Multi-modal multi-sensor feature fusion spiking neural network algorithm for early bearing weak fault diagnosis

To address the problem of diagnosing early weak faults in bearings, a multi-modal multi-sensor feature fusion Spiking Neural Network algorithm is proposed in this paper. At the feature level, Principal Component Analysis is utilized to merge the vibration signals in the horizontal and vertical directions from multiple sensors, so as to fully utilize the feature information of multi - modal signals. Subsequently, Moving Average denoising is adopted to highlight the information features of weak faults. Signal augmentation is achieved by serially connecting the fused vibration signals of multiple sensors, and the feature extraction capability is further enhanced by using the Continuous Wavelet Transform to extract the time frequency modal features, finally constructing a Spiking Neural Network intelligent diagnostic model. Experimental results show that this algorithm is superior to other feature extraction and diagnostic algorithms in accurately diagnosing early weak faults in bearings.