Vol 15, No 5 (2014)

In this paper, the authors consider the p-median optimal location problem on a graph (network) which is a popular model for both logistic problems (optimal transportation, telecommunication and other infrastructure elements placement) and problems of cluster analysis, pattern recognition and estimation theory. The aim of the p-median problem on a graph (network) is to find the given number p of vertices of a graph such that the total distance from each vertex to the nearest chosen vertex reaches its minimum. To solve this NP-hard (in general) problem approximately, the authors propose a heuristic algorithm based on ideas of the probability changing method which is a random search method with adaptation. The idea of the proposed algorithm is based on random choosing of vertices in accordance with the given probabilities of choosing each of them. The probabilities for every chosen vertex and its neighborhood alter depending on the value of the objective function (i.e. in accordance with the total distance from each of the vertices to the nearest chosen vertex). For the algorithm for the large-scale p-median problems, a problem of optimal use of computational capacity is important. The effectiveness of the proposed algorithm was proved experimentally on test datasets from the ORLIB (special dataset library for operations research). In addition, the authors illustrate the results for the proposed algorithm combined with a local search procedure for the considered problem. The experiments show that the results of such combination exceed the results of the multiple start of the local search procedure from randomly chosen vertices. In addition, the experiments demonstrate the ability of the proposed algorithm to reach an exact solution for small problems.

We consider the problem of identification and control of stochastic objects with discrete - continuous nature of the process. In this paper, we study more general class of dynamic objects in the future - objects with memory. The characteristic distinguishing feature of these processes is the fact that in the description the difference analogues of differential equations, taken in the classical theory of identification and control, are not used. The similar processes occur in many different kennels control of aerospace technology. For example, when vibration testing spacecraft channel “vibrator-sensor mounted on the spacecraft” can be described by difference equations. In this case, the lack of natural analogy between the equation in continuous time and difference is typical. This feature is the main difference with memory objects from the traditional dynamic processes. It leaves its mark in the modeling and management of such objects, and determines the urgency of the problem. This article discusses theoretical information about nonparametric algorithms of identification and control. Non-parametric model for objects with memory addresses are considered in two embodiments. One of them is closely related with the description of the object as the Duhamel integral. The second way is partial parameterization of the object, that is, to meet the conditions of both parametric and non-parametric uncertainties. The constructing nonparametric algorithms of dual control are based on the idea of A. A. Feldbaum. It states that the input object “on” its inverse counterpart, the language of mathematicians its inverse. Obviously, the description may not be accurate for some reasons, and then the inverse operator can only approximately describe the process in the direction of “exit-entry”. On this basis, both non-parametric models of objects with memory and nonparametric algorithms of dual control are lined up. The learning system of dual control with active accumulation of information is carefully analyzed. The detailed results of the numerical investigation of non-parametric models for multivariate processes with memory, as well as the results of numerical experiments applying the algorithm of nonparametric adaptive dual control are given.

Development and implementation of a multiagent system that designed for texture restoration of image background when deleting objects are examined in the thesis. General problems of photo and video reconstruction and its application are reviewed. The analysis of existing methods for restore gaps in big data arrays is held. Solution by using one of popular method of clustering analysis: special self-organizing neural network is offered. Algorithm of learning Koho- nen map is covered step by step: preparation initial map data, best matching unit choice, shifting adjacent nodes by neighborhood function, determination of training measures, ordering and fine tuning. Adaptation and modification of the Kohonen map algorithm for image restoring is proposed. Algorithms of initialization of map, choice of content of training vectors, best matching unit algorithm, neighborhood functions are highlighted in this paper. Kohonen multimap principle and cooperative solution by using multiagent paradigm is considered. Mutliagent algorithm is expanded by presegmentation step for defining of adjacent areas. Architecture of a multiagent system is developed, behavior of individual agents and communication ways are determined. Multiagent system that allows restoring background pixels of is implemented. Results of series of experiments are presented. Experiments were carried out on the database of images to search for objects of interest (CBIR database). Assessments of efficiency parameters of multimapping are presented. Evaluation of the optimal number of maps for by multimapping is based on a percentage of the original image palette coverage. The accuracy and performance of agent-based mechanism for the subsystems of training and reconstruction are represented. Assessments of accuracy metrics using SSIM, MSE, PSNR and method by pixel-per-pixel comparison are conducted. Performance estimation for various configurations of the multi-system is conducted in order to determine the most effective ones.

