11:40   Classical and Machine learning methods in flow control II Two-Layered Forgetting RLS-based Indirect Adaptive Model Predictive Displacement Control for a Tap-Water-Driven Artificial Muscle Satoshi Tsuruhara, Kazuhisa Ito Abstract: A tap-water-driven artificial muscle has the advantages of both McKibben-type artificial muscles and tap-water-driven systems, which mainly have low environmental burden and cleanliness. However, it is difficult to model and control due to the strong asymmetric hysteresis characteristics of the muscle, so data-driven controls have been actively studied because they do not explicitly require the mathematical model. However, designing controllers from only data is often impractical, e.g. difficult to consider constraints such as the applied voltage to a valve, so we consider a novel control method that combines model-based and data-driven methods for muscle. In this study, we propose a novel two-layered forgetting factor-based indirect adaptive model predictive control (AMPC) that approximates the nonlinear characteristics of the muscle with hysteresis characteristics as a linear time-varying system using only the linear model structure of the muscle. The proposed method shows a fast parameter convergence rate to the neighborhood of true values for this time-varying system without requiring prior system identification. As a result, the proposed method effectively compensates the effect of hysteresis of the muscle at each time step and allows input constraints to be considered via AMPC. The experiment demonstrates the effectiveness of the proposed method by comparing the four methods. Integrated Shape and Tangential Jet-Based Flow Control Optimization Through Deep Reinforcement Learning Piergiorgio Scavella, Gerardo Paolillo, Carlo Salvatore Greco Abstract: Aerodynamic shape optimization and active flow control have long been studied as complementary strategies to improve airfoil performance across diverse flight regimes. Traditional optimization methods—whether gradient-based or gradient-free—often struggle with the complexity and high dimensionality of coupled shape-control problems, especially in the presence of nonlinear flow features such as separation and transition. Deep Reinforcement Learning (DRL), known for its ability to operate in complex, dynamic environments, offers a powerful alternative. This study presents a DRL-based framework that performs joint optimization of airfoil geometry and continuous tangential blowing, allowing the learning agent to simultaneously adapt shape and flow control parameters. By embedding active control into the design space, the algorithm autonomously identifies optimal actuation strategies and geometric configurations to improve aerodynamic performance. Experimental investigations are performed on the optimized geometries to validate the proposed optimization framework. The results demonstrate the potential of DRL for integrated aerodynamic design and control. Event-based imaging velocimetry for jet flow control Luca Franceschelli, Enrico Amico, Marco Raiola, Christian Willert, Jacopo Serpieri, Gioacchino Cafiero, Stefano Discetti Abstract: This study investigates the use of Event-Based Imaging Velocimetry (EBIV) as a viable sensing technology for optimising open-loop jet-flow control strategies. EBIV is deployed in a jet-control experiment in which the actuation system combines both acoustic and synthetic jet forcing; the resulting velocity fields are used to evaluate the performance of the control action. The goal is to develop and assess EBIV as a fast, reliable sensor in-the-loop to support advanced flow control optimization algorithms such as Bayesian Optimization and Deep Reinforcement Learning. Keywords: Flow control; Event-Based Imaging Velocimetry; Jet Flow; Synthetic Jets; Optimization

end %-->