Introduction. The time interval systems for controlling train movement operated under the influence of significant industrial disturbances, interference from the electric current of traction rolling stocks, and significant climate changes that result in fluctuations of parameters of circuit elements. These factors lead to the appearance of internal disturbances. The fluctuations in a wide range of the conductivity of rail lines insulation are the main external disturbances leading to considerable changes of the informative parameter, the voltage at the output end of the rail line. At present, there are many methods for suppressing disturbances, which allow correcting fluctuations in the informative signal without deteriorating the quality of classification. The article deals with the problem of providing insensitivity of the output informative signal to the influence of disturbance by principles of coordinate compensation with a correcting link. Materials and Methods. To solve the problem, various methodologies of compensation for disturbances are considered in the paper; the method of coordinate compensation for disturbances at the input of a quadripole of rail lines is adopted as the main one. The equation of the transfer function of the correcting link is determined, assuming an indirect measurement of the input resistance of the rail line, which is a function of the conductivity of the insulation. Results. The article presents the results of the research of the invariant capabilities of the disturbance compensation principle. It is shown that disturbances compensation with a corrective link included at the input of a quadripole allows one to significantly reduce the dynamic range of the output informative signal change in each of the classes, i.e. classes have become more compact, and the quality of classification has become 5 times higher than in the absence of compensation of disturbances. Discussion and Conclusion. The results confirm the effectiveness of the proposed method for the coordinate compensation of disturbances in rail lines with an open circuit in the absence of the possibility for organizing feedback, a variable circuit in each of the classes of states, and the impossibility of creating a physical additional channel for the transmission of the disturbance. Using the proposed method in the construction of modern classifiers will significantly improve the stability of the functioning of train control systems; eliminate errors of the first kind, leading to unproductive idle train, and errors of the second kind, leading to accidents and crashes.

Introduction. The necessity to classify the state of rail lines affected by significant damaging factors on the sensitive element of the information sensor providing the assurance of classification quality with the required length of the rail lines of the control section forms the task of creating a classifier with extended functionality. Extending the functionality is possible using multidimensional state images with a set of informative features and training procedures for classification models. Using the classical classification principle with a single model leads to an excessive complication of the classification algorithm with low accuracy due to inaccurate solution of the system of conditional equations with multidimensional approximation by Hermite polynomials. Materials and Methods. The principles of reducing the dimension of the features space, various procedures for trainable classifier of state of rail lines with multidimensional patterns, the selection of decisive classification rules with a hierarchical grouping of classes, and the formation of a set of models of varying degrees of complexity trained to solve an incompatible system of equations are considered to solve the problem. There were obtained various degrees of complexity used in the adaptive algorithm for classifying the rail lines states using Hermite polynomials as models. Results. The article presents the results of developing 57 classifier models using Hermite polynomials with features of 2, 3, 4, 5, 6 arguments. As an example, the procedure of developing models with 2–6 features is shown. The research results showed that with an increase in the number of features, the quality of classification improves, as when dividing the state space into several classes. Discussion and Conclusion. The results of the studies confirm the feasibility of the principle of classification of rail line states by a set of classification models, and an algorithm of recursively increasing the classification complexity using a model of increased complexity. The criterion for presenting a new, more complex model is the mismatch between the results of the class calculation by the i-th model and the real class in which the rail line is located at the moment in time.

The article considers the methodology of forming the matrix of A-parameters of a rail line, represented by a multi-pole equivalent circuit. It is shown that when using a four-pole equivalent circuit of a rail line in case of violation of the equipotentiality of the circuit, it is impossible to take into account the flow of current along bypass paths, along the earth path, and the influence of adjacent track circuits. A multi-pole equivalent circuit of a rail line is represented as a 2x4 pole, in the rail lines of which self-induction EMF sources are included, and an earth path is used as the second wire. An equivalent multi-pole of equivalent circuit is represented by two groups of poles – at the input and output of the rail line, including one common (ground). The parameters of all elements of the equivalent multi-pole circuit are presented in the form of matrices, which makes it possible to analyze the state of the rail lines when changing the primary parameters of the rail multi-pole in a wide range. Using Kirchhoff's laws and solving a system of ordinary differential equations, the A-parameters of a rail multi-pole are obtained.