Deep Convolutional Networks in System Identification
This work addresses the problem of improving nonlinear system identification for engineering applications, but it is incremental as it builds on existing TCN methods and applies them to new datasets.
The paper explores the application of temporal convolutional networks (TCNs) to nonlinear system identification, establishing connections with classic models like Volterra series and block-oriented models, and provides experimental results on real-world datasets including the Silverbox and an F-16 fighter aircraft vibration dataset.
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.