Search results

The purpose of this article is to create mathematical models for a comprehensive assessment of the quality of repairs of collector-brush assembly drive motor vehicles, including an assessment of mechanical and switching components. The objectives of this study are to determine the linguistic variables based on the generated set of diagnostic features, including "beating of the working surface of the collector", "RMS heights collector lamellae", "amplitude of the first harmonic component of the profile of the collector", "the amplitude of the second harmonic component of the profile of the collector" "RMS heights collector slat excluding the first and second harmonic components", "minimum value of the second derivative of the profile of the collector function", "standard deviation of the second derivative of the profile of the reservoir function," "effective value of the higher harmonic components of the collector profile features" that have the greatest diagnostic value and determination of their membership functions, as well as the definition of the complex index of quality of repair and its components: complex index of quality of machining and integrated commutation quality index in the collector-brush unit of the traction motor. Solution of tasks performed using the mathematical apparatus of fuzzy logic through the use of statistical processing of the results of these pilot studies and the calculation of the diagnostic value of the measured and calculated parameters. As a result of the research formed the mathematical model of quality repair in the space of selected features using the apparatus of fuzzy logic for calculating the value of the proposed integrated indicators for arbitrary values of diagnostic parameters. The results may be used to control the quality of repairs of collector-brush assembly of traction motors of the rolling stock.

Nowadays fuzzy neural networks are widely used for modeling of complex industrial processes. The paper considers the application of fuzzy logic to generate a mathematical model of electricity consumption in rail transport for example, traction substation Dorogino. Algorithm for choice of the structure of fuzzy neural network including the species and number of membership functions for input and the number of training cycles is presented. Comparative analysis of the structures by evaluating the mean square error is made.