APPLICATION OF ANN IN HUMAN-MACHINE INTERFACES
UDC 004.5, 612.817.2
N.A.Budko, R.Y.Budko, A.Y.Budko
Currently, there are almost no areas of human activity that are not concerned with automation, which has received the greatest popularity over the past few years. To date, the methods that are based on the organization and functioning of biological neural networks have become most famous. The article provides an analytical review of the possibilities of using artificial neural networks (ANN) in the development of human-machine interfaces based on various physical principles of interaction with the human body. This interface provides user interaction with the machines it manages. Examples of the use of human-machine interfaces in household, medical and military areas are given. Efficiency is due to the flexibility, nonlinearity, speed and learning of systems based on neural networks. Thus, users can monitor the process with great precision, achieving the best result. The problems of using ANNs in control systems of technical objects based on the recognition of natural speech, tracking the direction of sight, analysis of the electrical activity of the brain and muscle fibers of a person are considered. The tasks of pre-processing information, classification, analysis of the result obtained by processing the neural network are described.
Keywords: :man-machine interface, artificial neural networks, control, electromyogram, electroencephalogram.
METHODS OF OPTIMIZING ECONOMIC AND SOCIAL SYSTEMS USING TECHNOLOGIES OF MODELING BUSINESS PROCESSES
G.B. Suyunova, N.A. Gaivoronskaya, E.V. Polovinko
This article describes several methodologies and tools that help to simulate business processes in an enterprise in order to make timely management decisions and optimize economic and social systems. The necessity of using various methods of modeling, reorganizing and automating business processes as a means of increasing the efficiency of solving management and decision-making problems in social and economic systems is indicated. It is noted that today the modeling of business processes of the organization is a traditional activity of business analysts of Russian enterprises, which can be a necessary tool for making correct management decisions. It is indicated that there are many different principles of notation. The article also noted that not all notations are equally applicable to the solution of various problems. The eEPC notation used to model business processes in the form of a sequence of events and functions is discussed in more detail, here are its advantages and disadvantages. It is indicated that the tool using the eEPC notation for process modeling is the ArisExpress platform, intended for integrated management of business processes. The article considers two key concepts of the specified modeling environment – these are the concepts of Event and Activity. It is noted that the event always causes the necessity of execution of a concrete action, and the execution of this action always ends with the onset of an event. It is also indicated that in order for the diagram to be more complete and clear, the notation provides for several more standard elements, such as: Role», «Document», «IT system». As a conclusion, it is noted that when constructing these models, it is very simple to make mistakes without knowing the rules by which they are compiled. Such errors lead in the subsequent to the discrepancy of the logic of the process, and as a result – the adoption of incorrect or untimely management decisions.
Keywords: control, decision-making, social system, economic system, notation, optimization, model.
MODEL FOR CONTROL DYNAMIC OBJECTS
S.V. Ippolitov, О.N. Choporov, D.V. Lopatkin, A.V. Sizov
The work is devoted to the solution of the actual scientific and technical problem related to ensuring the required accuracy of control in a group in the automatic mode. The technique for synthesizing an algorithm for automatic control of fast moving dynamic objects in their joint motion based on the theory of covariance control is presented. The essence of the theory is to provide a given steady-state value of the covariance matrix of the state of a linear system by means of feedback. The approach is substantiated and a numerical algorithm for determining the achievable covariance matrix of the system formalizing the specified requirements for the accuracy of control in the group flight mode in terms of the RMS errors of the controlled parameters is developed. The numerical algorithm for solving the synthesis problem of an achievable covariance matrix is based on the method of solving linear matrix inequalities (LMI), using the cvx package of the Matlab system. A general linearized model of the relative motion in the group is developed, taking into account external perturbations of the turbulence of the atmosphere and the random wind and internal disturbances associated with the dynamics of the control system drives. To take into account the influence of a random wind, the Dryden model, which describes the turbulence of the atmosphere, is used. On the basis of the described mathematical model and the developed algorithm, numerical modeling is carried out to evaluate the accuracy of control under the influence of perturbations.
Keywords: dynamic objects, synthesis, algorithm, control, matrix, modeling.
DISTRIBUTED CONTROL SYSTEM OF ISSUANCE OF MEDICAMENT FOR MEDICAL INSTITUTIONS
UDC 004.45-004.932: 004.896
E.S. Sychev, I.A. Scherbatov
Improved management of the distribution of medicines in health facilities is an urgent and difficult task. The article provides the use of hardware and software automation dispensing of drugs and performance of medical prescriptions. The architecture of a distributed control system issuing drugs described prototype robotic machine for dispensing drugs developed communications protocol between the machine and the database, synthesized medicines consumption prediction algorithm. Use of a distributed control system issuing expedient drugs in medical facilities with medium and large number of patients.
Keywords: control, delivery of medicaments, a robotic machine, forecasting.
THE POSSIBILITIES OF USING MODERN AUTOMATED WORKPLACES
The analysis of the properties of modern automated workplaces is given. The history of improving the principles of creating the desired characteristics of automation is considered.
Keywords: automated workplace, function, control.
ABOUT PROCESSES OF OPTIMZATION IN THE INNOVATION ECONOMY
The analysis of factors influencing the development of an innovative economy is given. The characteristics that determine the effectiveness of innovative activities are shown.
Keywords: economy, innovation, control, optimization.
THE FEATURES OF THE KINEMATICS CONTROL OF WHEELED ROBOT
Nasser Hakim Nawras, A.G.Sklyar, D.V.Rusanov
The paper examines characteristics of wheeled robots. Specified tasks arising from non-linear kinematics of the robot are pointed out. If we can solve them it will give opportunities for control on dynamic characteristics of robots. The recommendations are given for improving the performance of the wheeled robot when it go on stairs.
Keywords: : robot, control, model, kinematics, operation, programming.
DEVELOPMENT OF ALGORITMIC AND SOFTWARE CONTROL OF COMPLEX, DISTRIBUTED, AND CLOUD SYSTEMS BASED NEUROPROCESSORS
Reviewed the development of algorithmic and software for controlling the operation of a multiprocessor parallel computer systems, distributed and cloud type on the basis of conceptual new generation computing – neural computers. The reported study was funded by RFBR according to the research project № 14-07-00261 a.
Keywords: : neuroprocessor system, distributed system, cloud system, control, neuroprocessor.