We reviewed the use of numerical series to estimate the parameters in the autoregressive model in this paper. A method and the basic procedure for determining the order of autoregressive model and the choice of a numerical series are described. The purpose of this work is the generalization of the obtained results, identifying characteristics of the autoregressive when modeling complex processes and simplified procedures for the selection of parameters is based on the use of numerical series. The basic theoretical and practical results are obtained on the basis of methodology of system analysis, the theory of random processes, information technologies and methods of fundamental and applied mathematics. We compared the method of numerical series with known methods ofparameter estimation in autoregressive models. It is shown the relationship between the autoregressive models and classical mathematical concepts such as the ‘golden section’, ‘Pascal's triangle ’, the Fibonacci numbers and the Tribonacci numbers. Also we gave estimates for autoregressive models for long-term forecasting. It is shown the relationship between the fourth-order autoregressive with the series of the Kvadrobonacci numbers. We summarized the known recommendations on the application of numerical series. These recommendations help to simplify the procedure for selection of numerical series and improve the quality of the model. For short and medium-term forecasts with a constant average it is recommended to use coefficients which are calculated using the Fibonacci and the Tribonacci series. The obtained results will be useful in modeling of complex processes with a time component.

This article is devoted to the problem of identification of nonlinear dynamic systems Wiener class under conditions of incomplete information. It is now widely known parametric identification methods such systems, which often have a discretecontinuous. Normally, when a parametric formulation of the problem identification class of equations describing the dynamic process is known up to a vector of parameters. The next stage is the estimation of parameters from observations of “input-output" process variables. It is important to note that the choice of the parametric model structure of the object is extremely important. Model inaccuracies arising from some errors at the stage of its parametric selection or definition, can not be rectified in the evaluation parameters. This means that the model is in one sense or another, quite rough. In this paper, the linear element model Wiener is not known with an accuracy of parameters, which corresponds to the non-parametric uncertainty. As a non-linear element model is adopted one or other parametric structure. Specifically, we consider the case when the parameter block is represented as a quad and a saturation level. Thus, the problem of identification of objects of a class of stochastic Wiener is seen in partial non-parametric uncertainty. At the first stage model of linear dynamic block is built. To construct a non-parametric model of the last input object must submit the Heaviside function, in this case, the output of the object to within a factor is its transition function. Reconstruction of the weight function is carried out by the observations of transitional methods of nonparametric statistics. To estimate the parameters of non-linear element is necessary to conduct appropriate experiments. We should pay particular attention to the fact that in the identification of nonlinear dynamic system Wiener class, subject only to the control input and output variables. This situation is typical not only in the manufacture of spacecraft, but many of their units and components. Furthermore, these models are useful in creating computer systems of technical diagnostics with vibration testing of spacecraft (SC) on the channel: Vibrate - sensor mounted on the spacecraft. A numerical study of the proposed algorithms, consider the model of the class of Wiener in different conditions (at different levels of noise in the measurement channels, a different sample size and types of input actions). The results of computer studies show efficiency of the proposed algorithms.

Issues related to the design and training of decision trees, are considered in the paper. Problems of decision trees over-fitting are discussed as well as their ability to the generalization. Questions of local search procedures for the adjustment of decision trees are described. An evolutionary approach to the automated design of decision trees is suggested based on a hybridization of the genetic programming and genetic algorithm. Genetic programming fulfills the search of effective structures in the space of decision trees. Genetic programming is searching for effective variant of decision trees functional nodes position and interconnections, i.e. a structure. The tree structure is built with elements of terminal and functional sets of genetic programming. Elements of the functional set are conditions which limited one of input variables and divided original data set into subgroups. Elements of the terminal set are possible decisions which should be made within solving a problem in hand. Genetic algorithm solves the problem of parameters optimization. Each condition within a decision tree has one or more parameters which are coded into binary string. Genetic algorithm seeks parameters which minimize an error of the decision tree on the instances of the training sample. In the article, the framework of the joint execution of genetic programming and genetic algorithm is given and main evolutionary operators are considered. Suggested approach was implemented as a computing system that allows designing binary decision trees with one parameter nodes. Operation windows of the implemented computing system are presented. The problem of diagnosing the severity of injuries of the abdominal cavity with peritonitis has been solved with the use of developed approach. It was demonstrated that the evolutionary techniques based on the hybridization of the genetic programming and the genetic algorithm allow automated designing decision trees with the high ability to generalization which use four times less information comparing to data usually collected in a patient anamnesis.

