This article is devoted to the diagnosis of bearing failures of traction electric motor of electric trains of railways and subways. One of the main sources of mechanical failures of an traction electric motor is bearings. To control the technical condition of the bearings of an traction electric motor, it is proposed to use parameters such as temperature, vibration and noise. The developed model of the expert system based on fuzzy logic and diagnostic parameters allows, at the initial stage, to reflect the probability of bearing failure in real time under operating conditions when the input parameters change. A fuzzy expert system represents knowledge in the form of fuzzy productions and linguistic variables. The expert system model was developed using the Mamdani fuzzy inference algorithm of the Fuzzy Logic Toolbox package in the MATLAB computing environment. The use of fuzzy logic in the development of a knowledge base and inference mechanisms makes it possible to formalize the procedure for assessing the technical condition on the basis of fragmentary, unreliable and possibly inaccurate information and to make reasonable decisions on fault identification.