Series: АВТОМАТИКА И ИНФОРМАТИКА 4, 2022 г.

Key Words: Artificial intelligence; control systems; data-drivenprocess; Decision Making; human-machine interaction; optimization.

Abstract. The work examines the main aspects of the integration of decision making (DM) processes and the control of systems (Control Systems, CS) in modern objects with great complexity and complexity from the perspective of effective application of artificial intelligence methods using data flow. The DM procedure is treated in the light of modern settings and requirements for successful functioning under difficult to overcome conditions such as great uncertainty, scarcity and low quality of data, multicriteria, stochasticity, significant limitations, variability of structures and parameters. Particular attention is paid to the need to increasingly involve machine methods in hybrid Decision Making (DM). The solution of the DM task is treated as an optimization problem that can be solved by different formal, heuristic and hybrid methods depending on the context, existing experience and knowledge, available resources – cost, time, qualification. Special attention is paid to DM and CS approaches in centralized, decentralized and distributed site structures. The wide range of possibilities for the application of technologies based on artificial intelligence and the perspective of their application are indicated.

Повече

Кey Words: Non-frozen wooden prisms; unsteady models; autoclave steaming; energy consumption; energy efficiency; dispatching interference; veneer production.

Abstract. An approach for computing the energy consumption and energy efficiency of autoclaves for intensive steaming of non-frozen wooden prisms at limited heat power of the steam generator in cases of dispatching intervention into the temperature-time parameters of steaming regimes in order to obtain a duration that is suitable for the subsequent cutting of the veneer from the heated plasticized prisms has been presented. The approach is based on the use of two personal mathematical models: 2D non-linear model of the unsteady distribution of the temperature in the cross-section of non-frozen prismatic wood materials subjected to heating at conductive boundary conditions and consequent conditioning in an air environment, and model of the non-stationary thermal balance of autoclaves for steaming wood materials. For numerical solving of the models and practical application of the suggested approach, a software package was prepared in the calculation environment of Visual FORTRAN Professional developed by Microsoft and operating under Windows. Using this package computations and research of the change in the energy consumption and energy efficiency of steaming autoclaves for plasticizing of non-frozen beech prisms before cutting them into veneer have been carried out. The variables used during the simulations were equal, as follows: an initial wood temperature of 0 °C, moisture content of 0.6 kg·kg−1, and cross-section dimensions of the beech prisms 0.4 × 0.4 m; steaming autoclave with inner diameter of 2.4 m, length of its cylindrical part of 9.0 m, and loading level with prisms of 50%; limited heat power of 500 kW of the generator, which feeds the autoclave with saturated water steam. The calculations were carried out for the cases of reducing by the dispatcher the maximum temperature of the basic steaming regime from 130 °C to 120, 110, and 100 °C in the 3rd , 7th , and 11th hour of this regime. The suggested approach can be applied for creation of software for systems used for computing and model-based automatic realization of energy-efficient regimes for autoclave steaming of non-frozen wood materials with desired duration set by the dispatcher.

Повече

Key Words: IDOL; Hadoop; artificial intelligence; big data; analysis, processing; unstructured data.

Abstract. This paper presents at the challenges and prospects of handling and analyzing unstructured big data with artificial intelligence. A huge amount of data like video, text, images, and social content from various applications is created, collected, and accumulated every day in all areas of human activities. This unstructured data cannot be effectively stored, processed, and analyzed using traditional tools and databases. This paper addresses this issue and proposes an approach to help process and subsequently extract knowledge from unstructured data collected from various sources using artificial intelligence. Some of the few existing technological tools for processing unstructured data in a Hadoop environment are presented. As a result of the study, an architecture for such processing and analysis is proposed. It includes a set of technologies that provide a possible solution to the problem.

Повече

Key Words: NoSQL; digitalization; Big Data; financial services.

Abstract. Digital transformation covers different processes and one of the most important industries that has been developing and becoming increasingly digitized in the last years is banking and financial services. For the banks to meet their customers’ demands, needs and expectations it is important to make changes and adapt quickly to the developing technologies. In addition to that, banks need to manage great volumes of data while making changes to their systems without causing data losses and problems for their customers. Financial services provided by banks, credit unions, accountant companies, insurance companies, investment funds, stock brokerages, etc. need databases that can adapt to the increasing need for automation for which NoSQL databases can be very useful. Non-relational databases handle big amounts of data, they are scalable and deliver better performance when processing data. This study presents specifications for NoSQL databases and evaluation approach for non-relational database for financial services.

Повече

На 7 октомври 2022 г. доц. д-р инж. Георги Стоянов Тодоров навърши 75 години.

Той е дългогодишен активен член на Съюза по автоматика и информатика „Джон Атанасов”. Специалист е по компютърни системи и технологии.

Повече