A hybrid objective function for robustness of artificial neural networks-estimation of parameters in a mechanical system

Electronic Transactions on Numerical Analysis

article

Jan Sokolowski¹  Volker Schulz¹  Hans-Peter Beise³  Udo Schroeder² 

[1] Department of Mathematics, Trier University;Department of Basics & Mathematical Models;Dept. of Computer Science, Trier University of Applied Sciences

关键词: system identification;    parameter estimation;    convolutional neural networks;    sequential data;    prediction robustness;    mathematical modelling;    dynamical systems;   

DOI  :  10.1553/etna_vol56s209

学科分类：数学（综合）

来源: Kent State University * Institute of Computational Mathematics

【 摘 要 】

In several studies, hybrid neural networks have proven to be more robust against noisy input data compared to plain data driven neural networks. We consider the task of estimating parameters of a mechanical vehicle model based on acceleration profiles. We introduce a convolutional neural network architecture that given sequential data, is capable to predict the parameters for a family of vehicle models that differ in the unknown parameters. This network is trained with two objective functions. The first one constitutes a more naive approach that assumes that the true parameters are known. The second objective incorporates the knowledge of the underlying dynamics and is therefore considered as hybrid approach. We show that in terms of robustness, the latter outperforms the first objective on unknown noisy input data.

【 授权许可】

Unknown