Encoder initialisation methods in the model augmentation setting

TL;DR

This paper introduces new encoder initialization methods leveraging baseline models in neural state-space identification, enhancing noise robustness and convergence speed over traditional black-box approaches.

Contribution

It proposes novel encoder initialization techniques that incorporate baseline models, improving interpretability, noise robustness, and convergence in neural state-space system identification.

Findings

Improved noise robustness with baseline-based initialisation

Faster convergence compared to black-box methods

Validated on a mass-spring-damper system

Abstract

Nonlinear system identification (NL-SI) has proven to be effective in obtaining accurate models for highly complex systems. Recent encoder-based methods for artificial neural network state-space (ANN-SS) models have shown state-of-the-art performance with improved computational efficiency, where the encoder is used to estimate the initial state allowing for batch optimisation methods. To address the lack of interpretability of these black-box ANN models, model augmentation approaches can be used. These combine prior available baseline models with the ANN learning components, resulting in faster convergence and more interpretable models. The combination of the encoder-based method with model augmentation has shown potential. Thus far, however, the encoder has still been treated as a black-box function in the overall estimation process, while additional information in the form of the baseline model is available to predict the model state from past input-output data. In this paper, we propose novel encoder initialisation approaches based on the available baseline model, resulting in improved noise robustness and faster convergence compared to black-box initialisation. The performance of these initialisation methods is demonstrated on a mass-spring-damper system.