Neural network modeling of the efficiency of response to emergency situations in a multi-level control system

2021 ◽  
Vol 92 ◽  
pp. 79-93
Author(s):  
N. G. Topolsky ◽  
◽  
S. Y. Butuzov ◽  
V. Y. Vilisov ◽  
V. L. Semikov ◽  
...  
Keyword(s):  
Neural Network ◽  
Control System ◽  
Control Systems ◽  
Hierarchical Control ◽  
Hierarchical Systems ◽  
Level Control ◽  
Emergency Situations ◽  
Expert Assessments ◽  
Multi Level ◽  
The Relationship

Introduction. It is important to have models that adequately describe the relationship between the integral indicators of the functioning of the system with the particular indicators of the lower levels of management in complex control systems, in particular in RSChS. Traditional approaches based on normative models often turn out to be untenable due to the impossibility of covering all aspects of the functioning of such systems, as well as due to the high variability of the environment and the values of the set of target indicators. Recently, adaptive machine-learning models have proven to be productive, allowing build stable and adequate models, one of the variants of which is artificial neural networks (ANN), based on the solution of inverse problems using expert estimates. The relevance of the study lies in the development of compact models that allow assessing the effectiveness of the functioning of complex multi-level control systems (RSChS) in emergency situations, developing according to complex scenarios, in which emergencies of various types can occur simultaneously. Goals and objectives. The purpose of the article is to build and test the technology for creating compact models that are adequate to the system of indicators of the functioning of hierarchically organized control systems. This goal gives rise to the task of choosing tools for constructing the necessary models and sources of initial data. Methods. The research tools include methods for analyzing hierarchical systems, mathematical statistics, machine learning methods of ANN, simulation modeling, expert assessment methods, software systems for processing statistical data. The research is based on materials from domestic and foreign publications. Results and discussion. The proposed technology for constructing a neural network model of the effectiveness of the functioning of complex hierarchical systems provides a basis for constructing dynamic models of this type, which make it possible to distribute limited financial and other resources during the operation of the system according to a complex scenario of emergency response. Conclusion. The paper presents the results of solving the problem of constructing an ANN and its corresponding nonlinear function, reflecting the relationship between the performance indicators of the lower levels of the hierarchical control system (RSChS) with the upper level. The neural network model constructed in this way can be used in the decision support system for resource management in the context of complex scenarios for the development of emergency situations. The use of expert assessments as an information basis makes it possible to take into account numerous target indicators, which are extremely difficult to take into account in other ways. Keywords: emergency situations, hierarchical control system, efficiency, artificial neural network, expert assessments

scholarly journals Development Prospects of the Software-Hardware Complex of Hierarchical Control Systems

2021 ◽  
pp. 3-9
Author(s):  
Viktor F. Grechaninov ◽  
◽  
Anatoliy V. Lopushansky ◽  
Tetiana K. Ieremenko ◽  
◽  
...  
Keyword(s):  
Control Systems ◽  
Hierarchical Control ◽  
Development Trend ◽  
Management Systems ◽  
Hierarchical Systems ◽  
Current State ◽  
Hardware Complex ◽  
Multi Level ◽  
Hierarchical Management ◽  
The Impact

Introduction. Hierarchical control in complex multilevel systems has been studied since the period of classical cybernetics. At that time, basic definitions and concepts were introduced. It is time to start remembering those achievements because those decisions can already be implemented. However, the situation is constantly changing (evolving), so those tasks are perceived differently today. And the question arises as to how these old developments will progress, whether they will be used? Purpose. The purpose of this work is an attempt to predict the development of hierarchical multilevel control systems in the future and how it depends on the latest technologies that determine their software-hardware complex (SHC). Result. The analysis of the essence of the multilevel hierarchical management system, its features and additional requirements for the software-hardware complex, the current state of hierarchical management systems, the impact of advances in IT technologies and theories on the features of hierarchical management are carried out. The current state is studied on the example of NATO hierarchical systems. Based on the forecasts of the development trend of IT technologies, the forecast of trends in changes in hierarchical multilevel control systems is proposed. Conclusions. As a result of the analysis of the essence of hierarchical multi-level management systems, the current state, and forecast of the development of IT technologies, the authors made the following conclusions: – the hierarchical structure of a complex multi-level system will be in demand in the near future; – Hierarchical systems will consist of standard components with elements of artificial intelligence that controls the components; – the process of creating a hierarchical system will be simplified, so it will be possible to use ready-made solutions.

