International Scientific Journals
of Scientific Technical Union of Mechanical Engineering "Industry 4.0"

This paper examines the applicability of the neural networks in developing predictive models. A predictive model based on artificial neural networks has been proposed and training has been simulated by applying the Long Short-Term Memory Neural Network module and the time series method. Python programming language to simulate the neural network was used. The model uses the stochastic gradient descent and optimizes the mean square error. Business indicators for forecasting the results of the activity and the risk of bankruptcy of a company are forecasted and a comparison of the obtained forecast values with the actual ones is performed in order to assess the accuracy of the forecast of the developed model. As a result, it can be noted that business indicators can be successfully predicted through the Long Short-Term Memory Neural Network and the forecasted values are close to the actual ones.

Joint research takes its place as a major innovation process. The aim is to build relationships through which to gain access to external sources of high technology (or other assets) and their integration into the products and services of business organizations.
The establishment and operation of Competence Centers in our country, such as QUASAR, plays a leading role in planning, structuring and negotiating these relationships with universities, small high-tech companies, mid-market companies and large companies. The proper development of the business models of the Centers of Competence plays an essential role in this direction
The purpose of this study is to present the impact of business models on two dimensions of joint research: cooperation as an alternative to successful relationships and business models as an effective tool for assessing the portfolio of opportunities and risk allocation.

This article presents a calculation model based on the impact of tourism services and income of hotel enterprises, which have a special share in this service, on the gross product, GDP, labor resources, capital investment and working capital through econometric models. It assesses labor resources, GDP, investment in fixed capital and key indicators for the development of the tourism complex of the Republic of Turkey and provides relevant forecasts. In addition, the statistical significance of the model based on the Eviews software package was checked and its suitability for forecasting purposes was determined.

The hybrid electric vehicles (HEV) are promising vehicles with low exhaust emissions and increased autonomy of movement including internal combustion engine (ICE) and electric motor (EM) which is powered by the battery (B) . The main advantage of HEV over classic cars is the reduced fuel consumption, especially in urban traffic [1]. This is a prerequisite for good energy efficiency of HEV, which is determined by the fuel consumption and consumption, respectively the regeneration of electricity of HEV. These values depend on many factors such as speed, mileage, acceleration, mass, drag, climatic conditions and more. The modelling of the energy efficiency of HEV is related to the study and structuring of the factors that determine the fuel consumption and electricity consumption and the dependencies between them and their connection and construction in a model. The model of energy efficiency of HEV gives a quantitative assessment of the fuel consumption and the consumption (regeneration) of electricity of HEV, according to the main influencing parameters. In addition, the HEV energy efficiency model indicates the influencing parameters and their analytical or experimental determination. The correct modelling of energy efficiency is related to the correct determination of energy parameters and their logical connection in a selected model. The optimal model of energy efficiency of HEV is built from these factors that can be directly measured or calculated, which increases the accuracy and reliability of the results. This article discusses building an energy efficiency model of a hybrid electric vehicle.

In the past years, NATO member countries have faced the threat of bioterrorism, which requires the development of capabilities to deal with this threat. Timely detection and accurate identification of the type of bioagent used is essential for early wa rning of threatened military units, as part of the process of prevention and reduction of human casualties, as well as for the spread of the disease. The possible use of biological agents as weapons of mass destruction (WMD) is presented in the report. The military reconnaissance role in the process of investigation of disease outbreak is considered. For the implementation of the process for early warning and alert of biological threat, a scheme of a model of a platform for biological reconnaissance and monitoring is presented. In the model a configuration of hardware and software is used. Due to the increasing risk of use of biological weapons by terrorist organizations, the acquisition and integration of an advanced platform for monitoring and outbreak reconnaissance from the units of the Armed Forces of the Republic of Bulgaria is of key importance.

The study of the theoretical aspects of the development of innovative business has proved that the most effective form of innovative business, which can create and implement the final product, is a startup. The environment and infrastructure of a startup form its ecosystem. An innovation ecosystem includes economic agents, as well as an innovation environment consisting of ideas, rules of the game, social interactions, and culture. The state of the innovative business and the startup ecosystem of Ukraine behind its main components and institutions are analyzed, and the factors of the development of the startup ecosystem for its competitiveness among the world are determined. Government measures and initiatives should promote the emergence of a community of startup founders who will work closely with other actors in the private sector of the economy and the public sector. At the same time, the state should not assume the role of a leader, but only an initiator.

