About this role
Werken bij TU/e PhD in Control Theory for Learned Operators in Dynamical Systems - Personeelstype: Wetenschappelijk personeel - Vakgebied: Promovendus - Organisatie: Department of Mechanical Engineering - Solliciteer uiterlijk: 18-10-2026 - Voltijds equivalent: 1.0 FTE - Salaris: € 3.204 - € 4.051 Introduction Are you fascinated by the intersection of control theory and scientific machine learning? Join us in developing the mathematical foundations needed to make deep operators reliable, robust, and applicable for control of complex engineering systems. In this PhD project, you will investigate how operator-learning models can represent dynamical systems, how their stability and robustness can be characterized, and how controllers can be designed for them. Your work will combine rigorous theory, numerical methods, and applications in high-tech, medical, and energy systems. Job Description Modern engineering increasingly relies on data-driven models to describe complex dynamical systems. Scientific machine learning is now enabling a new class of models that learn operators mapping system inputs and initial conditions directly to system responses. These learned operators offer exciting opportunities for efficient simulation, digital twins, optimization, and control. In this PhD project, you will develop a new systems and control theory for learned operators, bridging modern scientific machine learning with classical control theory. Rather than focusing on a single machine-learning architecture, you will establish mathematical principles that apply across a broad class of operator-learning methods, including current and future deep operator models. Your research will investigate fundamental questions such as: when does a learned operator admit an equivalent state-space representation? How can stability, contraction, dissipativity, robustness, and other system-theoretic properties be defined and guaranteed directly in the opera...