Assessment of hybrid machine learning models for non-linear system identification of fatigue test rigs

TL;DR

This paper introduces a hybrid machine learning approach combining traditional models with LSTM networks to improve non-linear system identification in fatigue test rigs, demonstrating enhanced prediction accuracy and virtual sensing capabilities.

Contribution

It presents a novel hybrid modeling method integrating LSTM networks with existing models for non-linear system identification in fatigue testing.

Findings

Improved prediction accuracy over traditional linear models

Effective virtual sensing demonstrated on experimental data

Validated approach with publicly available dataset

Abstract

The prediction of system responses for a given fatigue test bench drive signal is a challenging task, for which linear frequency response function models are commonly used. To account for non-linear phenomena, a novel hybrid model is suggested, which augments existing approaches using Long Short-Term Memory networks. Additional virtual sensing applications of this method are demonstrated. The approach is tested using non-linear experimental data from a servo-hydraulic test rig and this dataset is made publicly available. A variety of metrics in time and frequency domains, as well as fatigue strength under variable amplitudes, are employed in the evaluation.