Precise assessment of bearing performance degradation is the foundation and key of predictive maintenance for rotating machinery

and also a new research area nowadays.An optimized BP neural network based on glowworm swarm optimization algorithm is proposed and applied for the first time in the performance degradation assessment of bearings.The glowworm swarm optimization algorithm is applied to obtain the initial weights and thresholds of BP neural network

while power spectral entropy

wavelet entropy

box dimension

correlation dimension

kurtosis and skewness are selected as the fault features.Experiments show that the glowworm swarm optimization algorithm has improved the prediction accuracy of network and the proposed method can precisely assess the performance degradation of rolling bearings

the effectiveness and accuracy of the proposed method in engineering application is validated.