{"title":"Improving the Training Quality of Reference Diagnostic Models of Complex Technical Objects by Augmentation of Training Data","authors":"Vladimir Grachev, Mihail Fedotov","doi":"10.20295/2412-9186-2023-9-03-258-273","DOIUrl":"https://doi.org/10.20295/2412-9186-2023-9-03-258-273","url":null,"abstract":"One of the most serious problems limiting the possibility of using intelligent methods of processing diagnostic information in the tasks of diagnosing complex technical objects is the difficulty of forming a training sample for all classes of the state of the object in an amount sufficient for high-quality training of reference diagnostic models or classifiers, due to high absolute reliability indicators of such objects. An effective way to solve the problem is to augment (artificially expand) training data. A feature of training samples in technical diagnostics tasks is the generally unknown type of their distribution in the space of features, while additional \"synthetic\" data should be distributed similarly to the actual training set to ensure high-quality training of the diagnostic model. As a result of the analysis of existing data augmentation methods, it was established that the possibility of determining data distribution parameters of the training sample in the course of training with subsequent reproduction of these parameters in the generated samples can be implemented in generative models based on variational autoencoders (VAE) and generative-adversarial networks (GAN). At the same time, the best results are achieved using GAN. In the tasks of intelligent classification of the state of a diagnostic object with marked training samples for generating additional data, it is preferable to use conditional GAN (CGAN). A serious problem that arises in solving practical problems related to the generation of additional data on the available sample (training sample of a small volume) is the assessment of the uniformity of the training and generated samples, the results of which determine the duration (number of eras) of the training process of the generative model. The paper proposes and substantiates an original method of estimating uniformity of multidimensional samples based on Ripley’s G and F functions used in spatial cluster analysis of point processes. Based on it, a quantitative indicator has been determined for quality control and training duration of the generative model. The efficiency of the proposed method is confirmed by the example of solving the problem of augmentation of training data for the reference diagnostic model of the gas-air path of a diesel locomotive.","PeriodicalId":499166,"journal":{"name":"Автоматика на транспорте","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136192272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Study of the characteristics of error detection with Hamming codes, the consideration of which is appropriate for the synthesis of automatic devices with fault detection","authors":"Dmitriy Efanov, Marina Zueva, Artem Pashukov","doi":"10.20295/2412-9186-2023-9-03-283-297","DOIUrl":"https://doi.org/10.20295/2412-9186-2023-9-03-283-297","url":null,"abstract":"The peculiarities of using Hamming codes in the synthesis of automatic devices with fault detection are investigated. Such devices imply the organization of embedded control schemes to detect occur-ring faults indirectly based on the results of calculating the values of operational functions. Various methods can be used by the implementation of embedded control schemes. In this study, the focus is shifted to the issues of synthesizing embedded control schemes using the method of logical signal correction (the method of logical complementation). This method involves transforming all or part of the signals coming from the diagnostic object in the embedded control scheme in such a way that the code word generated after the signal correction block belongs to a preselected block uniform code. The study considers the application of classical Hamming codes for these purposes. The use of the method of logical signal correction allows obtaining the values of the informational symbols of the code words of the Hamming code directly as values at the operational outputs of the diagnostic object, while the check symbols are obtained by correcting signals from some of the operational out-puts. However, it is also possible to use transformations of operational function values to obtain in-formational symbols, which expands the number of ways to organize the embedded control scheme. The article presents previously unknown absolute and relative error detection metrics in the code words of the Hamming code, taking into account their categorization based on types (according to the number of distortions in zero and one bits) and multiplicities. The experimental results with test combinational circuits confirm the effectiveness of using the method of logical signal correction with computation control using Hamming codes for synthesizing embedded