Artificial Intelligence

The aim of the Artificial Intelligence Department at the IMI is to create and study intelligent human-centered systems in reality-like environments. 


We perform fundamental research on theory and algorithms for complex interacting systems, and apply our results to design smart systems and to understand processes in diverse fields such as advanced manufacturing, materials science, biology, neuroscience, or politics. We develop cutting-edge novel methods for Artificial Intelligence, including tools for statistical learning, unsupervised machine learning, data science, and applied mathematics. 
Examples of applications of our research include the new generation of Smart Energy Networks in Europe, the Internet of Things, AI for advanced manufacturing, systems of autonomous robots, Cyber-Physical Systems, Deep Learning, systems in virtual and augmented reality, and automated analysis of social, industrial, and political networks.

We demonstrate the positive impact of our results on economy and society by actively supporting the transfer of our innovations and technologies to practice. We have a number of industry partnerships, and collaborations with businesses and organizations, both national and global. 

Laufende Projekte
Titel Kurzbeschreibung Ansprechpartner

Wertstromkinematik - Produktionssysteme neu gedacht

AIBetOn3D: KI-assistierter 3D-Druck für Baustoffe

AITT - AI-assisted Technology Transfer

Deutsch-Chinesische Industrie 4.0 Fabrikautomatisierungsplattform

Unified demand response interoperability framework enabling market participation of active energy consumers


Intention recognition-based human–machine interaction for mixed flow assembly
Peng, J.; Kimmig, A.; Wang, D.; Niu, Z.; Tao, X.; Ovtcharova, J.
2024. Journal of Manufacturing Systems, 72, 229 – 244. doi:10.1016/j.jmsy.2023.11.021
Product quality recognition and its industrial application based on lightweight machine learning
Peng, J.; Wang, D.; Kreuzwieser, S.; Kimmig, A.; Tao, X.; Wang, L.; Ovtcharova, J.
2024. Engineering Optimization, 1–26. doi:10.1080/0305215X.2024.2305242
Human-Machine-Interaction in Innovative Work Environment 4.0 – A Human-Centered Approach
Kreuzwieser, S.; Kimmig, A.; Michels, F.; Bulander, R.; Häfner, V.; Bönsch, J.; Ovtcharova, J.
2023. New Digital Work – Digital Sovereignty at the Workplace. Ed.: A. Shajek, 68–86, Springer International Publishing. doi:10.1007/978-3-031-26490-0_ 5
A subject-oriented reference model for Digital Twins
Bönsch, J.; Elstermann, M.; Kimmig, A.; Ovtcharova, J.
2022. Computers and Industrial Engineering, 172 (Part A), Art.-Nr.: 108556. doi:10.1016/j.cie.2022.108556
Final Report Sino-German Industry 4.0 Factory Automation Platform
Albers, A.; Ovtcharova, J.; Becker, J.; Lanza, G.; Zhang, W.; Zhang, T.; Qiao, F.; Ma, Y.; Wang, J.; Wu, Z.; Ehrmann, C.; Gönnheimer, P.; Behrendt, M.; Mandel, C.; Stürmlinger, T.; Klippert, M.; Kimmig, A.; Schade, F.; Yang, S.; Heider, I.; Xie, S.; Song, K.; Peng, J.; Goncalves, P.; Kampfmann, R.; Schlechtendahl, J.; Kattner, J.; Straub, C.; May, M.; Zhu, Z.; Bai, O.; Lin, Y.; Yang, Z.; Ding, L.; Rossol, A.-S.
2022. (J. Fleischer, Hrsg.), Karlsruher Institut für Technologie (KIT). doi:10.5445/IR/1000143693
Prediction of cybersickness in virtual environments using topological data analysis and machine learning
Hadadi, A.; Guillet, C.; Chardonnet, J.-R.; Langovoy, M.; Wang, Y.; Ovtcharova, J.
2022. Frontiers in Virtual Reality, 3, Art.-Nr.: 973236. doi:10.3389/frvir.2022.973236
A systematic review of data-driven approaches to fault diagnosis and early warning
Jieyang, P.; Kimmig, A.; Dongkun, W.; Niu, Z.; Zhi, F.; Jiahai, W.; Jiahai, W.; Liu, X.
2022. Journal of Intelligent Manufacturing, 34 (8), 3277–3304. doi:10.1007/s10845-022-02020-0
Wind turbine failure prediction and health assessment based on adaptive maximum mean discrepancy
Peng, J.; Kimmig, A.; Niu, Z.; Wang, J.; Liu, X.; Wang, D.; Ovtcharova, J.
2022. International journal of electrical power & energy systems, 134, Art.Nr. 107391. doi:10.1016/j.ijepes.2021.107391
Dual-stage attention-based long-short-term memory neural networks for energy demand prediction
Peng, J.; Kimmig, A.; Wang, J.; Liu, X.; Niu, Z.; Ovtcharova, J.
2021. Energy and buildings, 249, Art.-Nr.: 111211. doi:10.1016/j.enbuild.2021.111211
Wertstromkinematik – Produktionssysteme neu gedacht: Interdisziplinäres Forscherteam arbeitet an der Produktionstechnik der Zukunft (Teil 2)
Kimmig, A.; Schöck, M.; Mühlbeier, E.; Oexle, F.; Fleischer, J.; Bönsch, J.; Ovtcharova, J.; Hahn, J.; Grunwald, A.; Albers, A.; Rapp, S.; Hagenmeyer, V.; Scholz, S. G.; Schmidt, A.; Müller, T.; Becker, J.; Schade, F.; Beyerer, J.; Rehak, J.; Zwick, T.; Pauli, M.; Nuß, B.; Lanza, G.; Schild, L.; Overbeck, L.
2021. Zeitschrift für wirtschaftlichen Fabrikbetrieb, 116 (12), 935–939. doi:10.1515/zwf-2021-0207
Human-Centered Referential Process Models for AI Application
Elstermann, M.; Bönsch, J.; Kimmig, A.; Ovtcharova, J.
2021. Human Centred Intelligent Systems: Proceedings of KES-HCIS 2021 Conference. Ed.: A. Zimmermann, 56–65, Springer. doi:10.1007/978-981-16-3264-8_6
A flexible potential-flow model based high resolution spatiotemporal energy demand forecasting framework
Peng, J.; Kimmig, A.; Niu, Z.; Wang, J.; Liu, X.; Ovtcharova, J.
2021. Applied Energy, 299, Art.-Nr.: 117321. doi:10.1016/j.apenergy.2021.117321
The Research of Flexible Scheduling of Workshop Based on Artificial Fish Swarm Algorithm and Knowledge Mining
Peng, J.; Wang, J.; Wang, D.; Kimmig, A.; Ovtcharova, J.
2020. Advances in Swarm Intelligence – 11th International Conference, ICSI 2020, Belgrade, Serbia, July 14–20, 2020, Proceedings. Ed.: Y. Tan, 104–116, Springer International Publishing. doi:10.1007/978-3-030-53956-6_10
Methodical approach for the development of a platform for the configuration and operation of turnkey production systems
Gönnheimer, P.; Kimmig, A.; Mandel, C.; Stürmlinger, T.; Yang, S.; Schade, F.; Ehrmann, C.; Klee, B.; Behrendt, M.; Schlechtendahl, J.; Fischer, M.; Trautmann, K.; Fleischer, J.; Lanza, G.; Ovtcharova, J.; Becker, J.; Albers, A.
2019. Procedia CIRP, 84, 880–885. doi:10.1016/j.procir.2019.04.260