Rupenyan Alisa

Alisa Rupenyan

Dr. Alisa Rupenyan

Postadresseinspire AG
Dr. Alisa Rupenyan
ETL I29
Physikstrasse 3
CH-8092 Zürich
Schweiz
Telefon+41 44 632 81 42
BüroETL I29
Email
Websitehttp://www.inspire.ethz.ch/de/ifa
Mitarbeiter-KategorieLeitung ifa
Mitarbeiter-Gruppeadvanced control and IoT (inspire-ifa)
SprachkenntnisseDeutsch, Englisch
Vereine / FachgruppenIEEE-CSS, TC Manufacturing Automation TC Process Control; IEEE-RAS, TC Model-based optimization, TC Robot Learning; IFAC Industry committee, Expert for Innosuisse
Kompetenzen
  • Scientific and technical supervision of projects in the field of advanced control algorithms, merging machine learning with optimal control for mechatronics and process control
  • Multidisciplinary background combining expertise in laser physics, robotics and control, and machine learning
  • Data-driven optimization and automation of manufacturing processes
    - Process and performance optimization
    - Data-driven methods for fault detection/prediction
    - Data-driven process control
    - Learning-based control, predictive control
Referenzprojekte
  • Data-driven insights for smart grinding / Innosuisse Nr 31695.1 IP-ENG
  • Décolleteur 4.0  / Innosuisse Nr 32835.1 IP-ENG
  • Data-Driven Adaptive Control for High-End Motion Systems / Innosuisse Nr 46716.1 IP-ENG
  • Adaptive Coating Tracker & In-situ Verification (ACTIV) / Innosuisse Nr 37896.1 IP-ENG
Publikationen
  • Mohammad Khosravi, Varsha Behrunani, Piotr Myszkorowski, Roy S. Smith, Alisa Rupenyan and John Lygeros, Performance-driven cascade controller tuning with Bayesian optimization,  IEEE Transactions on Industrial Electronics, 2021 (early access)

  • Alisa Rupenyan, Mohammad Khosravi and John Lygeros, Performance-based Trajectory Optimization for Path Following Control Using Bayesian Optimization, Computing research repository, abs/2103.15416, 2021

  • Christopher König, Mateo Turchetta, John Lygeros, Alisa Rupenyan and Andreas Krause, Safe and efficient model-free adaptive control via Bayesian optimization, 2021 IEEE International Conference for Robotics and Automation, 2021

  • Markus Maier, Alisa Rupenyan, Christian Bobst and Konrad Wegener, Self-optimizing grinding machines using Gaussian process models and constrained Bayesian optimization, The International Journal of Advanced Manufacturing Technology, volume 108, pages 528–552, 2020

 

siehe auch Research Collection ETH