Postdoc
TU Kaiserslautern | Kaiserslatern, Germany
Classification: Control Theory and Optimization
The department of “Mechatronics In Mechanical And Automotive Engineering” at TU-Kaiserslautern (https://www.mv.uni-kl.de/mec/home) is seeking fill a research associate position for 3+ years (PhD or Postdoc position) within the scope of a DFG project for the Automation of the Carbonation Process. * Job Description: One of the primary goals of the project is to develop an algorithm to autonomously control the operation of the carbonation process chain. To this end, the aim is to develop a Self-Learning Robust Autonomous Control(ler) (SLARC) algorithm using a parametric statistical estimators which need to be implemented using (deep) neural networks (DNN). Consequently, these networks are to be trained using process specific data and process model (PDE simulation). Since autonomy is the primary objective, reinforcement-learning (RL) methods have to incorporated to enable continuous (online) learning of the process dynamics and consequently its control. More specifically, the work comprises of the following tasks: - Formulation of a process specific stochastic optimization problem - To analyze wellposedness of the optimization problem- controllability and observability properties - To establish stochastic-IOSS conditions for SLARC operating in closed loop. - To develop and implement process specific DNN based controllers - Incorporate RL methodology to facilitate online learning - Verification and validation of the controller in simulation and closed-loop setting - Collaborate with process engineers to obtain relevant process specific knowledge and measurement data * Payment according to TV-L E13 * Start of employment: 01.09.2022 * Duration of employment: initially for 1 year, extendible upto 6 years. * Hours of employment: to be agreed * Requirements: - A Master’s or PhD degree in Mathematics with outstanding grades. Preferably specializing in stochastic control and/or (nonlinear) PDE control and/or stochastic analysis - Basic knowledge in Machine learning or mathematical statistics is expected. - Fluent in Python programming. Knowledge in Pytorch library is an advantage. - Proficiency in English is essential. Knowing German is an advantage. - Highly motivated, independent and reliable, commitment to scientific research, willingness to engage and take initiative, positive attitude and good team skills. * Please submit your application via email to the PI of the project Dr. Sandesh Athni Hiremath (sandesh.hiremath(at)mv.uni-kl.de, https://www.mv.uni-kl.de/mec/staff/sandesh-hiremath) no later than 31.08.2022. Your application should be a single PDF file comprising the following documents: - Cover Letter - CV - University Certificates - References - List of Publications (optional) Further information on the open position is available here: https://www.mv.uni-kl.de/mec/open-positions/learning-based-stochastic-control-with-application-in-process-engineering For additional queries and info please feel free to contact on the above mentioned email.
Last updated: 30 July 2022