Prediction of particulate content in oil based on SPA vibration feature selection

Aiming at the non-stationary characteristics of oil pressure vibration signals containing particulate, a method for predicting particulate content in was proposed based on characteristic frequency extraction by vibrational mode decomposition (VMD), variable selection using successive projections algorithm (SPA) and T_S fuzzy identification combined. Firstly, signal decomposed VMD series narrow-band matrices were obtained. Then, variables selected SPA to construct feature vector matrix. Finally, matrix used as input identify oil. The results showed that reconstruction original sample could well characterize main variation signal; 19 from SPA, 11 sets taken model; each set sample, predicted output obtained, model prediction decision coefficient is 0.8637, root mean square error 0.1979, reasonable effect