Aiming at the new challenges in efficiency and reliability in the field of fault diagnosis in recent years

a coarsefine fault diagnosis method for induction motors based on the symmetrized dot pattern(SDP)was proposed.In this method

firstly

the vibration signals of each faulty motor were converted into snowflake images by SDP method

and then a two-stage fault diagnosis framework of coarse-fine classification was designed for image feature extraction and classification.In the coarse classification stage

the color histogram features and the support vector machine(SVM)were used to diagnose the samples

and a threshold was selected to determine the samples for the coarse classification.In the fine classification stage

Gist features that can extract image details and SVM were used to diagnose the remaining samples.Experimental results show that the proposed method combines the advantages of color histogram features and Gist features

can achieve the most reliable diagnosis with relatively high efficiency

and has certain anti-noise ability.