Search

The concept of digital ecosystem (DES) is widely used in autonomous manufacturing process control and the development of complex, stable, interactive, self-organizing and reliable management systems for various industries. The paper offers a concept of DES control system architecture based on predictive models. For estimating and predicting the state of resources in production processes, an approach is developed using data mining based model generation. The paper also reviews the current state of research in the field of DES and their applications in supply chain management (SCM).

This paper is devoted to the development of predictive models for decision support systems applied in precision farming. Application of predictive models makes it possible to use resources effectively, which reduces the cost of production and increases the efficiency of agricultural production. In addition, the forecast makes it possible to reach a long-term agronomic and ecological effect due to more careful tillage and reduced use of fertilizers. The algorithms using knowledge base for creating models of grain yield are described and the results of applying these models are presented.

An approach to the development of a digital ecosystem (DES) using predictive model and data fusion technics is presented with reference to industrial systems. Predictive models are based on data mining algorithms, wavelet analysis and the creation of knowledge bases. Digital identification models are presented, developed as digital twins for the state of DES. In turn, the control of DES is considered as situational control. The modern approach to the development of architecture for DES is proposed.

The paper considers the task of operational management of groupage cargo transportation by road. The organization of groupage cargo transportation in real practice is carried out on the base of a-priori compiled truck flight schedule. The task of operational management is considered as adaptive correction of the cargo transportation schedule according to the current situation

The paper presents an approach to intelligent models development for predicting different parameters of agricultural management. Intelligent predictive models based on knowledge can be built into decision support systems for agricultural producers. Such systems, in turn, allow agricultural producers to make plans and spend their resources more effectively. Based on intelligent analysis of the data, identification models are developed for agricultural commodity price prediction. Modeling results are presented that demonstrate high efficiency of presented approach. Predicted values of agricultural production market price can be used for predicting agricultural enterprise profit and, with using other parameters’ predicted values, could help farmers achieve their business goals more successfully.

The methods for developing predictive models in control systems and decision-making support for nonlinear non-stationary objects are proposed. The methods are based on the application of associative search procedure to virtual model identification as well as Gramian techniques. The associative search methods use intelligent process knowledge analysis. The knowledge base is created and extended in real-time process operation. Intelligent algorithms are offered for predicting power plant dynamics in optimization tasks. Gramian technique of stability analysis for discrete system is used for investigating linear virtual model stability. It is shown that the bilinear Lyapunov equation solutions can be calculated as an infinite sum of the matrix quadratic forms made up by the products of the Faddeev matrices obtained by decomposing of linear subsystem dynamic matrix resolvents.

A conceptual approach to the development of a digital ecosystem using multi-agent technology and predictive models is presented with reference to electric power systems. Predictive models are based on data mining algorithms, wavelet analysis and the formation of knowledge bases.

The paper describes advantages of teaching and application of modelling manufacturing systems. Two paradigms of modelling: Queuing systems and Simulation are briefly presented and analysed. Advantages of distance learning these approaches worldwide are presented. Furthermore, a combined way of learning these two methods, with a focus on the modelling and simulating selected basic processes of manufacturing systems, is proposed in briefly described case study. The concept provides division of this method depending on student’s education level.

The paper offers an approach to the development of a truck sharing management system for a digital ecosystem, which comprises an automobile plant, auto parts suppliers, customers and service centers. The management is based on predictive associative search models. To improve the efficiency of the situational management based on situational awareness, quantum clustering algorithms are used.

The ability to create the project team and manage their knowledge is commonly recognized as one the most important quality of the knowledge and innovative organization. The management of knowledge and skills, as well as the management of project competencies has turned out to be essential factors influencing performance of project process. In the paper, the authors present the method and tools for incentive modelling for project knowledge management. The kind of open distance learning systems is represented that can be used as a model of project learning process aimed at active behavior of students in the project development of not only knowledge, but also acquiring of competencies.

The article studies and develops the methods for assessing the degree of participation of power plants in the general primary frequency control in a unified energy system (UES) of Russia based on time series analysis of frequency and power. To identify the processes under study, methods of associative search are proposed. The methods are based on process knowledgebase development, data mining, associative research, and inductive learning. Real-time identification models generated using these algorithms can be used in automatic control and decision support systems. Evaluation of the behavior of individual UES members enables timely prevention of abnormal and emergency situations. Methods for predictive diagnostics of generating equipment in terms of their readiness to participate in the primary frequency control are also proposed. In view of the non-stationarity of the load in electrical networks, the algorithms have been developed using wavelet analysis. Case studies are given showing the operating of the proposed methods.

