Diagnosing of devices of railway automatic equipment on the basis of methods of diverse data fusion

Abstract

In the this work it is emphasized that fusion of the diverse data obtained from sources of primary information (sensors, the measuring equipment, systems, subsystems) for adoption of diagnostic decisions at a research of malfunctions of devices of railway transport, is one of the main problems. The generalized scheme of fusion of diverse data reflecting features of this process is considered. Also classification of levels, modern methods of fusion of diverse data in the conditions of incomplete, indistinct basic data is considered. Approach to fusion of diverse data on malfunction of the devices of railway transport received from a set of various sensors with use of the theory of Dempster-Shafer for the purpose of their integration and development of uniform diagnostic decisions for the benefit of end users is offered. Rationing of the weight coefficients reflecting ability of sensors, and fusion of values of mass of probability is the cornerstone of the offered approach. A numerical example for a decision-making illustration at diagnostics of malfunctions of devices of railway transport in the conditions of uncertainty is reviewed.