Abstract
Fault diagnosis of rolling bearings is key to maintain and repair modern rotating machinery. Rolling bearings are usually working in non-stationary conditions with time-varying loads and speeds. Existing diagnosis methods based on vibration signals only don’ t have the ability to adapt to rotational speed. And when the load changes, the accuracy rate of them will be obviously reduced. A method is put forward which fuses multi-modal sensor signals to fit speed information. Firstly, the features are extracted from raw vibration signals and instantaneous rotating speed signals, and fused by 1D-CNN-based networks. Secondly, to improve the robustness of the model when the load changes, a majority voting mechanism is proposed in the diagnosis stage. Lastly, Multiple variable speed samples of four bearings under three loads are obtained to evaluate the performance of the proposed method by analyzing the loss function, accuracy rate and F1 score under different variable speed samples. It is empirically found that the proposed method achieves higher diagnostic accuracy and speed-adaptive ability than the algorithms based on vibration signal only. Moreover, A couple of ablation studies are also conducted to investigate the inner mechanism of the proposed speed-adaptive network.
Author response: Learning multiple variable-speed sequences in striatum via cortical tutoring
