Deep Convolutional Networks in System Identification

TL;DR

This paper explores the application of deep convolutional networks, specifically TCNs, to nonlinear system identification, establishing connections with classical models and demonstrating effectiveness on real-world datasets.

Contribution

It introduces the relationship between TCNs and traditional system identification models, bridging deep learning and control theory.

Findings

TCNs are comparable to recurrent models for sequence tasks

Experimental results on Silverbox and F-16 datasets show promising performance

Deep learning models can effectively model nonlinear systems

Abstract

Recent developments within deep learning are relevant for nonlinear system identification problems. In this paper, we establish connections between the deep learning and the system identification communities. It has recently been shown that convolutional architectures are at least as capable as recurrent architectures when it comes to sequence modeling tasks. Inspired by these results we explore the explicit relationships between the recently proposed temporal convolutional network (TCN) and two classic system identification model structures; Volterra series and block-oriented models. We end the paper with an experimental study where we provide results on two real-world problems, the well-known Silverbox dataset and a newer dataset originating from ground vibration experiments on an F-16 fighter aircraft.