Design of experiments for the calibration of history-dependent models via deep reinforcement learning and an enhanced Kalman filter
From MaRDI portal
Publication:6159325
Abstract: Experimental data is costly to obtain, which makes it difficult to calibrate complex models. For many models an experimental design that produces the best calibration given a limited experimental budget is not obvious. This paper introduces a deep reinforcement learning (RL) algorithm for design of experiments that maximizes the information gain measured by Kullback-Leibler (KL) divergence obtained via the Kalman filter (KF). This combination enables experimental design for rapid online experiments where traditional methods are too costly. We formulate possible configurations of experiments as a decision tree and a Markov decision process (MDP), where a finite choice of actions is available at each incremental step. Once an action is taken, a variety of measurements are used to update the state of the experiment. This new data leads to a Bayesian update of the parameters by the KF, which is used to enhance the state representation. In contrast to the Nash-Sutcliffe efficiency (NSE) index, which requires additional sampling to test hypotheses for forward predictions, the KF can lower the cost of experiments by directly estimating the values of new data acquired through additional actions. In this work our applications focus on mechanical testing of materials. Numerical experiments with complex, history-dependent models are used to verify the implementation and benchmark the performance of the RL-designed experiments.
Recommendations
- Bayesian sequential optimal experimental design for nonlinear models using policy gradient reinforcement learning
- Calibration experimental design considering field response and model uncertainty
- Optimal experimental design and some related control problems
- Experimental design for partially observed Markov decision processes
- Optimal learning in experimental design using the knowledge gradient policy with application to characterizing nanoemulsion stability
Cites work
- \(\mathrm{SO}(3)\)-invariance of informed-graph-based deep neural network for anisotropic elastoplastic materials
- A non-cooperative meta-modeling game for automated third-party calibrating, validating and falsifying constitutive laws with parallelized adversarial attacks
- A return mapping algorithm for isotropic and anisotropic plasticity models using a line search method
- A Review of Modern Computational Algorithms for Bayesian Optimal Design
- A thermo-mechanically coupled theory for large deformations of amorphous polymers. II: Applications
- Approximation error bounds via Rademacher's complexity
- Bayesian experimental design: A review
- Deep reinforcement learning. Fundamentals, research and applications
- scientific article; zbMATH DE number 5822909 (Why is no real title available?)
- Kernel-based reinforcement learning
- Meta-modeling game for deriving theory-consistent, microstructure-based traction-separation laws via deep reinforcement learning
- Model Calibration and Parameter Estimation
- Novel sparseness-inducing dual Kalman filter and its application to tracking time-varying spatially-sparse structural stiffness changes and inputs
- Optimal Design of Experiments
- Reinforcement learning in the brain
- Reinforcement learning. An introduction
Cited in
(2)
This page was built for publication: Design of experiments for the calibration of history-dependent models via deep reinforcement learning and an enhanced Kalman filter
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6159325)
