Aim. The migration towards the Industry 4.0 digital technology will soon enable “right first time” (virtually with no material expenditures for experimental testing and subsequent design improvement) creation of increasing numbers of entities with unique application properties. Calculating the dependability indicators of such entities based on reliable statistical data will be greatly challenging. However, the need for dependable entities will remain. Additionally, the approaches to digital technology based on physical models and engineering knowledge enable the creation of predictive dependability methods (based on the assumption of non-acceptability or, contrarily, intentional programming of failures). That inevitably causes a paradigm shift in the modern dependability theory associated with a forced deviation from the mathematical models as the basis of the dependability theory. Methods. According to the Russian tradition, dependability is normally defined by specifying the required functions through a set of parameters that characterize the ability to perform them and the allowable variation limits of the parameter values. If the criteria of some required functions cannot be specified through parameters, a technique can be used, whereas the operation of the item is substituted with an information model in the form of a black box, in which the performance of the required functions is characterized by probabilistic indicators of failures (statistical, logical, Bayesian, subjective). In order to account for the parameters and probabilities of performance of the required functions in a coordinated manner, finding the values of the parameters within the allowed range can be characterized by the probability as the degree of confidence in the occurrence of such event, for example accounting for design reserves. In this case the performance of all the required functions can be characterized by an additive dependability indicator that is identified using the method of dependability structure diagram. This indicator completely characterizes the predicted dependability level. Results. Predicted dependability is estimated using the method of design engineering analysis of dependability (DEAD). This method allows using a set of algorithm-based techniques to present the design (per GOST 2.102) and process control (per GOST 3.1102) documentation for a technical item in the form of a generalized parametric model of operation. Such model allows taking into consideration the individual specificity of the design of entities based on the unity of functionality, operability and dependability, and thereupon estimating the probability of failures. DEAD and digital design algorithms are completely compatible and driven by common problems related to the substantiation of design solutions for the purpose of elimination (reduction of probability) of errors able to cause failures based on analytical, computational and experimental verification. Conclusions. Digital technology provides a tangible opportunity of predicting, reducing the impact or eliminating possible failures. That can be achieved through the same means that often cause failures, i.e. design engineering. For that purpose, it is required to create new applications of the modern dependability theory based on engineering disciplines and design engineering methods developed for ensuring quality and dependability of entities.

Pipeline transportation systems are used for the purpose of delivering to consumers various substances, materials, including those required for continuous flow processes. The operation of such complex industrial facilities is associated with some risks and possible failures of individual units and assemblies due to various causes. The paper examines the specificity of pipeline transportation systems behaviour in emergency situations. The development of such processes may cause the disconnection from the source of some or all end product consumers. The process of damage may occur in accordance with the following mechanisms: progressive damage, when individual pipeline systems fail in a random order; progressive blocking, when individual transportation nodes fail in a random order. An accident scenario, in which progressive damage to linear elements and blocking of transportation nodes simultaneously occur within a system, represents mixed damage. The Aim of this paper is to develop the criteria for estimating a pipeline transportation systems’ resilience to mixed damage, as well as the methods for solving routine problems of synthesis of network structures resilient to such process. Methods of research. The ability of a specific system to resist mixed damage depends on its network structure and is identified by means of simulation. The structural changes caused by mixed damage are described with a cyclogram, whose parameters indicate the number of damaged linear and blocked point elements within one cycle of system exposure. A comparison of the network structures’ ability to resist mixed damage is only possible in case they are comparable. For that purpose, the analyzed systems must have identical numbers of nodes, linear elements, as well as end product consumers. Additionally, such systems must be exposed to mixed damage with identical cyclograms. Results. The simulation of the mixed damage process identified such characteristic as the average percentage of system components, whose failure causes disruption of the connection of all consumers to the source, as well as the average percentage of nodes, whose blocking causes a complete disconnection of the source from all consumers. The developed method of estimation of resilience to mixed damage allows solving the following structural synthesis problems: selection of the position of the source of the end product within the given network; selection of the position of new consumers within an existing system; definition of the locations of additional fragments’ connection to the system; selection of coupling linear elements when additional fragments are connected to a transportation system. Conclusions. Mixed damage is a hazardous development scenario of an emergency situation and is associated with rapid degradation of the transportation capacity of pipeline systems. Various network structures vary in terms of their ability to resist mixed damage, while their resilience characteristics should be identified using computer simulation. A comparison of the mixed damage resilience characteristics is only possible for comparable network structures with equal numbers of nodes, linear elements and end product consumers. Additionally, the same cyclogram of mixed damage must be used.

