Nonlinear System Identification based on Support Vector Machine using Particle Swarm Optimization

Lee, Byunghwa; Kim, Sangun; Seok, Jinwuk; Won, Sangchul

doi:10.1109/sice.2006.315099

Cited by 9 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It improves the generalization ability through the principle of structural risk minimization, and solves practical problems such as small samples, non-linearity, high dimension, local minima, etc. It has been applied in pattern recognition, signal processing, function approximation and other fields [16].…”

Section: The Lssvm Based On the Cedamentioning

confidence: 99%

SAW Torque Sensor Gyroscopic Effect Compensation by Least Squares Support Vector Machine Algorithm Based on Chaos Estimation of Distributed Algorithm

Han

Cao

et al. 2019

Sensors

View full text Add to dashboard Cite

As this study examined the issue of surface acoustic wave (SAW) torque sensor which interfered in high rotational speed, the gyroscopic effect generated by rotation was analyzed. Firstly, the SAW coupled equations which contained torque and rotation loads were deduced, and the torque calculation error caused by rotation was solved. Following this, the hardware of the SAW gyroscopic effect testing platform and the turntable experiment were designed to verify the correctness of the theoretical calculation. Finally, according to the experimental data, the gyroscopic effect was compensated by multivariate polynomial fitting (MPF), Gaussian processes regression (GPR), and least squares support vector machine algorithms (LSSVM). The comparison results showed that the LSSVM has the obvious advantage. For improving the function of LSSVM model, chaos estimation of distributed algorithm (CEDA) was proposed to optimize the super parameters of the LSSVM, and numerical simulation results showed that: (1) CEDA is superior to traditional estimation of distributed algorithms in convergence speed and anti-premature ability; (2) the performance of CEDA-LSSVM is better than genetic algorithms (GA)-LSSVM and particle swarm optimization (PSO)-LSSVM. After compensating by CEDA-LSSVM, the magnitude of the torque calculation relative error was 10−4 in any direction. This method has a significant effect on reducing gyroscopic interference, and it lays a foundation for the engineering application of SAW torque sensor.

show abstract

Section: The Lssvm Based On the Cedamentioning

confidence: 99%