As an important part of mechanical equipment,rolling bearings play an important role in the stable operation of mechanical equipment.Commonly,the fault signal of rolling bearing is the superposition of multiple signals,so it is necessary to decompose the collected vibration signal,and then realize the identification of different fault mode of rolling bearing based on the pattern recognition method.A mechanical equipment fault classification and recognition method based on adaptive local iterative filtering (ALIF) and isometric feature mapping (ISOMAP) was proposed.ALIF was used to decompose the fault signals of rolling bearings; the multiple statistical features of selected mode components was extracted; finally,ISOMAP was used to perform dimensionality reduction processing on high-dimensional feature signals to realize the recognition of different failure modes of rolling bearings.The research results show that the proposed method has a good effect on the fault identification of rolling bearings.