Skip to main content

About this book

This book presents new findings on cyber-physical systems design and modelling approaches based on AI and data-driven techniques, identifying the key industrial challenges and the main features of design and modelling processes. To enhance the efficiency of the design process, it proposes new approaches based on the concept of digital twins. Further, it substantiates the scientific, practical, and methodological approaches to modelling and simulating of cyber-physical systems. Exploring digital twins of cyber-physical systems as well as of production systems, it proposes combining both mathematical models and data processing techniques as advanced methods for cyber-physical system design and modelling. Moreover, it presents the implementation of the developed prototypes, including testing in real industries, which have collected and analyzed big data and proved their effectiveness. The book is intended for practitioners, enterprise representatives, scientists, and Ph.D. and master’s students interested in the research and applications of cyber-physical systems in different domains.

Table of Contents


Cyber-Physical Systems Design


Flow Analysis and Its Applications for Equipment Design

An approach based on flow analysis of matter, energy and information is discussed. The cognitive approach matter-energy-information allows to analyze complex systems in different modes, including dynamic situations. It is shown that flow diagrams are universal, common to many complex technical systems including electronic equipment design and technologies, communication systems, and etc. Restrictions of the proposed method is discussed. It is remarkable that visual analytics of dynamic process is available using weighted directed graphs. Based on the available experience, a classification of the concepts of flow analysis of systems is proposed. The chapter discusses flow analysis practical applications. Finally, conclusions are derived.
Vadim Shakhnov, Elena Rezchikova, Lyudmila Zinchenko, Natalia Sergeeva

Cyber-Physical Control System of Hardware-Software Complex of Anthropomorphous Robot: Architecture and Models

Autonomous anthropomorphous robots represent complicated hardware-software complexes designed to functioning in a changing external environment. Additional features of any particular robot are defined by its scope. Educational activity imposes tight restrictions to ensure safe work and study environment at an institution. It is required to solve many different tasks in a real-time mode. The efficiency of their solutions is defined by availability of computing resources, as well as by thorough organization of the hardware-software complex oriented toward a specialized class of the autonomous robotics tasks. With this goal in mind, we analyzed the complex of the tasks for the teaching assistant robot. Among those, one of the most important was the task of obtaining information about the environment. We analyzed the task of a trainee status examination and possible ways of its solution, and offered the architecture of a hardware-software complex of the anthropomorphous robot assistant. The set-theoretic model of a hardware-software complex was constructed. Its use would further allow defining an optimum configuration of the offered hardware-software complex architecture for anthropomorphous robots. The distributed computing system of a hardware-software complex for anthropomorphous robot assistant facilitated parallel solving of the tasks related to situation analysis, as well as planning and control of the robot operations.
Mikhail Stepanov, Vyacheslav Musatov, Igor Egorov, Svetlana Pchelintzeva, Andrey Stepanov

Method of the Exoskeleton Assembly Synthesis on the Base of Anthropometric Characteristics Analysis

The article describes the synthesis module of design solutions for passive and active exoskeletons, taking into account the anthropometric parameters of the operator, the requirements and limitations imposed on the exoskeleton. Exoskeletons, presented on the market of their functional-parametric structure and technical characteristics, are investigated. The method of generating design solutions is considered by the example of an exoskeleton. An algorithm has been developed for the operator upper and lower extremities exoskeleton assembly synthesis, taking into account the anthropometric characteristics, requirements, and limitations of the exoskeleton, and also developed a system prototype for generating the assembly of the exoskeleton with regard to the anthropometric characteristics. The system for generating assemblies of different types of exoskeletons makes it easy to adapt to emerging markets and select the most suitable model taking into account various parameters.
Anna Matokhina, Stanislav Dragunov, Svetlana Popova, Alla G. Kravets

Using Special Text Points in the Recognition of Documents

The chapter develops the concept of a textual key point, the detector of which is a certain OCR. The descriptor of a textual key point is determined. Examples of algorithms for analyzing documents, using textual key points, are given. The chapter deals with the tasks of recognized document classification, localization of images of recognized documents and comparison of images of documents for finding differences. The results of the algorithms for the data sets of the documents of the Russian Federation are given. The proposed methods allow achieving high accuracy of complexly structured documents analysis with entering document images in modern cyber-physical systems based on big data technologies.
Oleg A. Slavin

Extraction of Cyber-Physical Systems Inventions’ Structural Elements of Russian-Language Patents