The aim of the research is to develop a database management system for collecting, processing, storing and using information for the teaching of PhD students at a university using the high-level Python language.
Studied and researched in the process of development are the main characteristics of the most widely used database management systems. The practical aspects of the design, creation and use of databases were analysed. Has been formulated the requirements to the functional capabilities of the developed database. For the development of the web-application was used Python programming language. The database model, the user interface and a set of reports were developed. A physical data model, oriented towards the design and the development of a database management system using the Python programming language was proposed. The main risks and threats to the security of information in the web-application are characterized. Guidelines for infrastructure protection are proposed.

In this paper the physical model for high pressure water atomization of metal melts using hydraulic nozzle of a vortex type was proposed. The developed model assumes, that due to high speed water flow with significant centrifugal component of its velocity vector the rarefaction is formed, which causes intensive air suction leading to the formation of rotating gas (vapor-air) layer of toroid-like shape, providing a gap between the water flow and the metal stream. Thus water stream is separated from the heated surface of metal stream and the formation of particles during crystallization of melt droplets occurs due to surface tension mainly in this vapor-air layer. The cooling of melt droplets in the gas-water leads to the formation of spherical powder particles. The proposed model correlates well with the known experimental data on the production of spherical powders using a vortex-type annular hydraulic nozzle.

In this paper, it was proposed the experimental identification of the mathematical model of the DC motor, coupled with a reaction wheel. It was proposed to approximate the experimental curve with the mathematical model of order 2 inertia, identified by Genetic Algorithm. To estimate the mathematical model of the control object it was proposed to use the Genetic Algorithm method, the results obtained were compared with the Strejc methods and the results obtained using the Process Models module from System Identification Toolbox from MATLAB.

The purpose of the study is the problem of forming a specialist knowledge model. Its relevance is related to the need for an adequate response to strengthening the scientific and technological progress dynamics and the transition to the information interactions economy. The research analyzes the consequences of Russia’s entry into the Bologna Convention on education. According to the principle of institutional autonomy, solution of these problems is the responsibility of universities. The paper shows that the way to solve these problems is to transfer universities to a design and technological type of administration. The most promising form of education project management is the model of information interaction within the framework of active self-developing network expert environments. Integration in the natural intelligence network structure forms a collective strategic subject, which is a tool of a knowledge and action synergy in the interaction process. The paper describes the developed structure of the active self-developing network expert environment when forming a specialist knowledge model. It is proposed to consider the construction of specialist’s knowledge model in the context of corporate knowledge management strategies in organizations to increase competitiveness as the established support systems for organization knowledge lifecycle and specialist’s integral knowledge model are used to integrate strategic corporate tasks with strategic tasks of developing employees’ corporate knowledge. They consider a specialist as an element of a company production system. His purpose is to give a product specified quantitative and qualitative parameters that ensure its competitive advantages. To carry out production activities, a specialist uses a complex of abilities, knowledge and skills that should be considered as models of his production and technological activities. At each moment, this complex should be considered as a subjective model of its production and technological activity. This creates a basis for a university self-development process by involving advanced consumers using network technologies in the innovative process of improving educational services, receiving ideas or content by referring to their creative abilities in exchange for a reward that corresponds to a contribution. The paper proposes a system that provides a direction for finding solutions and ideas, as well as filtering, summarizing information, determining its value and prospects. It is shown that the method of improving the quality of solutions on an educational project is the synthesis of crowdsourcing technologies, network expertise and the methodology of the active systems theory.

The dynamics of the environment in which businesses operate underlines the need for new tools and approaches to management engineering. There has been recently a growing interest in finding comprehensive solutions covering all aspects of the entire business management. Besides, with a more pronounced customer-centred focus of the company, the competition now takes on a brand-new character considering the fact that the rivalry is not between individual companies, but between entire chains of manufacturers and suppliers. The research study focuses on the need for innovative engineering solutions in response to company’s management processes. A network approach has been proposed as an opportunity to implement the reengineering of external processes (Х-engineering). Moreover, such a proposition is strongly substantiated by the fact that modern companies are prone to expand their activities in the (cyber) space, working together in different types of business networks (Businessnetwork-BN).

The simple model of grain and phase boundaries diffusion into polycrystalline solid system with micro grain dimensions is proposed. There are considered different types of diffusion regimes which are realized by definite correlations between volume and grain boundary diffusion lengths and average grain sizes.