Digital twin of the chip formation process

2020 ◽  
pp. 81-86
Author(s):  
Yu.G. Kabaldin ◽  
D.A. Shatagin ◽  
M.S. Anosov ◽  
A.M. Kuz'mishina
Keyword(s):  
Neural Network ◽  
Control System ◽  
Crystal Lattice ◽  
Network Model ◽  
Intelligent Control ◽  
Neural Network Model ◽  
Formation Process ◽  
Chip Formation ◽  
Intelligent Control System ◽  
The Relationship

The formation of chips during the processing of various materials was studied. The relationship between the type of chips, the type of crystal lattice of the material and the number of sliding systems is shown. A neural network model of chip formation is developed, which allows predicting the type of chips. An intelligent control system for the process of chip formation during cutting is proposed. Keywords: chip formation, crystal lattice, neural network model, type of chips. [email protected]

Multi-Level Control System for an Intelligent Robot that is Part of a Group

2021 ◽  
Vol 22 (11) ◽  
pp. 610-615
Author(s):  
V. I. Rubtsov ◽  
K. J. Mashkov ◽  
K. V. Konovalov
Keyword(s):  
Control System ◽  
Mobile Robotics ◽  
The State ◽  
Control Mode ◽  
Intelligent Robot ◽  
Level Control ◽  
Level Control System ◽  
Initial Location ◽  
Group Control ◽  
Multi Level

The article is devoted to the application of a group of robotic complexes for military purposes. The current state of control systems of single robotic complexes does not allow solving all the tasks assigned to the robot. The analysis of methods of controlling a group of robots in combat conditions is carried out. The necessity of using a multi-level control system for an intelligent combat robot is justified. A multi-level control system for an intelligent robot is proposed. Such a system assumes the possibility of controlling the robot in one of four modes: remote, supervisory, autonomous and group. Moreover, each robot, depending on the external conditions and its condition, can be in any control mode. The application of the technique is shown by the example of the movement of a group of robots with an interval along the front. The problem of the movement of slave robots behind the leader is considered. When forming the robot control algorithm, the method of finite automata was used. The algorithm controls the movement of the RTK in various operating modes: group control mode and autonomous movement mode. In the group control mode, the task is implemented: movement for the leader. For the state of "Movement in formation", an algorithm for forming the trajectory of the movement of guided robots was implemented. An algorithm for approximating the Bezier curve was used. It allows you to build a trajectory for the slave robot. On the basis of the obtained trajectory, the angular and linear velocity were calculated. In the autonomous control mode, two tasks are solved: moving to a given point and avoiding obstacles. Vector Field Histogram was used as an algorithm for detouring an obstacle, which determines the direction of movement without obstacles. The state of "Movement to a given point" is based on Pure Pursuit as a simple and reliable algorithm for solving such problems. A computer model of the movement of a group of robots was developed. The model is implemented in the MATLAB program using the Simulink and Mobile Robotics Simulation Toolbox libraries. Several different variants of the movement of the RTK group are modeled, which differ from each other in the initial location of the robots and the position of obstacles. The conducted computer simulation showed the efficiency and effectiveness of the proposed method of RTC control.

RETRAN Application of Turbine Trip and Load Rejection of Startup Test Analysis for Lungmen ABWR

2009 ◽  
Author(s):  
Chen-Lin Li ◽  
Chiung-Wen Tsai ◽  
Chunkuan Shih ◽  
Jong-Rong Wang ◽  
Su-Chin Chung
Keyword(s):  
Control System ◽  
Water Level ◽  
Control Systems ◽  
Nuclear Power ◽  
Pressure Control ◽  
Reactor Power ◽  
Level Control ◽  
Bypass Flow ◽  
Control Rod ◽  
Recirculation Flow

This study used RETRAN program to analyze the turbine trip and load rejection transients of Taiwan Power Company Lungmen Nuclear Power Plant’s startup test at 100% power and 100% core flow operating condition. This model includes thermal flow control volumes and junctions, control systems, thermal hydraulic models, safety systems, and 1D kinetics model. In Lungmen RETRAN model, four steam lines are simulated as one line. There are four simulated control systems: pressure control system, water level control system, feedwater control system, and speed control system for reactor internal pumps. The turbine trip event, at above 40% power, triggers the fast open of the bypass valves. Upon the turbine trip, the turbine stop valves close. To minimize steam bypassed to the main condenser, recirculation flow is automatically runback and a SCRRI (selected control rod run in) is initiated to reduce the reactor power. The load rejection event causes the fast opening of the bypass valves. Steam bypass will sufficiently control the pressure, because of their 110% bypass capacity. A SCRRI and RIP runback are also initiated to reduce the reactor power. This study also investigated the sensitivity analysis of turbine bypass flow, runback rate of RIPS and SCRRI to observe how they affect fuel surface heat flux, neutron flux and water level, etc. The results show that turbine bypass flow has larger impacts on dome pressure than RIPS runback rate and SCRRI. This study also indicates that test criteria in turbine trip and load rejection transients are met and Lungmen RETRAN model is performing well and applicable for Lungmen startup test predictions and analyses.

