Modeling and Parameter Identification of the MR Damper Based on LS-SVM

Abstract

In order to identify the nonlinear characteristics of the magnetorheological (MR) damper applied in multi-DOF vibration reduction platforms in the aerospace field in the modeling process, the least square support vector machine (LS-SVM) method is adopted, because LS-SVM can handle small-sample, high-dimensional characteristic problems. Firstly, the theory of the modeling method based on LS-SVM was illustrated including the genetic algorithm (GA) optimization method. Secondly, the characteristic curve of the MR damper was tested based on different conditions. Then, the current and historical input displacement, velocity, and current and the historical output are taken as the input of the LS-SVM model and the damping force of the current output is taken as the output of the model for model training. Meanwhile, the genetic algorithm is introduced to optimize the parameters of the LS-SVM model which affect the accuracy of the model, the penalty factor c = 16.48 , and the kernel parameter σ = 3.39 after optimization. Finally, in order to verify the method adopted in the paper, the Simulink model was simulated in certain input conditions; by comparing the simulation and experimental values of this model, it is found that the maximum error is within 10 N and the average error is around 0.89 N, which is similar to the accuracy obtained in other works of literature, and the correctness of this model is verified.

An Enhanced Ant Colony Optimization Mechanism for the Classification of Depressive Disorders

“…GA is used in this research under the MATLAB programming framework. The wrapper decision is built using GA and LS-SVM classifier algorithms [ 24 ]. Individuals within a population were assigned binary strings 1 and 0, indicating whether the feature was taken into account and whether it was included or not.…”