Deep Dictionary-Free Method for Identifying Linear Model of Nonlinear System with Input Delay

TL;DR

This paper presents a novel, dictionary-free deep learning approach using LSTM-enhanced Koopman models to accurately linearize and predict nonlinear systems with input delays, outperforming traditional methods.

Contribution

It introduces a new LSTM-enhanced Deep Koopman model that captures delayed dynamics without predefined dictionaries, improving prediction accuracy for nonlinear systems with input delays.

Findings

Significant improvement in prediction accuracy over extended eDMD.

Comparable results to eDMD with known dynamics.

Effective encoding of time delays into a linear framework.

Abstract

Nonlinear dynamical systems with input delays pose significant challenges for prediction, estimation, and control due to their inherent complexity and the impact of delays on system behavior. Traditional linear control techniques often fail in these contexts, necessitating innovative approaches. This paper introduces a novel approach to approximate the Koopman operator using an LSTM-enhanced Deep Koopman model, enabling linear representations of nonlinear systems with time delays. By incorporating Long Short-Term Memory (LSTM) layers, the proposed framework captures historical dependencies and efficiently encodes time-delayed system dynamics into a latent space. Unlike traditional extended Dynamic Mode Decomposition (eDMD) approaches that rely on predefined dictionaries, the LSTM-enhanced Deep Koopman model is dictionary-free, which mitigates the problems with the underlying dynamics being known and incorporated into the dictionary. Quantitative comparisons with extended eDMD on a simulated system demonstrate highly significant performance gains in prediction accuracy in cases where the true nonlinear dynamics are unknown and achieve comparable results to eDMD with known dynamics of a system.