To address the difficulty in extracting the characteristics of combined failure of rolling bearings, a novel fault identification method, one-dimensional mixed binary pattern (1D-MBP), is proposed. Firstly, regarding that variance can better highlight the partial weak failure information of sequence than median, the binarization of vibration signals based on one-dimensional local binary pattern (1D-LBP) is carried out with variance as criterion. Meanwhile, binarization sequence is converted to decimal sequence as the local conversion signal (LCS). Secondly, considering that failure information of rolling bearings is reflected in partial and global texture, the paper proposed the method of gaining global weighted mean value by weighting partial mean value with partial energy. Binarize vibration signals based on one-dimensional global binary pattern (1D-GBP) with obtained global weighted mean value as criterion and convert the obtained binarized sequence into decimal as the global conversion signal (GCS). Thirdly, signals are reconstructed by obtained LCS and GCS to get 1D-MBP signal. Finally, combined failure types of bearing can be identified from 1D-MBP signals based on TEAGER energy spectrum (TES). The result indicates that the 1D-MBP not only can effectively control noise components in vibration signal but also can precisely identify the combined failure types of rolling bearings.