control schemes. The results obtained in this study extend the theory of synthesis for self-checking digital devices and computational systems and can be practically applied in improving the methods for synthesizing au-tomatic devices with fault detection.","PeriodicalId":499166,"journal":{"name":"Автоматика на транспорте","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136192833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Methods of Monitoring the Fulfillment of the Shunt Effect of Track Circuits","authors":"Dmitriy Shvalov","doi":"10.20295/2412-9186-2023-9-03-229-238","DOIUrl":"https://doi.org/10.20295/2412-9186-2023-9-03-229-238","url":null,"abstract":"The value of the transient resistance \"wheel — rail\" is the determining factor for ensuring the shunt ef-fect of track circuits. Taking into account the severity of consequences of failure to ensure the shunt ef-fect — accidents or train derailments due to a switch being thrown under a train or opening of a traffic light fencing an occupied track section, continuous monitoring of the condition of track circuits (shunt sen-sitivity) is necessary for timely detection of critical values of destabilising factors or operating conditions. The article discusses ways to automate measurements of train shunt resistance and ways to prevent shunt loss (non-fulfillment of the shunt effect) by an occupied track circuit. The work also examines the possibility of implementing continuous monitoring of the shunt effect (monitoring of shunt sensitivity) based on a model of changing the values of their parameters during the movement of rolling units along a rail line. The obtained results can be used to solve such analytical and practical problems as: calculation and investigation of the dynamics of change in the sensitivity coefficient of the track circuit to the actual train shunt; construction of a classifier of the track circuit states invariant to external perturbations during the train movement from the moment of entry to the moment of release of the rail line; organisation of continuous monitoring of the shunt sensitivity of the track circuit.","PeriodicalId":499166,"journal":{"name":"Автоматика на транспорте","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136192759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Increasing the Economic Efficiency of Passenger Transport Enterprises by Traffic Modeling","authors":"Valeriy Dyatlov, Andrey Trunaev","doi":"10.20295/2412-9186-2023-9-03-247-257","DOIUrl":"https://doi.org/10.20295/2412-9186-2023-9-03-247-257","url":null,"abstract":"The article addresses the issues related to the possibility of using advanced technologies for real-time management of automotive traffic flows on routes. Modern directions of research in the field of traffic flow management have been analyzed. The article discusses the issues of economic efficiency of passenger enterprises in the context of modern challenges, as well as highlights the peculiarities of monitoring and dispatching processes for automotive transport using the example of the main routes map of Donetsk city. Modeling of the core functions and development mechanisms of passenger transport enterprise management has been carried out. The importance of automated systems and information technologies in ensuring road traffic safety is emphasized. A model for optimizing urban road traffic has been proposed, aiming to address the challenges of increasing the economic stability and efficiency of automotive enterprises, regulating tariffs for municipal passenger transportation, and enhancing road traffic safety. As a result of the study, significant factors for increasing the economic impact of optimizing road traffic on passenger transport routes in urban conditions have been identified.","PeriodicalId":499166,"journal":{"name":"Автоматика на транспорте","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136192763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Leonid Baranov, Anton Anohin, Il'ya Zherebyatin, Yuncyan Chzhan
{"title":"Forecasting Random Processes in Intelligent Transport Systems with Singular Perturbations","authors":"Leonid Baranov, Anton Anohin, Il'ya Zherebyatin, Yuncyan Chzhan","doi":"10.20295/2412-9186-2023-9-03-239-246","DOIUrl":"https://doi.org/10.20295/2412-9186-2023-9-03-239-246","url":null,"abstract":"Forecasting random perturbations allows improving the control quality in intelligent transport systems and ensuring the efficient operation of diagnostic systems. Several works are known where extrapolator models based on Chebyshev polynomials orthogonal on equidistant points are presented. These models use a predictive polynomial whose coefficients are computed using the least squares criterion. Additionally, an analysis of forecast errors for random stationary input signals has been conducted. At the same time, in the case of non-stationary input signals, singular perturbations may occur, the influence of which on the extrapolator leads to significant forecast errors.