This article is about the study of infinite groups with different conditions limbs actual problem in group theory. One of such conditions is the condition of saturation of a group specified set of groups. The group G is full of groups of many M, if any finite subset of is contained in a subgroup G isomorphic to some group of M . It is known that an arbitrary periodic group, saturated groups from a variety of groups |l 2(p n)}, where p and n not fixed, is isomorphic to L 2(Q), where Q is a locally - finite field. Additionally, this result has been generalized to the case when the group is saturated with groups from a variety ofgroups {>SL 2 (p n)}. It would be natural to consider the case when periodic group are saturated with groups from a variety of groups |GL 2( p n)} : Let a periodic group G is saturated with many groups {gL 2 (p n)}, where p, n not fixed. Then G - GL 2 (Q) for some locally finite fields Q . Thus, there is a problem of separation in periodic groups of classes of groups in which this hypothesis holds. This hypothesis is proved in the class of locally _ finite groups. One of the classes in which this hypothesis may be true, is the class of groups Shunkov. In this class, this hypothesis was proved for periodic groups Shunkov when the additional constraint is fixed p. Attempt to abandon the fixity conditions led to the need for classification of Sylow 2-subgroups in these groups. In this work, this classification is made. The structure of Sylow 2-subgroups of the group G for the case when is M of the full linear group of degree two over finite fields.

Today, computers are becoming more powerful and interconnected that makes their security one of the most important concerns. Conventional security software requires a lot of human effort to identify and work out threats. This human labor intensive process can be more efficient by applying machine learning algorithms. Artificial neural networks are one of the most widely used data mining techniques here. The highly increasing computing power and technology made possible the use of more complex intelligent architectures, taking advantage of more than one intelligent system in a collaborative way. This is an effective combination of intelligent techniques that outperforms or competes to simple standard intelligent techniques. One of the hybridization forms, the ensemble technique, has been applied in many real world problems. In this paper, artificial neural networks based ensembles are used for solving the computer security problems. We apply the self-configuring genetic programming technique to construct symbolic regression formula that shows how to compute an ensemble decision using the component ANN decisions. The algorithm involves different operations and math functions and uses the models providing the diversity among the ensemble members. Namely, we use neural networks, automatically designed with our GP algorithm, as the ensemble members. The algorithm automatically chooses component ANNs which are important for obtaining an efficient solution and doesn ’t use the others. Performance of the approach is demonstrated with test problems and then applied to two real world problems from the field of computer security - intrusion and spam detection. The proposed approach demonstrates results competitive to known techniques. With the approach developed an end user has no necessity to be an expert in the computational intelligence area but can implement the reliable and effective data mining tool.

The paper describes an active training example selection for a self-configured hybrid evolutionary algorithm for fuzzy rule bases design for classification problems. This method is related to instance selection methods, which allow not only decreasing of required computational recourses, but also increasing the quality of the obtained classifiers. The method changes the probabilities of instances which are selected into the training subsample depending on how good they are classified by the algorithm. After several generations the sample is changed and probabilities are recalculated. Those instances which were not used before and those which were misclassified by the algorithm had higher probabilities of getting into the training sample. The probabilities of instance selection were calculated using a procedure similar to proportional selection in the genetic algorithm. The idea of training instance selection described here was implemented for the fuzzy classifiers forming. This algorithm uses the combination of Pittsburg and Michigan approach for fuzzy rule base design with fixed terms, and the Michigan approach is used together with the mutation operator. The size of the rule base is not fixed, and may change during the algorithm run, and a corresponding class number and the rule weight were calculated heuristically for every rule. Moreover, the algorithm uses an initialization procedure that uses instances from the sample to generate more accurate rules. In the Michigan part the operators of adding rules, deleting rules and replacing rules has been implemented. The creation of new rules could be performed by genetic approach - using the existing rules, and heuristically - using those instances which were misclassified. The efficiency of the algorithm was shown on a set of complex classification problems with several classes, as an efficiency measure the overall accuracy and the average accuracy among classes was used.

