Direct shape optimization through deep reinforcement learning

2019/08/23 by Jonathan Viquerat, Jean Rabault, Viquerat, Jonathan +9 · 17 citations
Physics and Astronomy · Computer Science · Engineering · #Model Reduction and Neural Networks #Advanced Multi-Objective Optimization Algorithms #Topology Optimization in Engineering

paper · doi:10.1016/j.jcp.2020.110080

Abstract

Deep Reinforcement Learning (DRL) has recently spread into a range of domains within physics and engineering, with multiple remarkable achievements. Still, much remains to be explored before the capabilities of these methods are well understood. In this paper, we present the first application of DRL to direct shape optimization. We show that, given adequate reward, an artificial neural network trained through DRL is able to generate optimal shapes on its own, without any prior knowledge and in a constrained time. While we choose here to apply this methodology to aerodynamics, the optimization process itself is agnostic to details of the use case, and thus our work paves the way to new generic shape optimization strategies both in fluid mechanics, and more generally in any domain where a relevant reward function can be defined. • Deep Reinforcement Learning coupled with Computational fluid Dynamics. • Optimal shapes generation through Deep Reinforcement Learning. • Shape generation using Bézier curves and implemented in a new DRL environment. • Adequate reward function and shaping based on the lift-to-drag ratio. • Introduction of a degenerate DRL approach as general purpose optimizers.

Citations

• Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control

Cited by

• Reinforcement Learning for Active Flow Control in Experiments
• DiffeoMorph: Learning to Morph 3D Shapes Using Differentiable Agent-Based Simulations
• Autonomously Designed Pulses for Precise, Site-Selective Control of Atomic Qubits
• Transfer learning strategies for accelerating reinforcement-learning-based flow control
• SmartFlow: A CFD-solver-agnostic deep reinforcement learning framework for computational fluid dynamics on HPC platforms
• Oranits: Mission Assignment and Task Offloading in Open RAN-based ITS using Metaheuristic and Deep Reinforcement Learning
• Reinforcement Learning for Accelerated Aerodynamic Shape Optimisation
• Analytical coarse grained potential parameterization by Reinforcement Learning for anisotropic cellulose
• Design Optimization of a Pneumatic Soft Robotic Actuator Using Model-Based Optimization and Deep Reinforcement Learning. [europepmc]
• Manipulation of free-floating objects using Faraday flows and deep reinforcement learning. [europepmc]
• Asymmetric Airfoil Morphing via Deep Reinforcement Learning. [europepmc]
• Attention-Based Multi-Objective Control for Morphing Aircraft. [europepmc]
• Flow control of three-dimensional cylinders transitioning to turbulence via multi-agent reinforcement learning. [europepmc]
• Sensor-Driven Surrogate Modeling and Control of Nonlinear Dynamical Systems Using FAE-CAE-LSTM and Deep Reinforcement Learning. [europepmc]
• A novel comprehensible non-intrusive sensitivity-driven additive Aerodynamic Shape Optimization (AASO) and its implementation using the Lattice Boltzmann Method (AASO-LBM). [europepmc]
• Application of deep reinforcement learning for aerodynamic control around an angled airfoil via synthetic jet. [europepmc]
• On Bio-Inspired Strategies for Flow Control, Fluid-Structure Interaction, and Thermal Transport. [europepmc]

Related

• A mechanism-driven reinforcement learning framework for shape optimization of airfoils
• Deep Reinforcement Learning in Fluid Mechanics: a promising method for both Active Flow Control and Shape Optimization
• Reinforcement Learning for Accelerated Aerodynamic Shape Optimisation
• Airfoil Shape Optimization using Deep Q-Network
• Deep convolutional neural network for shape optimization using level-set approach