Fault Diagnosis of Flywheel Components Based on Ensemble Empirical Mode Decomposition and Support Vector Machine
The flywheel assembly for satellite is an important executive component of satellite attitude control.It is necessary to monitor the status of flywheel components in time,but in the actual production process,it is often impossible to monitor the status of flywheel components due to the lack of experimental data in the early stage.It was proposed that the simulation data was used with white noise to optimize the support vector machine to achieve the purpose of state monitoring of flywheel components.At the same time,the ensemble empirical mode decomposition was used to denoise the measured signal.The denoised signal was used to verify the classification accuracy of the support vector machine.The test results showed that the support vector machine can identify normal,inner and outer ring fault states.The classification efficiency reached 98.33%.
ensemble empirical mode decompositionsupport vector machinesatellite attitude control
NETL
NSTL
万方数据
