Human-induced force reconstruction using a non-linear electrodynamic shaker applying an iterative neural network algorithm
An iterative neural network framework is proposed in this paper for the human-induced Ground Reaction Forces (GRF) replication with an inertial electrodynamic mass actuator (APS 400). This is a first approach to the systematization of dynamic load tests on structures in a purely objective, repeatabl...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Polish Academy of Sciences
2023-03-01
|
Series: | Bulletin of the Polish Academy of Sciences: Technical Sciences |
Subjects: | |
Online Access: | https://journals.pan.pl/Content/126564/PDF/BPASTS_2023_71_3_3347.pdf |
_version_ | 1797793703435173888 |
---|---|
author | César Peláez-Rodríguez Álvaro Magdaleno Sancho Salcedo-Sanz Antolín Lorenzana |
author_facet | César Peláez-Rodríguez Álvaro Magdaleno Sancho Salcedo-Sanz Antolín Lorenzana |
author_sort | César Peláez-Rodríguez |
collection | DOAJ |
description | An iterative neural network framework is proposed in this paper for the human-induced Ground Reaction Forces (GRF) replication with an inertial electrodynamic mass actuator (APS 400). This is a first approach to the systematization of dynamic load tests on structures in a purely objective, repeatable and pedestrian-independent basis. Therefore, an inversion-free offline algorithm based on Machine Learning techniques has been applied for the first time on an electrodynamic shaker, without requiring its inverse model to tackle the inverse problem of successful force reconstruction. The proposed approach aims to obtain the optimal drive signal to minimize the error between the experimental shaker output and the reference force signal, measured with a pair of instrumented insoles (Loadsol©) for human bouncing at different fre- quencies and amplitudes. The optimal performance, stability and convergence of the system are verified through experimental tests, achieving excellent results in both time and frequency domain. |
first_indexed | 2024-03-13T02:52:08Z |
format | Article |
id | doaj.art-0b340b52c4524c09bbaf7f8ae12ab4c9 |
institution | Directory Open Access Journal |
issn | 2300-1917 |
language | English |
last_indexed | 2024-03-13T02:52:08Z |
publishDate | 2023-03-01 |
publisher | Polish Academy of Sciences |
record_format | Article |
series | Bulletin of the Polish Academy of Sciences: Technical Sciences |
spelling | doaj.art-0b340b52c4524c09bbaf7f8ae12ab4c92023-06-28T10:00:05ZengPolish Academy of SciencesBulletin of the Polish Academy of Sciences: Technical Sciences2300-19172023-03-01713https://doi.org/10.24425/bpasts.2023.144615Human-induced force reconstruction using a non-linear electrodynamic shaker applying an iterative neural network algorithmCésar Peláez-Rodríguez0https://orcid.org/0000-0003-1260-8112Álvaro Magdaleno1Sancho Salcedo-Sanz2Antolín Lorenzana3Department of Signal Processing and Communications, Universidad de Alcalá, Alcalá de Henares, 28805, SpainITAP. Escuela de Ingenierías Industriales. Universidad de Valladolid. P.º del Cauce, 59, 47011 Valladolid, SpainDepartment of Signal Processing and Communications, Universidad de Alcalá, Alcalá de Henares, 28805, SpainITAP. Escuela de Ingenierías Industriales. Universidad de Valladolid. P.º del Cauce, 59, 47011 Valladolid, SpainAn iterative neural network framework is proposed in this paper for the human-induced Ground Reaction Forces (GRF) replication with an inertial electrodynamic mass actuator (APS 400). This is a first approach to the systematization of dynamic load tests on structures in a purely objective, repeatable and pedestrian-independent basis. Therefore, an inversion-free offline algorithm based on Machine Learning techniques has been applied for the first time on an electrodynamic shaker, without requiring its inverse model to tackle the inverse problem of successful force reconstruction. The proposed approach aims to obtain the optimal drive signal to minimize the error between the experimental shaker output and the reference force signal, measured with a pair of instrumented insoles (Loadsol©) for human bouncing at different fre- quencies and amplitudes. The optimal performance, stability and convergence of the system are verified through experimental tests, achieving excellent results in both time and frequency domain.https://journals.pan.pl/Content/126564/PDF/BPASTS_2023_71_3_3347.pdfground reaction forceselectrodynamic shakerartificial neural networksforces reconstructioniterative neural network |
spellingShingle | César Peláez-Rodríguez Álvaro Magdaleno Sancho Salcedo-Sanz Antolín Lorenzana Human-induced force reconstruction using a non-linear electrodynamic shaker applying an iterative neural network algorithm Bulletin of the Polish Academy of Sciences: Technical Sciences ground reaction forces electrodynamic shaker artificial neural networks forces reconstruction iterative neural network |
title | Human-induced force reconstruction using a non-linear electrodynamic shaker applying an iterative neural network algorithm |
title_full | Human-induced force reconstruction using a non-linear electrodynamic shaker applying an iterative neural network algorithm |
title_fullStr | Human-induced force reconstruction using a non-linear electrodynamic shaker applying an iterative neural network algorithm |
title_full_unstemmed | Human-induced force reconstruction using a non-linear electrodynamic shaker applying an iterative neural network algorithm |
title_short | Human-induced force reconstruction using a non-linear electrodynamic shaker applying an iterative neural network algorithm |
title_sort | human induced force reconstruction using a non linear electrodynamic shaker applying an iterative neural network algorithm |
topic | ground reaction forces electrodynamic shaker artificial neural networks forces reconstruction iterative neural network |
url | https://journals.pan.pl/Content/126564/PDF/BPASTS_2023_71_3_3347.pdf |
work_keys_str_mv | AT cesarpelaezrodriguez humaninducedforcereconstructionusinganonlinearelectrodynamicshakerapplyinganiterativeneuralnetworkalgorithm AT alvaromagdaleno humaninducedforcereconstructionusinganonlinearelectrodynamicshakerapplyinganiterativeneuralnetworkalgorithm AT sanchosalcedosanz humaninducedforcereconstructionusinganonlinearelectrodynamicshakerapplyinganiterativeneuralnetworkalgorithm AT antolinlorenzana humaninducedforcereconstructionusinganonlinearelectrodynamicshakerapplyinganiterativeneuralnetworkalgorithm |