Aim. The paper continues a series of publications discussing the dependability terminology and its standardization. It aims not to review and discuss specific terms, but rather to formulate the main principles that should be used as the basis for the development of a general terminology standard for dependability in technics. Such consistent general principles will enable easier solutions regarding specific terms and definitions. Methods. The general principles and requirements set out in the regulatory documents on standardization are specified in the context of the dependability terminology standard. The provisions of a number of other general technical standards that have an impact on the standardization of dependability terminology are also taken into account. Current and former terminology standards are considered, both domestic (GOST 13377–67, GOST 13377–75, GOST 27.002–83, GOST 27.002–89, GOST R 27.002–2009 and GOST 27.002–2015) and international (IEC 60050-191:1990 and IEC 60050192:2015). The author analyzed to what extent they comply with the general principles; the shortcomings of the reviewed standards are identified. Findings and conclusions. The main principles that a general dependability terminology standard should conform to are formulated: continuity in relation to previous similar domestic standards, alignment with the international IEC standard, consistency with other general technical standards, internal consistency and logical coherence, generality and universality to meet the needs of all industries.

Aim. Currently, there is a fully-fledged system of Russian dependability standards, the GOST R 27.ххх series. However, due to the suspension of the terminology standard (GOST R 27.002-2009) this system is now incomplete. In this situation, a compromise solution can be found with dual designation in the current dependability standard in Russia. The aim of the paper is to define the proposals for improved basic terminology in dependability. Methods. The paper uses methods of system analysis in respect to dependability terminology. The last decade was marked by active discussions regarding dependability terminology. Not only particular definitions, but the definition of the term “dependability” itself are addressed. The dependability terminology in the Russian Federation is currently represented in two standards: the Russian GOST R 27.002-2009 (suspended indefinitely) and the interstate GOST 27.002-2015. This paper continues the discussion regarding a limited set of concepts and terms that interest the author most. Such concepts as item, entity, failure, property, ability, calculation, estimation, prediction, requirements for dependability are examined. It is noted that the concept of technical entity is based on the product, the study object as a finished result of some technical activity, i.e. to make and at the same time provide the product with the ability to perform certain functions. It is shown that a product’s properties characterize its abilities, therefore, while identifying, the focus should be on the ability of a product provided with properties (features) required for the performance of certain functions. The features (properties) themselves are primary only for the purpose of identification of the entity’s required ability and are secondary for the purpose of dependability identification. It is demonstrated that there is no need to substitute the concepts of “calculation” and “estimation”. The correctness of the definition of “prediction” in the Russian standard GOST R 27.002-2009, i.e. a computational process aimed at predicting the values of quantitative characteristics, is noted. Conclusions. Based on the terminological analysis performed in the paper, the following proposals were developed. Dependability terminology should be complemented with the definition of entity. An entity should be understood as a functional unit provided with abilities defined by the required properties. A failure should be understood as an event consisting in the disruption of the product’s up state. The concept of item should be interpreted as in GOST R 27.001-2009: an item (entity, system) that is considered individually in terms of dependability, that consists of hardware and software or their combinations. The terms of dependability, reliability, durability, etc. should be defined as the identified ability of the product to perform the required function in the given circumstances. The term “requirements for dependability” should be specified in the dependability standards. The term “dependability estimation” should not be introduced in the interstate standard GOST 27.002-2015.

The Aim of the paper is to demonstrate the advantages of taking into consideration real correlations by means of their symmetrization, which is significantly better than completely ignoring real correlations in cases of statistical estimation using small samples. Methods. Instead of real correlation numbers different in sign and modulo, identical values of correlation numbers moduli are used. It is shown that the equivalence of transformation to symmetrization is subject to the condition of identical probabilities of errors of the first and second kind for asymmetrical and equivalent symmetrical correlation matrices. The authors examine the procedure of accurate calculation of equal data correlation coefficients by trial and error and procedure of approximate calculation of symmetrical coefficients by averaging the moduli of real correlation numbers of an asymmetrical matrix. Results. The paper notes a practically linear dependence of equal probabilities of errors of the first and second kind from the dimension of the symmetrized problem being solved under logarithmic scale of the variables taken into consideration. That ultimately allows performing the examined calculations in table form using low-bit, low-power, inexpensive microcontrollers. The examined transformations have a quadratic computational complexity and come down to using pre-constructed 8-bit binary tables that associate the expected probability of errors of the first and second kind with the parameter of equal correlation of data. All the table calculations are correct and do not accumulate input data round-off errors. Conclusions. The now widely practiced complete disregard of the correlations when performing statistical analysis is very detrimental. It would be more correct to replace the matrices of real correlation numbers with symmetrical equivalents. The approximation error caused by simple averaging of the moduli of coefficient of asymmetrical matrices decreases as the square of their dimension or the square of the number of neurons that generalize classical statistical tests. When 16 and more neurons are used, the approximation error becomes negligible and can be disregarded.

