Emulating the dynamics of complex systems using autoregressive models on manifolds (mNARX)

TL;DR

This paper introduces mNARX, a manifold-based autoregressive surrogate model that efficiently approximates complex dynamical systems by leveraging physics and domain knowledge, outperforming traditional methods in accuracy and scalability.

Contribution

The paper presents mNARX, a novel manifold nonlinear autoregressive model that incorporates physics and domain knowledge to improve surrogate modelling of complex systems.

Findings

mNARX outperforms traditional autoregressive surrogates in predicting coupled spring-mass systems.

mNARX effectively models high-dimensional, time-dependent systems with active controllers.

The approach scales well with problem complexity and integrates with dimensionality reduction techniques.

Abstract

We propose a novel surrogate modelling approach to efficiently and accurately approximate the response of complex dynamical systems driven by time-varying exogenous excitations over extended time periods. Our approach, namely manifold nonlinear autoregressive modelling with exogenous input (mNARX), involves constructing a problem-specific exogenous input manifold that is optimal for constructing autoregressive surrogates. The manifold, which forms the core of mNARX, is constructed incrementally by incorporating the physics of the system, as well as prior expert- and domain- knowledge. Because mNARX decomposes the full problem into a series of smaller sub-problems, each with a lower complexity than the original, it scales well with the complexity of the problem, both in terms of training and evaluation costs of the final surrogate. Furthermore, mNARX synergizes well with traditional dimensionality reduction techniques, making it highly suitable for modelling dynamical systems with high-dimensional exogenous inputs, a class of problems that is typically challenging to solve. Since domain knowledge is particularly abundant in physical systems, such as those found in civil and mechanical engineering, mNARX is well suited for these applications. We demonstrate that mNARX outperforms traditional autoregressive surrogates in predicting the response of a classical coupled spring-mass system excited by a one-dimensional random excitation. Additionally, we show that mNARX is well suited for emulating very high-dimensional time- and state-dependent systems, even when affected by active controllers, by surrogating the dynamics of a realistic aero-servo-elastic onshore wind turbine simulator. In general, our results demonstrate that mNARX offers promising prospects for modelling complex dynamical systems, in terms of accuracy and efficiency.