Fig 1.
Dual-frequency feature extraction and energy matrix construction process for the VE-BRB model.
Fig 2.
The diagnosis process of the VE-BRB model.
Fig 3.
The overall framework of the VE-BRB model.
Fig 4.
(a) From CWRU (b) From HUST.
Fig 5.
The X/Y and DE/FE acceleration signals from the HUST and CWRU datasets.
(a) HUST-RE, (b) HUST-C, (c) HUST-IR, (d) HUST-OR, (e) CWRU-IR, (f) CWRU-NO, (g) CWRU-OR.
Table 1.
Reference values for input signals.
Fig 6.
Impact of the initial values of rule weights and attribute weights on model accuracy.
Fig 7.
Diagnostic interpretation results of the proposed VE-BRB model under the combination fault (C) condition.
(a) 3D visualization of rule activations; (b) Rule activation map based on the dual-frequency feature inputs; (c) Scatter distribution of the activation strength; (d) Histogram of the belief degree outputs corresponding to mixed fault states.
Fig 8.
Distributions of predicted bearing states.
Fig 9.
Confusion matrix for classification of bearing conditions.
Table 2.
Diagnostic results of Case 1 and Case 2 under different conditions.
Table 3.
Detailed description of the ablation experiment.
Fig 10.
Ablation study results for VE-BRB.