- S. Kamm, K. Sharma, N. Jazdi, and M. Weyrich, “A Hybrid Modelling Approach for Parameter Estimation of Analytical Reflection Models in the Failure Analysis Process of Semiconductors,” in 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE), Lyon, France, 23-27 August 2021, 2021, pp. 417–422.
- S. Kamm, N. Jazdi, and M. Weyrich, “Automatisierte Datenintegration für den Fehleranalyseprozess von Halbleiterbauelementen mithilfe von Ontologien und Graphen,” in VDI-Kongress Automation 2021, 29.-30.06.2021, Virtuell, 2021.
- B. Maschler, S. Kamm, and M. Weyrich, “Deep industrial transfer learning at runtime for image recognition,” at - Automatisierungstechnik, vol. 69, no. 3, pp. 211-220, 03.2021, 2021.
- S. Kamm, K. Sharma, I. Kallfass, N. Jazdi, and M. Weyrich, “Hybrid Modelling for the Failure Analysis of SiC Power Transistors on Time-Domain Reflectometry Data,” in 2021 IEEE International Symposium on the Physical and Failure Analysis of Integrated Circuits (IPFA), 2021.
- S. Kamm, N. Jazdi, and M. Weyrich, “Knowledge Discovery in Heterogeneous and Unstructured Data of Industry 4.0 Systems: Challenges and Approaches,” in 54th CIRP Conference on Manufacturing Systems, Athen, Greece, September 2021, 2021.
- N. Sahlab, S. Kamm, T. Müller, N. Jazdi, and M. Weyrich, “Knowledge Graphs as Enhancers of Intelligent Digital Twins,” in 4th IEEE International Conference on Industrial Cyber-Physical Systems (ICPS), May 2021, 2021.
- K. Sharma, S. Kamm, V. Afanasenko, K. M. Barón, and I. Kallfass, “Non-Destructive Failure Analysis of Power Devices via Time- Domain Reflectometry,” in 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE), Lyon, France, 23-27 August 2021, 2021, pp. 423–428.
- B. Maschler, S. Kamm, N. Jazdi, and M. Weyrich, “Distributed Cooperative Deep Transfer Learning for Industrial Image Recognition,” in 53rd CIRP Conference on Manufacturing Systems (Virtual Conference), 1-3 July 2020, Chicago, pp. 437-442, 2020.
Research focus: Analyzing heterogeneous data using AI methods for robust decisions
Description: The amount of recordable data continues to increase. As a result, the variety and thus the heterogeneity of the data are also increasing more and more. This brings new challenges for data management and data analysis of this heterogeneous data. Data management should provide the data in a uniform, machine-readable format as best as possible in order to make the data centrally accessible to the user and downstream analysis models. Moreover, classical machine learning models typically use only data of one form (e.g., image data) for data analysis.
To take advantage of the variety of data, new machine learning models shall be explored and applied to make robust decisions on this database. For this purpose, existing knowledge (e.g. in the form of simulation models) shall be used to improve the learning behavior of the models. Furthermore, methods are to be investigated with which the data for these analysis models can be provided centrally while preserving the complex relations.
Research portal: ResearchGate Simon Kamm