool, tools, robot, AGV) depending on various data needed for a job-shop scheduling algorithm. The findings show that the necessary data has to be derived from different automation levels in a company: horizontally from ERP to shop-floor, vertically from the order handling department to the maintenance department. Utilizing that data, the contribution provides a cascaded scheduling approach for machine tool jobs as well as CNC and robot tasks for highly autonomous production cells supplied by AGVs.}, language = {en} } @article{MillerCeballosEngelmannetal., author = {Miller, Eddi and Ceballos, Hector and Engelmann, Bastian and Schiffler, Andreas and Batres, Rafael and Schmitt, Jan}, title = {Industry 4.0 and International Collaborative Online Learning in a Higher Education Course on Machine Learning}, series = {2021 Machine Learning-Driven Digital Technologies for Educational Innovation Workshop}, journal = {2021 Machine Learning-Driven Digital Technologies for Educational Innovation Workshop}, pages = {1 -- 8}, language = {en} } @article{SeitzScherdelReichenaueretal., author = {Seitz, Philipp and Scherdel, Christian and Reichenauer, Gudrun and Schmitt, Jan}, title = {Machine Learning in the development of Si-based anodes using Small-Angle X-ray Scattering for structural property analysis}, series = {Computational Materials Science}, volume = {218}, journal = {Computational Materials Science}, pages = {111984 -- 111984}, language = {en} } @article{ScherdelMillerReichenaueretal., author = {Scherdel, Christian and Miller, Eddi and Reichenauer, Gudrun and Schmitt, Jan}, title = {Advances in the Development of Sol-Gel Materials Combining Small-Angle X-ray Scattering (SAXS) and Machine Learning (ML)}, series = {Processes}, volume = {9}, journal = {Processes}, number = {4}, pages = {672 -- 672}, language = {en} } @inproceedings{WehnertSchaeferSchmittetal., author = {Wehnert, Kira-Kristin and Sch{\"a}fer, S and Schmitt, Jan and Schiffler, Andreas}, title = {C7. 4 Application of Laser Line Scanners for Quality Control during Selective Laser Melting (SLM)}, series = {SMSI 2021-System of Units and Metreological Infrastructure}, booktitle = {SMSI 2021-System of Units and Metreological Infrastructure}, pages = {298 -- 299}, language = {en} } @article{SeitzSchmitt, author = {Seitz, Philipp and Schmitt, Jan}, title = {Alternating Transfer Functions to Prevent Overfitting in Non-Linear Regression with Neural Networks}, series = {Journal of Experimental \& Theoretical Artificial Intelligence}, journal = {Journal of Experimental \& Theoretical Artificial Intelligence}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:863-opus-49199}, abstract = {In nonlinear regression with machine learning methods, neural networks (NNs) are ideally suited due to their universal approximation property, which states that arbitrary nonlinear functions can thereby be approximated arbitrarily well. Unfortunately, this property also poses the problem that data points with measurement errors can be approximated too well and unknown parameter subspaces in the estimation can deviate far from the actual value (so-called overfitting). Various developed methods aim to reduce overfitting through modifications in several areas of the training. In this work, we pursue the question of how an NN behaves in training with respect to overfitting when linear and nonlinear transfer functions (TF) are alternated in different hidden layers (HL). The presented approach is applied to a generated dataset and contrasted to established methods from the literature, both individually and in combination. Comparable results are obtained, whereby the common use of purely nonlinear transfer functions proves to be not recommended generally.}, language = {en} } @article{WeberWilhelmSchmitt, author = {Weber, Aleksej and Wilhelm, Markus and Schmitt, Jan}, title = {Analysis of Factors Influencing the Precision of Body Tracking Outcomes in Industrial Gesture Control}, series = {sensors}, volume = {24}, journal = {sensors}, number = {18}, publisher = {MDPI}, doi = {10.3390/s24185919}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:863-opus-57575}, pages = {18}, abstract = {The body tracking systems on the current market offer a wide range of options for tracking the movements of objects, people, or extremities. The precision of this technology is often limited and determines its field of application. This work aimed to identify relevant technical and environmental factors that influence the performance of body tracking in industrial environments. The influence of light intensity, range of motion, speed of movement and direction of hand movement was analyzed individually and in combination. The hand movement of a test person was recorded with an Azure Kinect at a distance of 1.3 m. The joints in the center of the hand showed the highest accuracy compared to other joints. The best results were achieved at a luminous intensity of 500 lx, and movements in the x-axis direction were more precise than in the other directions. The greatest inaccuracy was found in the z-axis direction. A larger range of motion resulted in higher inaccuracy, with the lowest data scatter at a 100 mm range of motion. No significant difference was found at hand velocity of 370 mm/s, 670 mm/s and 1140 mm/s. This study emphasizes the potential of RGB-D camera technology for gesture control of industrial robots in industrial environments to increase efficiency and ease of use.}, language = {en} }