A Multiple-Kernel Relevance Vector Machine with Nonlinear Decreasing Inertia Weight PSO for State Prediction of Bearing

<div>The comparison of the absolute percentage prediction errors for kurtosis of bearing vibration signal among NDIWPSO-MkRVM, NDIWPSO-RBFRVM and NDIWPSO-PolyRVM in case 1.</div>

Shock and Vibration

fig3

Figure 3

Figure 3: A Multiple-Kernel Relevance Vector Machine with Nonlinear Decreasing Inertia Weight PSO for State Prediction of Bearing 