 This article presents an example of the occurrence of additive perturbations that arise in automatic train control systems. An analytical expression has been derived, and calculations of forecast error magnitudes in the presence of singular perturbations have been conducted. The analysis of the calculation results allows determining the influence of extrapolator parameters on the forecast error magnitude, highlighting the necessity of detecting singular perturbations, and excluding their influence on the forecast error magnitude.
 The article discusses an algorithm for detecting singular perturbations and their exclusion during the forecasting process. The conclusion is drawn about the effectiveness of using extrapolators for random perturbations with the exclusion of singular perturbations in intelligent systems for automatic train control in subway transportation.","PeriodicalId":499166,"journal":{"name":"Автоматика на транспорте","volume":"228 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136192834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Method for Determining Dynamic Priorities of Cargo Operations for Optimizing the Use of Self-Propelled Units in Railway Industrial Transport and Technological Systems","authors":"Natal'ya Goncharova","doi":"10.20295/2412-9186-2023-9-03-274-282","DOIUrl":"https://doi.org/10.20295/2412-9186-2023-9-03-274-282","url":null,"abstract":"The application of fuzzy logic is considered in optimizing the sequence of operations that involve the use of self-propelled units in industrial railway transportation. The consequences of using constant values calculated analytically as operation priorities have been analyzed. The type of queue discipline and the specifics of constraints on the stay of requests in the queue, characteristic of railway industrial transport and technological systems, are described. The advantages and disadvantages of existing methods for queuing freight operations specified in the daily work plan in railway industrial transport and technological systems are investigated. Limitations arising from the use of classical scheduling theory methods have been identified. Finding the optimal sequence of operations in railway industrial transport and technological systems involves simultaneous movement planning for multiple mobile units, which is not considered in classical graph theory. The classical problem of finding the shortest path and its known solving algorithms only work with static graphs, while railway industrial transport and technological systems are characterized by rapid changes in the graph's state. The problems caused by the dynamic nature of the graph's state in railway industrial transport and technological systems have been analyzed. The application of fuzzy logic methods will enable the construction of an optimal sequence of operations based on incomplete and imprecise information and address several operational planning tasks for freight operations without precise calculations. The expected result of applying the method for determining dynamic operation priorities implemented in the neuro-fuzzy module is an increase in the adaptability of operational planning for freight operations and a reduction in the time of engagement and the required number of self-propelled mobile units.","PeriodicalId":499166,"journal":{"name":"Автоматика на транспорте","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136192423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Analysis of the State of Signaling, Centralization and Blocking Systems Infrastructure in the Murmansk Region of the Oktyabrskaya Railway","authors":"Igor Kushpil, Vladimir Moiseev","doi":"10.20295/2412-9186-2023-9-03-298-306","DOIUrl":"https://doi.org/10.20295/2412-9186-2023-9-03-298-306","url":null,"abstract":": Given the prospects for the future development of interstate transportation in the Northwest region and the positive experience of operating the St. Petersburg — Helsinki line, the article conducts an analysis of the state of signaling, centralization, and blocking systems on the main cross-border railway routes of the Oktyabrskaya Railway. The conducted analysis revealed that there are two most promising cross-border railway sections with direct access to the main railway line and the ports of the Barents and White Seas. From the Finnish side: the section from Alakurtti station to Ruchii Karelskiye station, which can potentially be extended to the nearest Finnish station, Salla (approximately 70-75 km). From the Norwegian side: the section from Nickel-Murmansk station to Kola station, with plans to extend it to the Norwegian station, Kirkenes (approximately 50-60 km). On these sections, there is a need for the modernization of signaling, centralization and blocking systems. Additionally, the article proposes a technical solution for the modernization of these systems, with simultaneous reduction in operational costs for their maintenance. The essence of the solution lies in the utilization of a microprocessor-based centralization system with a distributed control architecture, the principles of coordinate train traffic management, and the application of minimally-manned maintenance technologies for signaling, centralization and blocking devices.","PeriodicalId":499166,"journal":{"name":"Автоматика на транспорте","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136107803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}