The analysis of a design modern current collection devices used in space equipment is presented in the article. The main objective of this work is determination of the constructive methods and receptions that improve the output characteristics of the current collection device, preserving the reliability of functioning of the device throughout all term of active existence of the spacecraft in an orbit. The role of the current collection device in a spaceship power supply system is considered; the basic constructive elements of the device are described; the principles offunctioning of the device are stated. The main output characteristics of the current collection device - value of the voltage drop across the layer of the collector rings and the total power disseminated on the device are defined. The factors affecting described output parameters - change the actual contact area between the collector rings one kinematic contact pairs, the penetration of particles of dielectric material on the contact surface of the collector rings, the formation of non-conductive films. It shows the influence of axial and radial instability clips collector rings on the actual contact area of collector rings one kinematic contact pair, are stated. The reasons for the formation ofparticles of the dielectric material during operation of the device, formation of a film of dielectric material on the contact surface of the collector rings are described. The influence of the total radial bias force on the deformation of the contact rings one kinematic contact pair is considered. The relation between the cyclic loading of the outer collector rings and wave-like change of the moment of rotation of the output shaft of the device is determined. An experiment on the effects offluctuations in the torque of rotation of the output shaft of the device on the value of the voltage drop at the collector rings in a single layer is presented and described. The authors conclude that smoothing the peaks of the twisting moment will provide smoother and stable characteristic changes of the voltage drop across the collector layer of the rings, to reduce the average value of the voltage drop on each layer of the collector rings and, therefore, reduce the total power dissipated on the current collection device. It is suggested to include solutions to achieve axial and radial stability clips of current collector rings in the operation of the device in the future construction of current collection devices.

The effect of residual magnetization of the welded parts on the accuracy positioning of the electron beam along the joint connection is a complicated scientific and technical problem to achieve the high quality of welded joints in the aerospace industry, shipbuilding and power engineering. As a result of analysis of the magnetic fields of residual magnetization the authors obtained the mathematical model of their distribution in the space between the electron beam gun and the workpiece and also the quantitative characteristics of deflection of the electron beam from the joint connection were obtained. For obtaining the mathematical model, the authors use a method which is widely known in the literature. This method is based on the representation of residual magnetization as equivalent field of conductor with current. Comparative evaluation of experimental and calculated data confirms the adequacy of the modeling. The authors have developed a method and a functional diagram of the automatic compensation of the effect of magnetic fields on the accuracy of positioning of the electron beam along the joint connection in the process of electron beam welding. The system of automatic compensation includes a collimated X-ray sensor, which is designed for monitoring deflection of the electron beam from the optical axis of the electron beam gun. The X-ray sensor is placed on the electron beam gun. The collimation slit of X-ray sensor is aimed at the optical axis of the gun. The method of synchronous detection is used to process information from the X-ray sensor. Thus the signals of the first and second harmonics of the scanning frequency of the electron beam across the joint connection are allocated. The method of synchronous detection uses the technological scanning of electron beam across and along the joint connection. The technological scanning allows to provide the measurement of deflection of the electron beam and to expand opportunities to improve weld quality by controlling the distribution of energy in the heating spot. Automatic compensation of the action of magnetic fields of residual magnetization of welded product can reduce the positioning error of the electron beam on the joint connection in the weld root in 20-30 times.

