+7 (495) 987 43 74
Join us -              
Рус   |   Eng


Meshalkin V. P.

Dr of Technical Sciences, Professor, International Institute of Logistics, resources and technological innovation MUCTR. DI Mendeleev’s head

Computer-aided system for joint investment funds evaluation using back-propagation neural nets

The authors of the article have developed software that helps analyze and forecast profitability for joint investment funds (JIF) using back-propagation neural nets. The authors presented moving window algorithm for time series construction for neural nets training. The results show that neural nets might be used for correct forecasting of JIF profitability.


Constructing integrated model for risk management of metallurgical enterprise

A method of risk management in the metallurgical enterprise is proposed. Activities specific features are considered and risk management process is decomposed in such a way that every task is mathematically described and allocated to one of the steps originated from the decomposition.


Choosing a supplier in supply chain with a fuzzy logic algorithm

Developed fuzzy-logic algorithm and software and information management decision support system for rational choice of supplier in the supply chain by using the analytic hierarchy process and fuzzy set theory operations. The numerical experiments results confirm the efficiency of the algorithm for making logistics management solutions.

Logical-statistical algorithm for the identification of through pores and its application to the analysis of the nonmaterial structure

Logical and statistical algorithm based on Boolean, morphological and statistical operations to determine through-pore and using micro still images of composite nonmaterial cross sections is presented. Algorithm was applied for micro still images sequence analysis at different section depths of the silicon carbide composite nanomaterial / yttrium aluminum garnet (SiC/Y3Al5O12) sample, obtained by X-ray tomography.

Simulation multiagent fuzzy logic model for industrial companies marketing decision making under uncertainty

The task of creating a tool-making support system of industrial enterprise marketing decisions under uncertainty. It is proposed to use the methodology for multi-agent programming situational modeling functioning of the market as a complex socio-economic system and fuzzy inference procedures for handling uncertain information. We consider examples of situational strategies and making ratio- nal marketing solutions for oil and gas service market.

Heuristic computational tools the integrated logistic support of life cycle of pipeline systems of manufacturing enterprises

It shows the influence of pipeline systems for reliability, cost-performance and industrial security enterprises of the chemical industry and other industries. It shows the role of system maintenance and repair, as well as integrated logistics support in ensuring the capacity for work of industrial piping systems. The drawbacks of maintenance and integrated logistics support using disparate software tools are shown. To eliminate these drawbacks authors offered of the approach to integrated logistic support for the life cycle of pipeline systems of industrial enterprises based on the theory of artificial intelligence, modern methods of mathematical modeling and logistics resource saving in the field organization of production. Developed the following heuristic computational tools computerized integrated logistics support industrial piping systems: logic and information life-cycle model of pipeline systems, which mimics the procedure logistic support of piping systems, as complex organizational and technological decision-making procedures; frame and productional models represent unformalized knowledge about the technical and structural characteristics of the pipeline; heuristic-computing algorithms of calculation of the technical and structural characteristics pipeline systems. Developed heuristic-computing tools allow to automate integrated logistics support life cycle of pipeline systems and to organize the interaction of all its subjects in a single information space.

Information-measuring system geographically remote locations in the gas transport sector

Also in the gas industry introduced information-measuring system of gas distribution point. The system provides data acquisition from geographically distributed points on the following parameters: the gas pressure high or medium pressure at the inlet pipe, flow, pressure and temperature of the gas dispensed to consumers, gassed object, control and emergency operation of unauthorized access to the facility. Based on the results in the thesis organized serial production of a new generation of cabinet distribution points at Novomoskovsk factory of «Elektrotsentrmontazh.» Developed and implemented information-measuring system crane nodes, implemented with regard to the crane in service nodes of the Moscow ring pipeline branch of «Gazpromregiongaz.» Implementation of information-measuring system crane nodes allowed to increase security of supply by the operation status control valve stations, which had previously been tested through periodic inspections and removal of process parameters staff in manual mode. The validity of the use of GSMcommunication due to the distribution valve stations over a large territory and the absence of any other means of communication. In addition, the task was complicated by the fact that most of the valve stations of the Moscow ring gas pipeline network has no power. This required the development of intelligent information-measuring unit with a small power supply and solar powered.

