Simulation-Driven Universal Surrogates of Coupled Mechanical Systems: Real-Time Simulation of a Forestry Crane
Journal of Computational and Nonlinear Dynamics · 01.07.2024 · 19 (7)
DOI: 10.1115/1.4065015 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computational and Nonlinear Dynamics, online erschienen am 13.05.2024. Verfasst von Qasim Khadim und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 61 Literaturangaben.
Abstract (Originalsprache)
Preparing simulation-driven surrogates for a coupled mechanical system can be challenging because the associated mechanical and actuator dynamics demand high-fidelity numerical solutions. Proposed here is a universal hydraulic surrogate (UHS), which can provide solutions to high-fidelity mechanical systems with a universal actuator in a surrogate-assisted monolithic approach. The UHS acts as an alternative to the standard lumped fluid theory by eliminating the hydraulic pressures differential equations. A surrogate-assisted universal actuator uses an approximated model to define hydraulic force in high-fidelity mechanical systems. The approximated force model was developed through training against the dynamics of a one-dimensional (1D) hydraulic cylinder and spring-damper. A covariance matrix adaption evolutionary strategy (CMA-ES) was used as an optimization algorithm to minimize differences between the standard dynamics and UHS approaches at the position and velocity levels. The robustness of resulting UHS was validated to predict the behaviors of the simple four-bar mechanism and the forestry crane. The focus was on numerical accuracy and computational efficiency. The maximum percent normalized root mean square error (PN-RMSE) between the states of the approximated force model and lumped fluid theory were approximately 2.04% and 6.95%, respectively. The proposed method was approximately 52 times faster than the standard lumped fluid theory method. By providing accurate predictions outside the training data, the simulation-driven UHS promises better computational performance leading to real-time simulation solutions for the coupled mechanical systems. The UHS can be applied in simulation, optimization, control, state and parameter estimation, and Artificial Intelligence (AI) implementations for coupled mechanical systems.
Zitieren
APA
Khadim, Q., Kurvinen, E., Mikkola, A., & Orzechowski, G. (2024). Simulation-Driven Universal Surrogates of Coupled Mechanical Systems: Real-Time Simulation of a Forestry Crane. Journal of Computational and Nonlinear Dynamics, 19(7). https://doi.org/10.1115/1.4065015
Vancouver
Khadim Q, Kurvinen E, Mikkola A, Orzechowski G. Simulation-Driven Universal Surrogates of Coupled Mechanical Systems: Real-Time Simulation of a Forestry Crane. Journal of Computational and Nonlinear Dynamics. 2024;19(7). doi:10.1115/1.4065015
BibTeX
@article{Khadim2024,
author = {Khadim, Qasim and Kurvinen, Emil and Mikkola, Aki and Orzechowski, Grzegorz},
title = {Simulation-Driven Universal Surrogates of Coupled Mechanical Systems: Real-Time Simulation of a Forestry Crane},
journal = {Journal of Computational and Nonlinear Dynamics},
year = {2024},
volume = {19},
number = {7},
doi = {10.1115/1.4065015}
}
EUVIMED