Research Article

Improving Rolling Bearing Fault Diagnosis by DS Evidence Theory Based Fusion Model

Table 5

Comparisons of classification performances of different models.

Bearing conditionClassification accuracy
LVQBPLVQ-PCADecision treeTree pruningTree-PCADS fusion

Good, (%)70.09.187.585.586.282.490.4
Outer race fault, (%)66.711.178.972.774.097.996.6
Inner race fault, (%)100.090.0100.090.792.179.494.9
Average accuracy (%)78.936.788.883.084.186.694.0
Time (s)2.31.61.52.62.01.34.2