Bilinear realization from input-output data with neural networks

TL;DR

This paper introduces a method that uses neural networks as surrogate data generators to accurately recover Markov parameters for bilinear system identification, enabling classical realization techniques for interpretable modeling and control.

Contribution

It combines neural networks with classical bilinear system realization to improve data-driven modeling and control design.

Findings

Neural networks effectively simulate input-output data sequences.

The method accurately recovers Markov parameters from measurements.

It produces interpretable bilinear models for engineering applications.

Abstract

We present a method that connects a well-established nonlinear (bilinear) identification method from time-domain data with neural network (NNs) advantages. The main challenge for fitting bilinear systems is the accurate recovery of the corresponding Markov parameters from the input and output measurements. Afterward, a realization algorithm similar to that proposed by Isidori can be employed. The novel step is that NNs are used here as a surrogate data simulator to construct input-output (i/o) data sequences. Then, classical realization theory is used to build a bilinear interpretable model that can further optimize engineering processes via robust simulations and control design.