Changing the properties of the material during physical and mechanical processing can significantly reduce the working life of the manufactured product, therefore it is important to control the quality of the surface layer of the parts. To solve this problem, non-destructive testing techniques such as etching, visual, capillary, magnetic powder, ultrasonic, vibration, eddy current methods are used at bearing enterprises. The article discusses the physical foundations of the presented techniques and provides their comparative analysis. Machine vision and digital signal processing approaches can be used to automate the processing of the results of non-destructive testing of the surface layer of bearing parts within the framework of the Industry 4.0 concept. From the point of view of productivity and the possibility of integration into the production system, the eddy current method is the most promising, the result of surface control in this way is an array of digital values. The development of modern methods of information analysis makes it possible to efficiently process a large amount of data, and machine learning makes it possible to solve problems of classification, regression, etc. This article provides methodological support for the development and application of an automated eddy current control system using machine learning and data mining methods. The works of scientists devoted to the processing of the results of the shock control of various objects, including bearing parts, are considered, it is noted that previously attention had not been paid to the issue of a reasonable choice of a machine learning model for recognizing defects on the surface of parts. The possibility of using the median polishing method to transform the eddy current signal is shown. The development and implementation of a bearing defect recognition system based on the methodological support presented in this paper can significantly improve the efficiency of product quality control and optimize the technological process.