Dynamical System Parameter Identification using Deep Recurrent Cell Networks

TL;DR

This paper explores using deep recurrent neural networks, especially BiLSTMs, for identifying damping factors in second-order linear dynamical systems, demonstrating improved accuracy over unidirectional models.

Contribution

It introduces a novel application of bidirectional gated recurrent cells for dynamical system parameter identification, showing their superiority over traditional unidirectional models.

Findings

BiLSTMs outperform GRUs and LSTMs in damping factor identification.

Bidirectional models utilize information from both past and future in sequence data.

Deep recurrent architectures effectively capture system parameters from finite input-output sequences.

Abstract

In this paper, we investigate the parameter identification problem in dynamical systems through a deep learning approach. Focusing mainly on second-order, linear time-invariant dynamical systems, the topic of damping factor identification is studied. By utilizing a six-layer deep neural network with different recurrent cells, namely GRUs, LSTMs or BiLSTMs; and by feeding input-output sequence pairs captured from a dynamical system simulator, we search for an effective deep recurrent architecture in order to resolve damping factor identification problem. Our study results show that, although previously not utilized for this task in the literature, bidirectional gated recurrent cells (BiLSTMs) provide better parameter identification results when compared to unidirectional gated recurrent memory cells such as GRUs and LSTM. Thus, indicating that an input-output sequence pair of finite length, collected from a dynamical system and when observed anachronistically, may carry information in both time directions for prediction of a dynamical systems parameter.