Recognizing defects in surface layer of bearings by using fractal analysis of eddy current signal

Bearing manufacturing requires strict adherence to the technological standards and quality control of products at all stages processing. One most accurate environmentally friendly monitoring methods in bearing production is eddy current method. When using this method, a large array numerical data generated that reflects information on physical mechanical conditions surface. Thus, defect detection process reduced defining task segmentation, is, selection parts an with different dynamics, which rather difficult for operator. To solve problem, pattern recognition system proposed, elements 
 are alphabet classes (defects surface layer), dictionary features (fractal dimension array), rules decision making (method standards). Fractal analysis applied two-dimensional consisting several vectors, will increase degree automation searching identifying sensor readings indicating defect, since affects layer product not only area its greatest prevalence. Three calculating fractal presented. Application reference method theory substantiated, analytical expression According proposed solutions, it possible classify rolling rings by preliminary each defect. Implementation software developed can improve efficiency update process.