In order to accurately describe the performance degradation trend and predict the remaining useful life of rolling bearings

and solve the problem of low prediction accuracy of the remaining useful life of rolling bearings

a new method for predicting the remaining useful life of rolling bearings was proposed based on multi-scale degradation index combined with Informer model. The time-frequency domain characteristics of rolling bearing vibration signals were first extracted

and a multi-scale degradation index was obtained by Pearson correlation coefficient combined with kernel Principal Component analysis (KPCA)

which could better characterize the degradation state of rolling bearings. Informer model was introduced to efficiently and fully explore the complex relationship between the input multi-scale degradation index and the rolling bearing degradation trend

and realize the prediction of the remaining useful life of rolling bearings. The experimental results show that this method can effectively improve the prediction accuracy of remaining useful life of bearings

and provide a reference and implementation approach for health management and performance evaluation of rolling bearings.