Multi-Objective Physics-Guided Recurrent Neural Networks for Identifying Non-Autonomous Dynamical Systems
Oliver Schön, Ricarda-Samantha Götte, Julia Timmermann (2022): “Multi-Objective Physics-Guided Recurrent Neural Networks for Identifying Non-Autonomous Dynamical Systems.” 14th IFAC Workshop on Adaptive and Learning Control Systems (ALCOS 2022). The recording of the conference presentation is available at https://www.youtube.com/watch?v=MD5Vhy7z8DA.
Using AI to Analyze MBSE System Models
Abstract: Requirements Change Management requires the Assessment of Requirements Dependencies. We are developing an AI-based algorithm for probabilistic Change Propagation. Comming soon.
Physics-guided Neural Networks for Identifying Dynamical Systems
For my Master’s thesis, I started investigating the use of Physics-guided Neural Networks for identifying dynamical systems from Data. Please find the abstract and my Master’s thesis (German only) below. Abstract: Since their introduction, Physics-guided Neural Networks (PGNN), a novel class of hybrid models, have already been successfully implemented in several domains of application. …
Physics-guided Neural Networks for Identifying Dynamical Systems Read More »
PGNN-based Mixed Integer MPC for fast and automated COVID-19 PCR Tests
PGNN-based Mixed Integer MPC utilizing Bayesian Optimization and Exhaustive Search. Control of a Lab-on-Chip PCR testbed.
Biogas Production Project
Biogas as an environmentally friendly energy source is becoming increasingly valuable. This can be seen by the growing number of biogas powered vehicles. Though biogas production has been around for a long time, there are still a lot of challenges when it comes to efficient large-scale biogas production. During my semester abroad in Norway, I …