Motivation and social aspects as interaction among teachers and students are essential for a competence-based learning process in an Open Distance Learning environment, and the goal in this article is to develop an interactive model to manage motivation between process’ participants. The article contains the concept of developing a motivation model aimed at supporting activity and cooperation of both the students and the teacher. The structure of the motivation model and formal assumptions are presented. The proposed model constitutes the theoretical formalization of the new situation, when a teacher and the students are obligated to elaborate on a didactic material repository content in accordance with the competence requirements. The mathematical method, based on game theory and simulation is suggested. Conditions for using simulation in the model are analysed in two simulated cases.

Approach to the system’s dynamic modeling and decision-making support development for specialist doctors based on intelligent mathematical models is proposed. Based on intelligence analysis of the content of a global database, the system will dynamically generate the inductive knowledge for different aspects of diagnosis and treatment of cancer. The system in essence will model the decision-making process to guide “a human operator”, which in this case is a doctor who consciously or sub-consciously analyses the situation and makes decisions based on his or her professional knowledge and experience. However, even the most skilled doctor is unable to process the information volume of such proportions and do the multiple factor analysis as deep as his or her assistant - an intelligent computerized system, which is able to instantly focus on the specific developing situation while considering all prior history, and produce a model and a prognosis.

The article represents the analysis of using the possibilities of the scenario analysis methods and modelling in the process of solving the planning and management problems of measures to ensure the man-made safety of a wide range of potentially dangerous production and infrastructure facilities. The classification of emergency situations (ES) on potentially dangerous objects is given in terms of the readiness degree of the management system and technical services to eliminate the consequences of emergencies. The main stages and technology of formation of scenarios for the development of man-made disasters and emergencies are considered. The processes of modelling and synthesis of alternative scenarios for the development of ES are proposed to be implemented using the theory of functional sign graphs. An example of practical use of the scenario analysis methodology in the process of solving the problem of management the consequences of emergencies in a land production facility (building) is given.

The paper offers identification algorithms enabling process parameters estimation under limited output samples and time-varying inputs. The algorithms are based on the associative search of analogs and wavelet-analysis of signals. The effectiveness of the techniques proposed is demonstrated with the example of product quality prediction in oil refining industry.

The paper offers an approach to the investigation of the dynamics of nonlinear non-stationary processes with the focus on the risk of dynamic system stability loss. The risk is assessed on the basis of the accumulated knowledge about power supply system operation. New methods for power supply modes analysis are developed and applied as follows: linear discrete point knowledge-based models are developed for nonlinear non-stationary objects, wavelet analysis is used for non-stationary processes, stability loss risks are analyzed through the investigation of spectral decompositions of Gramians of these linear predictive models. Case studies are included.

The paper presents the concept of on-line estimating the state of the Mission Control Center resources and algorithms for forecasting of contingencies. Resource state prediction methods based on the development of a machine learning techniques called association rules are presented. Using this method, the detection of such parameters and their values, the appearance of which, at some point in time, affects the probability of a certain state of the system at another moment in time, and in particular, the occurrence of an emergency. The results of real case studies and specialist interface fragments are presented. System development options are discussed.

A conception of constructing intelligent virtual analyzers as an implementation of the identification approach within control systems is presented, enabling one to develop and adjust prediction models in the most effective manner. Specifically, the paper presents an approach constructing identification models of a submarine by us the associative search applying the technological archives and knowledge base created by use of simulation complexes.

A system identification method using predictive models based on the imitation of analyst's associative thinking is developed. Identification algorithms using associative search for description of the knowledge about control plant are presented. Wavelet analysis is applied for time-varying objects identification.

This paper addresses the concept of developing an intelligent Smart Grids control system. It suggests using the ideology of multi-agent systems and intelligent algorithms for predicting the power plant dynamics in the tasks of optimizing facility operation.

The topicality of the problem of power generating facility identification is justified against the background of European and Russian power grids interconnection. Intelligent control techniques for power generation states is presented. A technology for estimating the dynamics of power grid's generating facilities participation in overall primary frequency regulation in contingencies is developed based on frequency and generating capacity time series. Process identification algorithms based on virtual models design using process data archives and knowledge bases are discussed. Associative search methods are used for identification algorithms development.

IFAC-PapersOnline.net (ISSN 1474-6670); International audience; The paper presents intelligent identification methods for Smart Grid based on Wide Area Measuring Systems (WAMS) technology. The methods are based on intelligent process knowledge analysis. The knowledgebase is created and extended in real-time process operation. Intelligent algorithms are offered for predicting power plants dynamics in the tasks of generating facility’s operation optimization. The operator’s decision-making process is modeled by associative search algorithms.