One of the promising materials used in various fields of technology, is titanium and its alloys. This is due to its favorable combination of physical and chemical properties and improved corrosion resistance to the atmospheric conditions. However, in certain corrosive media, especially in the presence of abrasion, titanium and its alloys is the subject to corrosive degradation. The electroplating method used currently to improve the corrosion resistance of metals, has several disadvantages: low ecological safety of the process associated with aggressive electrolytes used, the need for additional operations washing, degreasing, etching, strict observance of the temperature regime during processing. The resulting coatings electroplated not meet the requirements for corrosion resistance in corrosive environments, especially in the presence of abrasive wear. The paper proposes a method for improving the corrosion resistance of titanium and its alloys in corrosive environments, especially in the presence of abrasion, the metal coating on the surface of the protective layer microarc oxidation. The studies of morphology, chemical composition and thickness of the coatings were conducted. These studies have shown that in the MAO coating not only the phase y-TiO 2 is formed, but also the phase a-TiO 2, which is a major contributor to the hardened layer. Hardening of microarc oxidation during metals due to the formation on the surface coating which consists of titanium oxide and oxides of chemical elements contained in the electrolyte composition. Accelerated Laboratory Test corrosion resistance coatings showed that the coatings have MAO higher corrosion resistance as compared to coatings deposited by galvanic anodizing. Samples treated in silicate-alkaline electrolyte have the highest corrosion resistance. Process conditions for applying a corrosion resistant coating on titanium and its alloys are defined.

Due to the need to increase the efficiency of innovation use in the production sector, its innovative growth rates, a modern Russian economy is faced by the problem of the fastest transition to development of an innovative model. This task is particularly acute for Siberian regions having the economy of a raw orientation. Now recession of industrial production in these regions is the most essential that is caused by decreasing in the growth rates of the mining and manufacturing industry focused on low-reefficient processing of the raw materials. Therefore the organization of effective management of economy of such regions has to resolve the issues of transition to technologically balanced structure of production, creation of system of the accelerated introduction of world-class innovative technologies in the resource-extraction and processing industries increasing production efficiency and mineral raw material resources use. As a fundamental conceptual provision of management of innovative modernization of economy, taking into account specifics of the regions of Siberia having a raw focus in article the mechanism ofpreservation and development of resource sector of economy, the hi-tech, knowledge-intensive enterprises is allocated and defined. It is offered to base this mechanism on simultaneous formation from the enterprises of resource and hi-tech sector of system of the production and technological chains interacting and keeping innovative development. These chains have to lay the foundation of a kernel of innovative economy (with emphasis on creation of a kernel of the innovative industry). In this work it is proved that the most important organizational component of the region economy innovative modernization management mechanism which has to be created, the network of innovative interaction (cooperation) is. It represents system of scientific and technical and technological cooperation of the innovative centers of managing of the region and the specialized centers of competences the region which is directed on speed increase of the intellectual capital formation in the region, efficiency of a scientific transfer and technical knowledge in economy.

In current conditions the technological development of industrial complex regions of the Russian Federation is one offundamental factors of national economic growth. Providing continuous updates of technical and technological base and creation of new products and services is only possible with the implementation of innovative development of industry, both at the Federal and regional levels. Management of technological development of industrial complex is a poorly understood field of Russian management. The review of this problem is relevant from the position ofpractices, needed of evidence-based guidelines enables to increase the efficiency potential of industrial enterprises, to accelerate technological development and to ensure competitiveness. In the article the factors which influence the development of industry are selected. The approaches to interpretation of terms ‘industrial complex’ and ‘technological development’ are investigated. The concept of technological development of regional industrial complex is disclosed. The principles offormation the strategy of technological development for regional industrial complex, with special focus on integration in industry and science are formulated. Besides, when setting the strategy for scientific and technological development is especially important, that public will be ready to change and actively support them. The necessity of transition to the principles of best available technologies is justified. Identified principles of industrial and innovative development will expand the scale of creation of high-tech industries in the region.

Management of development of the export potential of the machine building enterprise is the system uniting certain instruments forming the export potential into a unified system and providing the achievement of goals. The main role of management of development of the export potential of the enterprise is the transformation of all available limited resources: labor, information, natural, industrial, infrastructure, etc. into an integral generality able to ensure the implementation of the strategic set goals of the enterprise. Management should form a level of export potential of the machine-building enterprises, so that the interests of owners, investors and company personnel were satisfied. Managing of the development is a systematic application of various tools to ensure the achievement of company strategic objective. There are three standard options of strategic development of enterprise engineering in this article and the authors propose a set of tools that correspond to these strategies. The objects of study are engineering plants which plan to launch their products to the international markets, the subject of the research is the management relations arising in the process offormation and development of the export potential of machine-building enterprises. The theoretical basis of the study is the works of domestic and foreign researchers, reflecting the state and prospects of development of machine-building enterprises and international market of engineering products in general. The methodological basis of the research is scientific methods of research: comparative and statistical analysis, grouping, comparison and synthesis, allowing ensures the validity of the results and findings of the present study. The standard enterprise development strategies to identify key features of the export potential for each strategy have been analyzed. The study proposed to use a variety of management tools export potential enterprises with different development strategies. The value of the export potential of the company characterizes the competitive opportunities of enterprise in the international market. The development of the export potential of the enterprise is based not only on increasing sales of a particular type of product, it is also inextricably linked with the possibility in the near future to enter the markets of other countries.

