Iakov Korovin

A Recovery Method for the Robotic Decentralized Control System with Performance Redundancy

The fault of the robotic control system is critical and leads to the general system failure, while autonomous robots have to gain their aims without any maintenance. Contemporary academic studies propose decentralized control systems as prospective from the robustness point of view. On the other hand, a performance redundancy allows to optimize resource utilization and improve the fault-tolerance potential of the control system. This paper is devoted to the recovery method of the robotic decentralized control system with performance redundancy. A reconfiguration problem has been formalized, decentralized method of the solution obtaining is represented. Also some simulation results are given and discussed.

A novel approach to fault tolerant information and control system design

Design and construction of information and control systems (ICSs) for objects where failure would be critical is an important scientific problem. Such ICSs require both fault tolerance and survivability. Common methods and facilities for addressing fault tolerance do not use the capabilities of modern telecommunications equipment. In this paper, we present an integrated approach that allows to level up the fault-tolerance of an ICS, and requires new methods and algorithms for the reconfiguring procedure. The problem of defining the configuration is formalised, and results of an experimental study of the effectiveness of asynchronous parallel simulated annealing are presented and discussed.

Neuronetwork Decision Support System for Oilfield Equipment Condition Online Monitoring

In this paper we offer the solution of the problem of oil-extracting production efficiency and safety raise by decision support system (DSS) application developed on the artificial neuronetwork technology basis. The description of new database knowledge discovery neuronetwork methods, applied for diagnostics and forecasting is provided. The architecture and the functions of DSS applied for oilfield objects state online monitoring, developed on proposed methods and algorithms basis, is described.

Historic handwritten manuscript binarisation using whale optimisation

Preserving the content of historic handwritten manuscripts is important for a variety of reasons. On the other hand, digital libraries are rapidly expanding and thus facilitate to store this information directly in digital form. For digitising text documents, a crucial step is to binarise the captured images to separate the text from the background. In this paper, we propose an effective approach for binarisation of handwritten Arabic manuscripts which employs a whale optimisation algorithm, incorporating a fuzzy c-means objective function, to obtain optimal thresholds. Experimental results confirm the effectiveness of the proposed approach compared to earlier methods.

Credibility investigation of newsworthy tweets using a visualising Petri net model

Investigating information credibility is an important problem in online social networks such as Twitter. Since misleading information can get easily propagated in Twitter, ranking tweets according to their credibility can help to detect rumors and identify misinformation. In this paper, we propose a Petri net model to visualise tweet credibility in Twitter. We consider the uniform resource locator (URL) as an effective feature in evaluating tweet credibility since it is used to identify the source of tweets, especially for newsworthy tweets. We perform an experimental evaluation on about 1000 tweets, and show that the proposed model is effective for assigning tweets to two classes: credible and incredible tweets, which each class being further divided into two sub-classes (“credible” and “seem credible” and “doubtful” and “incredible” tweets, respectively) based on appropriate features.

Improving Dependability of Reconfigurable Robotic Control System

The robotic information and control systems based on performance redundancy and decentralized dispatching concepts are fault-tolerant and have a high potential in the dependability aspect. The paper deals with a dependability improvement through the configuration forming. As the load balancing improves the reliability function, the quality criteria of system configurations relates to load balancing. Configuration forming is a multicriteria and multiconstraint problem. The proposed approach is to replace monitoring and control tasks relocation criterion by delegating of task context distribution to the software components of the system. The paper contains a new simplified model of the configuration forming problem, the dependability improvement approach and simulation results being discussed briefly.

Modelling of oil spill spread

This paper presents a model of oil spill spread taking into account the evaporation of light, neutral and non-evaporating pseudofractions of oil spots, dissolution of oil spots and biodegradation. An approximation of the diffusion-convection problem is performed based on schemes of high order of accuracy. An experimental implementation, designed to model possible ecosystem scenarios of shallow waters for oil spills in the Azov-Black Sea basin, is presented. Based on a multi-processor architecture, decomposition methods of grid domains have been employed for computationally expensive diffusion-convection tasks in the context of a parallel implementation. The maximum speed-up achieved is by a factor of about 230 based on a configuration of 512 computational nodes.

Application of hybrid data mining methods to increase profitability of heavy oil production

In this paper, we consider the problem of increasing the efficiency of heavy oil production by a qualitative enhanced oil recovery (EOR) application. A novel approach, based on the analysis of data related to successful events, is proposed. In particular, a synthesised model, targeted to automated search of wells for EOR application, is developed. For data processing, we present a novel approach based on a hybrid implementation of neural network analysis techniques and evolutionary algorithms. The presented approach enables the selection of EOR in fuzzy, difficult to formalise, oilfield conditions and consequently reduces the dependency on human factors.

Real-time diagnostics of oil production equipment using data mining

In this paper, we consider the problem of increasing the efficiency of heavy oil production by a qualitative enhanced oil recovery (EOR) application. A novel approach, based on the analysis of data related to successful events is proposed. In particular, a synthesised model, targeted to automated search of wells for EOR application, is developed. For data processing, we present a novel approach based on a hybrid implementation of neural network analysis techniques and evolutionary algorithms. The presented approach enables the selection of EOR in fuzzy, difficult to formalise, oilfield conditions and consequently reduces the dependency on human factors.

Decentralized Approach to Control of Robot Groups During Execution of the Task Flow

The current paper covers the solution of the problem of decentralized control of a network-centric group of heterogeneous robots (robots of various types), that have various functional capabilities, during collective execution of complicated tasks received from consumers in a priori unknown moments of time. Here, the complicated task is the task which requires performance of a certain set of various interconnected operations for its execution. In the paper we describe methods of multi-agent adaptive distribution of operation of complicated tasks between the robots of the network-centric group according to their current condition and functional specialization. The methods are based on interaction of program agents which represent interests of the individual robots of the group during distribution of operations of the incoming tasks.