TWO-STAGE INTELLIGENT FAULT DIAGNOSIS OF MOTORS BASED ON VISUAL IMAGE FEATURES
XU Dong
PENG Xin
ZHANG XiaoFei
Abstract：Aiming at the new challenges in efficiency and reliability in the field of fault diagnosis in recent years,a coarse-fine 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 clas⁃sification 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.
Keywords：Symmetrized dot patternVisual characteristicsSupport vector machineTwo-stage fault diagnosis
Publication Date：2024-12-15
Online Publishing Date：2026-09-12(First online date of this platform, not the publication date of the document)
Pages：7( 1295-1301 )