Application of Machine Learning Methods to Control the Process of Defectoscopy of Railway Tracks

Abstract

This article describes the application of machine learning methods to control the process of railway flaw detection. It is told about the new capabilities of computer technology, which make it possible to clarify the damage for the lineman. A new way of interaction of a specialist with diagnostic information using the Internet of Things is proposed. The description of architecture is given according to three standards at the design stage. An application for a smartphone has been developed. The effectiveness of using foggy computing environments and cloud technologies for recognizing damage to railway tracks using machine learning has been proven. Specific examples are given.