Method and device for predicting residual service life of rotary machine and electronic equipment

The invention discloses a method and a device for predicting the residual service life of a rotary machine and electronic equipment. The method comprises the following steps of: performing envelope transformation on collected data and calculating a statistical index; related features are selected and dimensionality reduction is carried out to obtain health indexes; abnormal value elimination and monotonicity enhancement are carried out on the health indexes, and a fault threshold value is calculated; integrating weak attention into the GRU network to obtain a prediction model; training of a prediction model is completed by using historical information; and completing the task of predicting the remaining service life by using the trained model. According to the method, sensitive health indexes are constructed through sensitivity enhancement and feature calculation and selection of the envelope spectrum, and health monitoring of equipment is facilitated; weak attention is integrated for the GRU network, and the