International financial sanctions imposed against our country in 2014, and outlined the recession put before the Russian economic science, the problem of finding ways of further development of the country. Infrastructure projects, as international experience shows, has always been a powerful tool to stimulate economic growth. For the Russian Federation - the largest country in the world is the greatest relevance transport infrastructure, in which JSC “Russian Railways” play a decisive role. Rail transport, since its inception, has traditionally been a powerful engine of social and economic development of the country. Russian system of taxation of corporations is defined in separate articles of the Tax Code, which makes it difficult to understand the impact of taxes on the financial and economic results of their activities. As statistics show, large corporations are taxpayers, form the basic income of the consolidated federal budget. Individual corporations can be attributed to polysystemic monopolies, including JSC “Russian Railways”. Polysystemic monopolies have a significant multiplier effect for economic growth and development. Consequently, the tax policy in respect thereof shall be taken into account these features. Implemented analysis allows a comprehensive look at tax policy of the Russian state in relation to the largest corporations, which has obviously expressed fiscal nature. In resulting in the withdrawal offinancial resources in central government funds to the detriment of corporate finance. There is a tendency of decrease in investment activity on the part of big business. This applies to both traditional infrastructure and knowledge-based - aerospace. This has led to a significant reduction in the rate of economic growth for the period 2011-2014 year, and in 2015-2016 is expected recession. Worded provisions allow the use offiscal policy for the expanded reproduction through the use of potential polysystemic monopolies. This could have a significant multiplicative effect on the Russian economy, which ultimately will contribute to accelerate the pace of socio-economic development of our country and the growth of tax revenues at all levels of the budget and state funds.

In the economy of Russia the enterprises of defense industry complex, owing to specifics of the realized tasks represent the hi-tech productions with the developed scientific and technical sphere allowing to let out competitive production. The transition processes caused by reforms of national economy at the end of the last century led to increase of the crisis phenomena. Considerable reduction of the state defensive order, folding of the majority of the current and perspective development, violation of structural communications, deterioration of financial and economic indicators of activity of the enterprises, decrease in their production and innovative potential essentially affected economic stability of the enterprises of defense industry complex. At the present stage of development of economy new approaches to management are required: to the forefront there are economic criteria of efficiency, requirements to flexibility of management raise. Development of information technologies and computerization of production force the modern enterprises to turn into more and more difficult systems. New control methods are necessary for ensuring controllability of such systems. Still the most perspective direction in development of new approaches to business management connecting theories of decision-making, information support and organizational modeling there is a controlling. In work the methodical tools of expeditious controlling of production of civil appointment based on use of control cards and use of a method of delimitation of tolerances, supplementing existing a binding to the purposes of activity of the enterprises of defense industry complex and allowing to trace dynamics of changes of controlled indicators and to correct administrative decisions in a common information space are offered.

The article considers the role and features of high-tech industries. Its development requires the significant investments. This is performed by development and implementation of innovative and investment projects. Evaluation of innovative and investment projects requires consideration of many factors, the combination of which will determine the overall efficiency and individual stages of the project. We identified four basic stages of designing and manufacturing science-intensive products, special attention is given to the stage of research and development work. The article considers the main problems of the enterprises in implementation and evaluation of the effectiveness of innovation and investment projects for the production of science-intensive products. Now there is the toughening of consumer demands for quality and cost of the proposed projects. It is necessary to accelerate the process of entering the market with a new product and its successful mastering when developing new projects. New innovative and investment projects require significant financial investments, diverted resources for a long period. Furthermore, it is necessary to carry out justification for the selection inception of the innovative and investment projects by analyzing market readiness for this type of innovation. It is necessary to carry out the following steps for the purpose of the current assess of projects promising: analysis of market conditions, potential and existing competitors, demand for new products and technologies, taking into account the possible potential of the company, its compliance with future challenges, calculation and analysis of the financial results of the project, the financial sustainability of the enterprise.