Factors affecting the reliability of data transmission in networks with nodes with periodic availability were considered. The principles of data transfer between robots are described; the need for global connectivity of communications within an autonomous system is shown, since the non-availability of information on the intentions of other robots reduces the effectiveness of the robotics system as a whole and affects the fault tolerance of a team of independent actors performing distributed activities. It is shown that the existing solutions to the problem of data exchange based on general-purpose IP networks have drawbacks; therefore, as the basis for organizing autonomous robot networks, we used developments in the domain of topological models of communication systems allowing us to build self-organizing computer networks. The requirements for the designed network for reliable message transfer between autonomous robots are listed, the option of organizing reliable message delivery using overlay networks, which expand the functionality of underlying networks, is selected. An overview of existing popular controlled and non-controlled overlay networks is given; their applicability for communication within a team of autonomous robots is evaluated. The features and specifics of data transfer in a team of autonomous robots are listed. The algorithms and architecture of the overlay self-organizing network were described by means of generally accepted methods of constructing decentralized networks with zero configurations. As a result of the work, general principles of operation of the designed network were proposed, the message structure for the delivery algorithm was described; two independent data streams were created, i.e. service and payload; an algorithm for sending messages between network nodes and an algorithm for collecting and synchronizing the global network status were developed. In order to increase the dependability and fault tolerance of the network, it is proposed to store the global network status at each node. The principles of operation of a distributed storage are described. For the purpose of notification on changes in the global status of the network, it is proposed to use an additional data stream for intra-network service messages. A flood routing algorithm was developed to reduce delays and speed up the synchronization of the global status of a network and consistency maintenance. It is proposed to provide network connectivity using the HELLO protocol to establish and maintain adjacency relations between network nodes. The paper provides examples of adding and removing network nodes, examines possible scalability problems of the developed overlay network and methods for solving them. It confirms the criteria and indicators for achieving the effect of self-organization of nodes in the network. The designed network is compared with existing alternatives. For the developed algorithms, examples of latency estimates in message delivery are given. The theoretical limitations of the overlay network in the presence of intentional and unintentional defects are indicated; an example of restoring the network after a failure is set forth.

The Aim of the paper is to reduce the number of hazardous events on railway tracks by developing a method of prediction of rare hazardous failures based on processing of large amounts of data on each kilometre of track obtained in real time from diagnostics systems. Hazardous failures are rare events; the set of variate values of the number of such events for an individual kilometre of track per year is: [0, 1]. However, for a railway network as a whole the yearly number of such events is in the dozens and efficient management requires the transition from the estimation of the probability of hazardous failure occurrence to the identification of the most probable location of failure. Methods. The problem of identification of rare, but hazardous possible events out of hundreds of thousands of records of non-critical railway track parameter divergences cannot be solved by conventional means of statistical processing. Hazardous events are predicted using the above statistics and artificial intelligence. Big Data and Data Science technology is used. Such technology includes methods of machine learning that enable item classification based on characteristics (features, predicates) and known cases of undesired event occurrence. The application of various algorithms of machine learning is demonstrated using the example of prediction of track superstructure failures using records collected between 2014 and 2019 on the Kuybyshevskaya Railway. Findings and conclusions. The result of facility ranking is the conclusion regarding the location of the most probable hazardous failure of railway track. That conclusion is based on the correspondence analysis between the actual characteristics of an item and conditions of its operation and the cases of adverse events and cases of their non-occurrence. The practical value of this paper consists in the fact that the proposed set of methods and means can be considered as an integral part of the track maintenance decision-making system. It can be easily adapted for online operation and integrated into the automated measurement system installed on a vehicle.

Aim. The state of the art of railway computer-based control, command and signalling (CCS) systems is characterized by high requirements in terms of dependability, functional safety and cybersecurity under the conditions when digital transformation and challenges associated with the demand for increased competitiveness of railway transportation force the transition to new paradigms in engineering, testing, verification, validation and standardisation to facilitate and speed up the process of development and implementation. It is expected that while preserving the level of dependability and safety, at least, as it is, the industry has to enable the maximum possible introduction of innovative solutions and digital tools aimed at further automation of CCS systems to enhance the capacity and throughput of railways and the performance of systems, to minimize the impact of the human factor and reduce the number of failures and downtimes. In this context, the key factors are the interoperability (technical and operational compatibility) of systems and the technological independence of railway operators and infrastructure managers from the designer/supplier of railway automation systems, eliminating the vendor lock-in effect. Methods. The paper gives an overview of the state of the art of railway computer-based control, command and signalling using the example of the EU and provides an analysis of these systems in terms of dependability and safety in the context of migration to new grades of automation. Results. The author has considered the evolution of control, command and signalling systems in the EU using the example of the European Railway Traffic Management System (ERTMS). The analysis covered the general trends and approaches to engineering, testing, verification, validation and standardisation of railway CCS systems. The paper has overviewed the major EU research and design programmes of CCS development with the dependability and safety methodology taken into account. A special attention has been given to the methods of open engineering, remote lab testing and standardisation of ERTMS interfaces. Conclusions. In the context of digital transformation, the development of state-of-the-art railway computer-based CCS systems implies an accelerated introduction of a whole range of innovative solutions and a wide application of commercial off-the-shelf components (COTS), thus making systems more complex and being capable of affecting the dependability parameters. In order to maintain these parameters at a specified level and to minimize the impact of human factors, the railway community is increasingly using formal methods and automated means of engineering, diagnostics and monitoring at all stages of the system’s lifecycle. A major factor of dependability is the standardisation of the system’s architecture, interfaces, open source design and testing software, including the standardisation of approaches to remote lab testing of products by different manufacturers to prove the reliability of operation at the boundaries of systems of various manufacturers.