
The objective of this study is to develop a methodology for controlling the technological process of rail joint welding at rail welding facilities, ensuring the reliability of welded joints. Based on the data obtained from rail welding enterprises, an improved methodology was developed for assessing the stability of the technological process used in the production of welded rail joints, as well as the overall quality level of welding operations at rail welding facilities (RWFs). It has been established that the continuous increase in train weight and speed imposes strict requirements on the quality of rails in operation. The developed methodology makes it possible to identify a key cause of premature rail failure manufacturing defects, particularly welding defects arising during the production of long welded rails, as well as during the repair and welding of used rails.

This paper presents the development and investigation of an intelligent control system for a high-frequency ozone generator integrated into an IoT-based and telecommunication environment. A cyber-physical nonlinear mathematical model combining the electrical, thermal, gas-dynamic, and chemical subsystems of the ozone generation process is proposed. The model was implemented in discrete-time form and experimentally validated using the corona–discharge-based high-frequency ozonator ETRO-02. The deviation between simulation and experimental results did not exceed 5.3% for settling time, 6.7% for overshoot, 1.6% for steady-state ozone concentration, and 0.9% for gas temperature, confirming the adequacy of the proposed model. Based on this model, a hierarchical two-level intelligent control architecture is synthesized, consisting of a fast local control loop with a cycle time of 1–5 ms and a supervisory monitoring layer. The proposed adaptive state-feedback control law with online gain adjustment ensures stable real-time operation under nonlinear dynamics, ±20% parameter variations, network delays of 1–10 ms, and packet loss probabilities of up to 5%. As a result, the settling time is reduced from 420 ms to 160 ms, the overshoot from 12.5% to 3.1%, and the steady-state error from 6.5% to 1.6%, while the specific energy consumption decreases from 11.8 to 6.2 Wh/m3. The obtained results demonstrate that the integration of a cyber-physical model with a millisecond-level intelligent control system significantly improves the dynamic performance, robustness, and energy efficiency of high-frequency ozone generators compared to classical control and monitoring-oriented IoT systems. Unlike cloud-centric IoT monitoring architectures that operate at second-level update cycles, the proposed system closes the control loop locally at the millisecond scale, enabling stabilization of fast nonlinear electro-plasma dynamics. The results demonstrate that edge-intelligent adaptive control significantly enhances both dynamic performance and energy efficiency, confirming the feasibility of millisecond-level cyber-physical regulation for industrial ozone generation systems.

The purpose of this article is to consider the main types of failures of load-bearing parts of traction rolling stock, which have a significant impact on the operational reliability and safety of railway transport. In the bearing components of the mechanical part of locomotives, both gradual and sudden failures may occur. The analysis of the causes of failures, fatigue failures, wear, corrosion damage, and manufacturing defects has been performed. Gradual failures arise due to the accumulation of fatigue damage. The methods of increasing the life of the bearing elements and improving the design are proposed. Sudden failures are defined as those associated with a reduction in the safety margin of long-term (static) or impact strength below the permissible value. According to these studies, the probability of a sudden failure is determined as the probability that the random value of the applied static stress exceeds the random value of some characteristic of the material's strength, σR, which refers to the yield strength or tensile strength, σb. The results of this study can be used in the development of technical measures for the maintenance and repair of locomotives.

The article is a review article devoted to the devices and methods of their use for the experimental study of the stress-strain state of the earth bed of road and railway embankments, approach embankments to bridges, and transport interchanges. Today, an important task in the construction of embankments is the determination of the expected settlement. To measure the stresses in the soil mass of the roadbed, sensors based on strain gauges (Messdozes) are used. The authors consider several types of messdozes according to the ‘classical scheme’, analyze the revealed disadvantages of different designs during laboratory and field tests, and describe the ways of their elimination. The advantages of the modernized scheme of messdozes are described, and the calibration of the modernized sensors (Messdozes) is considered. Modernized sensors have been tested by students of the scientific circle ‘Transport constructions’ under the direction of Associate Professor Bondar I.S. during a series of laboratory experiments carried out on the basis of the testing laboratory ‘Testing of track and artificial constructions’ of ALT University named after Mukhamedjan Tynyshpaev, Almaty.

The purpose of this article is the mathematical modeling of a spring-friction set of a freight car trolley depending on the profile of the railway track. The article uses the methodology of the results of the generalized model of power interaction of friction pairs "pressure beam-friction wedge" and "friction wedge-friction bar" of the spring-friction set of the cart 18-578 in the mechanical system "track-car-load," in a particular case cart from which such models of the e of the freight car 18 100 can be obtained. The manuscript contains a software study using a computer simulation of a freight wagon trolley, which complements the experimental studies. The mathematical (symbolic) method in the computer algebra system MathCAD (a type of computer-aided design system) is used to solve the equations of equilibrium of the supercharger beam as a real object. In the course of the experimental study, a computational mathematical model of the force action of friction pairs of spring-absorbing trolley apparatuses was developed, and the results of calculations of the reaction of the friction bar to the friction wedge were mathematically obtained. The optimal parameters were obtained analytically, and the indicators of the angles of inclination of the contact surfaces of the trolley of the freight car were justified.

The purpose of the article was to present the results of braking equipment testing and determination of the adequacy of compressed air production of the braking system when the train is loaded. Experimental tests of the braking system of TE33A diesel locomotive in a goods train are performed. According to the initial data the main parameters of the braking system in the empty and loaded train were evaluated. As a result of tests, and according to the calculated data, the dependences of the volume of the main reservoirs, and the dependences of the required compressor capacity, on the number of axles have been obtained. It has been established that the braking system operation in release modes for a 400-axle train corresponds to the operating conditions and the main requirements of the normative documents.

The indicators of dynamic qualities that ensure the traffic safety, as well as the permissible impact on the railway track, with the obligatory fulfillment of which the railway rolling stock can be used in the transportation process, are presented in this article. The purpose of this work was to carry out the complex dynamic (running), and the impact on the railway track, tests of the rolling stock, during which simultaneous registration of dynamic processes on the railway rolling stock, and in the elements of the superstructure of the track, is carried out, as well as in elements of turnouts. Dynamic tests were carried out on the track switches from the minimum speed to the maximum possible speed of 50 km/h by the TE33A diesel locomotive during the freight traffic. Meeting the requirement of reproducibility of test conditions and having a typical design of the track structure on wooden or reinforced concrete sleepers.

The paper considers the comparative analyses of machine learning algorithms for dataset: cardio_train.csv from kaggle.com (link: https://www.kaggle.com/sulianova/cardiovascular-disease-dataset).Moreover, using machine learning algo-rithms there will be discovered the best accuracy algorithms for the cardio_train.csv. Considering procedures have done in Python 3.0 programming language, which represents confusion matrix and classification report, in order to see precision score, recall, f1-score, and support. Furthermore, in this paper you are able to see following classification models: KNN algorithm, Logistic Regression, Decision Tree, Random Forest, Naïve Bayes and SVM. As a result, it will be defined the superior accura-cy for processing medical dataset.