Gradient-free optimization of chaotic acoustics with reservoir computing

Abstract

We develop a versatile optimization method, which finds the design parameters that minimize time-averaged acoustic cost functionals. The method is gradient-free, model-informed, and data-driven with reservoir computing based on echo state networks. First, we analyse the predictive capabilities of echo state networks both in the short- and long-time prediction of the dynamics. We find that both fully data-driven and model-informed architectures learn the chaotic acoustic dynamics, both time-accurately and statistically. Informing the training with a physical reduced-order model with one acoustic mode markedly improves the accuracy and robustness of the echo state networks, whilst keeping the computational cost low. Echo state networks offer accurate predictions of the long-time dynamics, which would be otherwise expensive by integrating the governing equations to evaluate the time-averaged quantity to optimize. Second, we couple echo state networks with a Bayesian technique to explore the design thermoacoustic parameter space. The computational method is minimally intrusive. Third, we find the set of flame parameters that minimize the time-averaged acoustic energy of chaotic oscillations, which are caused by the positive feedback with a heat source, such as a flame in gas turbines or rocket motors. These oscillations are known as thermoacoustic oscillations. The optimal set of flame parameters is found with the same accuracy as brute-force grid search, but with a convergence rate that is more than one order of magnitude faster. This work opens up new possibilities for non-intrusive ("hands-off") optimization of chaotic systems, in which the cost of generating data, for example from high-fidelity simulations and experiments, is high.

arXiv comment16 figures, 26 pages

References in corpus (15)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model
• A review of linear response theory for general differentiable dynamical systems
• Least Squares Shadowing sensitivity analysis of chaotic limit cycle oscillations
• Forward and Adjoint Sensitivity Computation of Chaotic Dynamical Systems
• Sensitivity analysis on chaotic dynamical system by Non-Intrusive Least Square Shadowing (NILSS)
• Sensitivity analysis of a time-delayed thermo-acoustic system via an adjoint-based approach
• Echo State Networks trained by Tikhonov least squares are L2(μ) approximators of ergodic dynamical systems
• Multiple Shooting Shadowing for Sensitivity Analysis of Chaotic Dynamical Systems
• Global modes, receptivity, and sensitivity analysis of diffusion flames coupled with duct acoustics
• Sensitivity Analysis of Chaotic Systems using Unstable Periodic Orbits
• Hyperbolicity, shadowing directions and sensitivity analysis of a turbulent three-dimensional flow
• Adjoint sensitivity analysis on chaotic dynamical systems by Non-Intrusive Least Squares Adjoint Shadowing (NILSAS)
• Stability, sensitivity and optimisation of chaotic acoustic oscillations
• Probability density adjoint for sensitivity analysis of the Mean of Chaos

Cited by in corpus (5)

• Stability analysis of chaotic systems from data
• Real-time thermoacoustic data assimilation
• Recursive divergence formulas for perturbing unstable transfer operators and physical measures
• Model-free Forecasting of Rogue Waves using Reservoir Computing
• Direct data-driven forecast of local turbulent heat flux in Rayleigh-Bénard convection