On the 60th anniversary of Yury B. Rubin

The publication is dedicated to the 60th anniversary of professor Yuri B. Rubin, the famous Russian scientist, Rector of Moscow University of Industry and Finance «Synergy» and co-chairman of editorial board of our edition entitled «The Journal of Applied Informatics». Professor Yuri B. Rubin is a Doctor of Economics, Corresponding member of Russian Academy of Education, Rector of Synergy University, Head of Theory and Competition Practice Chair. He is a Winner of the Russian Federation Government Prize in Education, Honorary Worker of Higher Professional Education of the Russian Federation, Member of the International Higher Education Academy of Sciences; Member of Directors Board in the European Foundation for Quality Assurance «E-learning», Honored Worker of the Russian Federation — the Higher School. Yuri B. Rubin was among the initiators of new professions and academic disciplines such as «Applied Informatics» and «Software and administration of information systems». He is a main founder of «The Journal of Applied Informatics» which is published thanks to his support. All his colleagues and the editorial board congratulate Professor Yuri B. Rubin on the 60th anniversary and wish him all the best!

Computer-aided analysis and optimization of structural and parametrical reliability of complex gas supply pipeline systems

The scientific and technical basis of the computer-aided analysis, optimization methods and techniques to ensure the structural and parametrical reliability of energy and resource saving Complex Gas Supply Pipeline Systems (CGSPS) are generalized and developed. The methodology for support and optimizing the performance reliability of CGSPS is presented. Оriginal techniques for engineering and technological failure analysis of facilities and complex gas pipelines, forcasting, reliability diagnostics and troubleshooting the causes of CGSPS are developed. New engineering techniques to ensure the reliability and safety of CGSPS systems are proposed. The technique for construction and practical application of the original topological (graph) models of gas supply pipeline systems reliability is briefly stated. On the basis of these models original methods of reliability factors calculating, including a qualitative analysis method of «the reliability of gas supply pipeline system topology» and decomposition methods of reliability multi-criteria optimization for CGSPS, are developed. Special program complexes for calculation and optimization of reliability, security risk management, integrated logistic support of gas pipelines and facilities of CGSPS, environmental monitoring and CGSPS impact assessment on the environment are developed.

Program complex for life cycle support of pipeline systems of petrochemical companies

The paper presents engineering and technical setting goals, the results of the development and application of heuristic and computing tools and complex programs of integrated logistics support life cycle of pipeline systems petrochemical companies. Shows the role of integrated logistics support as an important factor in ensuring serviceability and reliability of pipeline systems of petrochemical companies. The weaknesses of the existing level of application of information technology that ensure the implementation of integrated logistics support life cycle of pipeline systems of petrochemical companies are given. It is shown that to eliminate disadvantage is possible using software packages, which designed keeping in mind the methodology of system approach and methods of artificial intelligence theory, modern concepts of integrated logistics support and integrated information environment. The results of the systems analysis life cycle of pipeline systems are given. Engineering and technical setting goals of integrated logistics support life cycle of pipeline systems of petrochemical companies are Implemented. Presents a functional and hardware requirements for the complex of programs for implementation of integrated logistics support. the architecture, the computational-network structure, the composition of the database and description of functional modules of software complex programs of integrated logistics support life cycle of pipeline systems of petrochemical companies a «Pipeline» are given. The results of the practical application of the developed complex of programs «Pipeline» on one of the Russian enterprises are given.

Preliminary assessment of the pragmatic value of information in the classifiсation problem based on deep neural networks

A method is proposed for preliminary assessment of the pragmatic value of information in the problem of classifying the state of an object based on deep recurrent networks of long short-term memory. The purpose of the study is to develop a method for predicting the state of a controlled object while minimizing the number of used prognostic parameters through a preliminary assessment of the pragmatic value of information. This is an especially urgent task under conditions of processing big data, characterized not only by significant volumes of incoming information, but also by information rate and multiformatness. The generation of big data is now happening in almost all areas of activity due to the widespread introduction of the Internet of Things in them. The method is implemented by a two-level scheme for processing input information. At the first level, a Random Forest machine learning algorithm is used, which has significantly fewer adjustable parameters than a recurrent neural network used at the second level for the final and more accurate classification of the state of the controlled object or process. The choice of Random Forest is due to its ability to assess the importance of variables in regression and classification problems. This is used in determining the pragmatic value of the input information at the first level of the data processing scheme. For this purpose, a parameter is selected that reflects the specified value in some sense, and based on the ranking of the input variables by the level of importance, they are selected to form training datasets for the recurrent network. The algorithm of the proposed data processing method with a preliminary assessment of the pragmatic value of information is implemented in a program in the MatLAB language, and it has shown its efficiency in an experiment on model data. Read more...