Research on the Relationship between Stabilization Problem and Tracking Problem of Missile Control System

2011 ◽  
Vol 66-68 ◽  
pp. 199-202
Author(s):  
Jun Wei Lei ◽  
Jing Tang ◽  
Hua Li Wu
Keyword(s):  
Control System ◽  
Control Systems ◽  
Tracking Problem ◽  
Stabilization Problem ◽  
Parameter Uncertainties ◽  
The Relationship

The stabilization problem of a system without parameter uncertainties can always be transferred to a tracking problem if it is no need to consider the robustness requirement of a system. But those two questions are not the same for a missile control systems. In this paper, the uncertainties of parameters are considered, and we found that the stabilization problem can not be transferred to a tracking problem.

Hierarchical Control Approach for Autonomous Mobile Robots

1970 ◽  
Vol 110 (4) ◽  
pp. 101-104 ◽  
Author(s):  
T. Proscevicius ◽  
A. Bukis ◽  
V. Raudonis ◽  
M. Eidukeviciute
Keyword(s):  
Neural Networks ◽  
Fuzzy Logic ◽  
Artificial Neural Networks ◽  
Mobile Robots ◽  
Control Systems ◽  
Hierarchical Control ◽  
Autonomous Mobile Robots ◽  
Hierarchical Systems ◽  
Control Approach ◽  
Specific Management

Methods for intelligent mobile robots control which are based on principles of hierarchical control systems will be reviewed in this article. Hierarchical intelligent mobile robots are new direction for development of robotics, which have wide application perspectives. Despite increasing progress in technologies, the main problem of autonomous mobile robots development is that, they are ineffective in their control. In each of the hierarchical control levels (movement in space, problems solving and signal processing sets) will define by specific management of objectives, goals and rules. Communication and management between hierarchies are implemented by higher level of hierarchy using obtained information about the environment and lover level of hierarchy. Studies have shown that artificial neural networks, fuzzy logic are widely used for the development of the hierarchical systems. The main focus of the work is on communications in hierarchy levels, since the robot must be controlled in real time. Ill. 4, bibl. 13 (in English; abstracts in English and Lithuanian).http://dx.doi.org/10.5755/j01.eee.110.4.298

Multi-Level Control Systems

1965 ◽  
Vol 2 (2) ◽  
pp. 252-256 ◽  
Author(s):  
J.D. Pearson
Keyword(s):  
Control Systems ◽  
Level Control ◽  
Multi Level

The Research and Design of Liquid Level Control System Based on Computer Nerve Network

2012 ◽  
Vol 591-593 ◽  
pp. 1629-1632
Author(s):  
Li Zhang ◽  
Jian Hui Wang ◽  
Hou Yao Zhu
Keyword(s):  
Neural Network ◽  
Control System ◽  
Pid Control ◽  
Liquid Level ◽  
Level Control ◽  
Control Effect ◽  
Nerve Network ◽  
Level Control System ◽  
Pid Neural Network ◽  
Liquid Level Control

This thesis mainly elaborated the PID neural network feed-forward algo-rithm and back propagation algorithm and the structure form of its controller, then make use of MATLAB to simulate the liquid level adjusting system, analysis its control perform-ance and choose appropriate neural network parameters, and compared with the traditional PID control effect, analyzes the advantages of PID neural network. Through the comparison with the conventional PID control, PID neural network is superior to the traditional PID. The traditional PID control tuning parameters has a large number of thumb rules for reference, but the setting out of the parameters is not necessarily good. And sometimes we have to modify the parameters if we wound the better control effect. PID neural network is set up as long as the learning step in accordance with the PID rule set. this paper has show that Liquid Level Control System based on Computer Nerve Network has good control effect of rapid and effective.

Sign in / Sign up

Export Citation Format

Share Document