The chapter presents software for extracting predicate-argument constructions that characterizing the composition of the structural elements of the inventions from cyber-physics domain and the relationships between them. The extracted structures reconstruct the component structure of the invention in the form of a net. Such data is further converted into a domain ontology and used in the field of information support of automated invention. A new method for extracting structured data from patents has been proposed taking into account the specificity of the text of patents and is based on the shallow parsing and segmentation of sentences. The ontology scheme includes the structural elements of technical objects as the concepts and the relationship between them, as well as supporting information on the invention. The results suggest that the proposed approach is promising. A further direction of research is seen by the authors in improving the existing method for extracting data and expanding ontology.
Sergey S. Vasiliev, Dmitriy M. Korobkin, Alla G. Kravets, Sergey A. Fomenkov, Sergey G. Kolesnikov

Conceptual Approach to Designing Efficient Cyber-Physical Systems in the Presence of Uncertainty

Cyber-physical systems are one of the most advanced areas of research technology. However, being distributed systems with a large number of interconnected elements, they often pose a challenge for their designers concerning intra-network control and interaction. The chapter suggests a way to present a cyber-physical system as a multicommodity network model that demonstrates the dual character of connections between the elements of the system. The efficiency of such systems is studied regarding their ability to fulfill the requirements of their elements in the presence of uncertainty. Using the concept of the difficulty of achieving the goal, the authors developed an algorithm for analyzing the efficiency of the multicommodity network. The algorithm can be used to assess the efficiency of the system functioning in different conditions with different parameters. The suggested tools help to determine the most efficient version of the system, which can eventually broaden the scope of application domains of such systems.
A. P. Alekseev

About Preparation of the Analytical Platform for Creation of a Cyber-Physical System of Industrial Mixture of Loose Components

The results of the preparation of an analytical platform for building a cyber-physical system (CPS) for industrial mixing of bulk components in a gravitational apparatus with additional mixing elements are presented. The latter includes rotating drums with brushes and inclined fender planes. To perform an analysis of the efficiency of the process of mixing bulk materials with different physical and mechanical properties in rarefied flows, the author’s models are used. The above elements of the analytical platform for CPS contribute to the development of engineering methods for calculating gravity-type mixing equipment.
A. B. Kapranova, I. I. Verloka, D. D. Bahaeva

Development of an Automated System for Monitoring and Diagnostics a Guided Robotic Vehicle

This research considers the development of an automated system for monitoring and diagnostics of a controlled robotic vehicle. This system is based on an algorithmic approach performed by creating models in the form of fuzzy behavior charts. A key feature is the ability to represent a continuous change in time as a set of modes. While decomposing the diagnostics object (a robotic vehicle), there were created models of its main nodes in the form of fuzzy behavior charts of the second rank. For the diagnostics of the selected nodes, there were considered all possible faults, which also was compared with those ones that can be traced using the created models. Based on the tables of possible malfunctions of the electric motor, the battery, and the infrared proximity sensor, there was obtained a list of malfunctions and abnormal situations that can be organized in the knowledge base structure. Analysis of fault tables allowed developing the structure of an automated system for monitoring and diagnostics of abnormal and emergency situations. The obtained results (models and algorithms) were used to create a software product.
Alexander Bazhanov, Roman Vashchenko, Vasily Rubanov, Olga Bazhanova

About Formation of Elements of a Cyber-Physical System for Efficient Throttling of Fluid in an Axial Valve

An example of the calculation of an axial valve separator, as one of the stages of the formation of elements of a cyber-physical system designed for the effective throttling of a fluid, is performed. The engineering methodology of the authors for calculating the design parameters of the axial valve with the external location of the locking part was chosen as the basis. When obtaining the results, the author’s models are used that describe hydrodynamic cavitation at its initial stage in a separator of an axial valve.
A. B. Kapranova, A. E. Lebedev, A. M. Melzer, S. V. Neklyudov

A Study of a Trajectory Synthesis Method for a Cyclic Changeable Target in an Environment with Periodic Dynamics of Properties

Trajectory planning in a large dynamic environment is a computationally complex cyber-physical task. The chapter considers an environment with periodic dynamics that simulates the rhythm of the day and night. Robots move between two target points cyclically. To optimize the trajectory planning process, it is possible to use pre-calculated paths. The pre-calculated state space consists of the planned paths for environmental states that can be considered static for a given period of time. The planning of robot movement in such the state space is carried out using parts of the pre-calculated optimal trajectories for a certain time and criteria for the transition between them. The method and criteria are studied by simulating the robot movement on two fundamentally different realistic maps. The method allows to plan the trajectories asynchronously with the time of the beginning of the movement of the robot, as well as to estimate the energy costs of overcoming the route.
Dmitrii Motorin, Serge Popov, Vadim Glazunov, Mikhail Chuvatov