This article describes the features of Adaptive planning production program of defense industry enterprises in which the central management are planning the assortment policy. The purpose of this study is to support the concept of “Adaptive planning of the production program of the enterprise". As a result of the analysis of kinship terms, identifying key, defined author's position. The definition of Adaptive planning of the production program of enterprise, taking into account the diversity of approaches to understand the concepts and basic principles of planning is proposed. Due to the ambiguity of interpretation principles reflecting enterprise production program planning for Adaptive planning, clarified and supplemented by the principles of planning. These principles are determined by relevance, adaptability, dynamic and uncertain factors of internal and external environment, as well as the need to ensure sustainable development of the enterprise. A qualified content submitted principle involves mandatory uncertainty, continuous adjustment, correction and clarification of the plans, the ability to change its focus in response to unexpected changes of internal and external nature. The pressing challenge of approaches for a reasonable compromise between the costs of the implementation of the planning process and achieved the effect is solved. The directions to reduce the level of uncertainty and corporate planning and commercial and financial stability are shown: the use of more complex approaches and methods, including the theory of decision-making under uncertainty, proposes the introduction of a system ofplanning, responsive to changing economic conditions. With the introduction of Adaptive planning it is proposed to monitor the structure and volume of demand within a timeout period that allows moving the production program to meet changed conditions. The solution to this problem proposed by developing techniques for the planning of the production program of the adaptive enterprise.

Time series prediction is quite complex and interesting problem. Usually a forecast is based on information from the past, i.e. on previous values offeatures. The economic situation in the country depends on different factors and events and influences many situations. The innovation projects in aerospace field require a large amount of investments and take a long time for development and implementation. These kinds of investments require relevant and reliable information about possible future economic situation to minimize risks and correct the plans in right time. In particular, to get such information one may use the time series of the various indexes of economic development. In this paper, the neural network predictors are used as the main technology offorecasting. They are generated automatically by means of genetic algorithms that allow increasing the quality of the prediction. Besides, the advantages of the use of selfconfiguring genetic algorithms in comparison with standard genetic algorithms are demonstrated when adjusting the weighting coefficients of the neural network. The quality of the solution provided by the neural network depends also on its structure. In this paper, the genetic programming is used for the neural network structure design due to its ability to provide effective and flexible models without a human expert. This allows automating the neural network based predictors configuring. The combination of these intellectual information technologies is tested on the financial time series forecasting task using the values of the prices and volumes along with the technical indicators as the inputs. The developed system allows automated designing the neural network based predictors and getting a high quality forecast of economic indexes changes. The developed system shows better results in the comparison with the other forecasting technologies.

The majority of Russian regions has to decide the problems of decreasing the dominance in branch economic structure of the low technological development level in economic process of globalization, resource with based economy and to improve the regions competitiveness based on the innovation economic development. The article deals with systematization factors which have an influence on the economic space quality of the regions with resource based economy and also defines the most significant problems, which prevent from increasing the economic quality in globalization. Also the article describes the types of spatial structures and specifics some regions with resource based economy in Russia. It is shown that the systematization factors have an influence on the economic space on the basic of the features of economic growth. It is reported that defines the role and importance of the intensive factor of economic growth to increasing the production volume from improvement technologies. Moreover, the negative and positive factors are allocated from structure the extensive and intensive factors by author. These factors let to reveal the quality development problems and realize some arrangements for improving the quality economic space on the purpose increasing the competitiveness of technological branch. The paper looks at recent research dealing with macroeconomic indicators per head in 2012 in Krasnoyarsk region in comparison with similar data on Federal Siberian District and Russia at all. According to the author, the criteria of the assessment of economic space quality are selected. It should be noted about new requirements to organization and the quality spatial development of region with resource based economy. The author concentrates on a wide range of things which raise special problems of the analysis risks of regional economic branch; it is necessary to realize the assessment of a technological branch at the regional economic level.