The Fault Diagnosis of Rolling Bearing Based on Improved Deep Forest

Table 2

Performance of proposed and compared methods under 10 classifications.

Method	Training accuracy (%)	Testing accuracy (%)
RF	37.42	39.10
ET	43.19	40.35
XGBoost	47.68	44.36
LightGBM	55.02	57.89
SVM	67.13	73.43
LSTM	57.65	57.89
gcForest	95.31	94.99
Proposed method	98.05	96.99