Research Article

Bearing Degradation Process Prediction Based on the Support Vector Machine and Markov Model

Table 7

The corrected results of the points 1−20 based on Markov model.

PointSVM model prediction errorRelative error (%)SVM-Markov model prediction errorRelative error (%)

10000
2−0.0103821579.21%−0.006361178.31%
30.0029068.5739%0.0006031.7791%
40.007427120.311%−0.0010212.7922%
5−0.021835274.63%−0.009362117.75%
60.02413830.429%0.01325416.708%
70.005954312.666%0.0026155.5628%
80.01624422.459%0.01002713.863%
90.02231633.565%0.00956514.386%
100.01669232.417%0.00947318.397%
110.05393573.825%0.02156329.515%
12−0.005235834.947%−0.00235515.719%
13−0.058422107.06%−0.01934735.455%
14−0.094039122.79%−0.01423618.589%
15−0.032173263.1%−0.00987880.779%
16−0.034682159.3%−0.00896941.197%
17−0.004101355.3%−0.001892199.5%
18−0.13365117.18%−0.05084144.576%
19−0.06811120.92%−0.02832350.282%
20−0.070675135.04%−0.01426727.152%