The Fault Diagnosis of Rolling Bearing Based on Improved Deep Forest

Table 1

Performance of proposed and compared methods under 4 classifications.

Method	Training accuracy (%)	Testing accuracy (%)
RF	62.04	64.51
ET	68.05	69.31
XGBoost	67.02	68.67
LightGBM	78.14	79.33
SVM	81.11	80.38
LSTM	80.81	80.38
gcForest	97.44	96.87
Proposed method	98.72	98.54