Cyber-Physical Systems Modeling


Intellectualization Methods of Population Algorithms of Global Optimization

We consider constrained global optimization algorithms that are adaptive (self-adaptive) to the optimization problem being solved. We set tasks of parametric, structural and structural-parametric adaptation of these algorithms. We present the following methods for synthesis of adaptive algorithms for global optimization: tuning methods; control methods; self-control methods. We give some examples of adaptive algorithms and the results of research of their efficiency.
Anatoly Karpenko, Taleh Agasiev, Maksim Sakharov

Development of Models and Algorithms for Intellectual Support of Life Cycle of Chemical Production Equipment

The article gives the statement of tasks necessary for automation of processes of adoption of intellectual decisions on the integrated logistic support of chemical production equipment, the solution of which is aimed at creating a cyber-physical system of the life cycle of the equipment. An example of formalization of this equipment life cycle with the help of functional modeling methods is given. There are given the models of knowledge representation about the equipment in a form of frames, and also—the processes of adoption of intellectual decisions on integrated logistic support of the equipment in a form of production rules. A heuristic-computational algorithm that allows automating the determination of classification characteristics of the equipment according to the degree of danger of the working substance is presented.
Evgenii Moshev, Valeriy Meshalkin, Makar Romashkin

Simulation of the Multialternativity Attribute in the Processes of Adaptive Evolution

This article is devoted to the expansion of the ideas of evolutionary cybernetics to the problems of cyber-physical systems design. The main objective of such design is to reproduce the ability of an adaptive evolution that is proper to biological systems in the cyber-physical systems. This ability specific to biologic systems provides their sustainable development in a wide range of criteria of their functioning. More and more, the principle of variety of the processes running simultaneously in a complex system becomes the principal mechanism of realization of adaptive evolution. Mathematical representation and the analysis are made of this mechanism of variety in biological structures of various level of complexity. For pre-biological structures, the evolutionary value of multialternativity is explained in the processes of their streamlining and self-copying. Evolutionary models of the elementary macromolecules–quasitypes and the model of a syser with linked matrixes are investigated. It is shown below that the emergence and stable existence of pre-biological structures are possible as a result of a variety of the results of copying providing the cross mutational streams as well as the general evolutionary progress of population in general. As a model of the population evolution, its formal representation is offered as the discrete uniform Markov’s process altering its state under the influence of complementary streams of events in the external environment and accumulation of a gene pool. For a vector of probabilities of these states the differential equation of Kolmogorov was composed hence, its solution gave the chance to obtain a quantitative assessment of a genetic variety’s role as an emergency condition of either the evolution of biological population or its degeneration. The conclusion is made about the significance of the property of multialternativity as the mechanism of realization of the general cybernetic principles of creation the cyber-physical systems.
Semen Podvalny, Eugeny Vasiljev

Regularization Methods for the Stable Identification of Probabilistic Characteristics of Stochastic Structures

This chapter covers the method of experimental data analysis and processing in cyber-physical systems for medical monitoring, control of manufacturing processes and management of industrial facilities. The suggested methods are used to develop mathematical models of dynamic systems with stochastic properties for managing complex structural subsystems of cyber-physical systems. The most important computational stage of the simulation is thereat the identification of multimodal (in general) densities of the random variable distribution. A matrix conditioning analysis is herein suggested with minimizing relevant functionals of the identification problem. For the method of identifying multimodal densities of random variable distribution a matrix condition analysis is suggested with minimizing the relevant functionals of the problem. It is shown that under ill-conditioning of the equivalent system of equations an algorithm for regularization of solutions is needed. The regularization of the basic method for identifying distribution densities based on the ridge regression-algorithm (RRA) is proposed and substantiated. The classical RRA is improved and modified for local regularization showing the advantage of the high-order unstable SLAEs over the classical Tikhonov method. The suggested regularization algorithms and programs are universal, applicable to the study of random structures in natural science, biomedicine, and computational mathematics.
Vladimir Kulikov, Alexander Kulikov

Outlier Detection in Predictive Analytics for Energy Equipment

The method of data preprocessing used to predict the technical condition of power equipment is described. Preprocessing implemented using neural networks allows us to identify and eliminate outliers in the investigated data. An example illustrating the proposed method of processing big data using bagged trees algorithm, support vector machines and artificial neural networks is shown.
Alexander Andryushin, Ivan Shcherbatov, Nina Dolbikova, Anna Kuznetsova, Grigory Tsurikov

Ontology-Based Model of User Activity Data for Cyber-Physical Systems

The chapter focuses on the issue of modeling of user interaction with the graphical interface of cyber-physical systems. The primary subject of the presented study is users activity data, that is the user’s actions with system graphical interface and their characteristics. This data is collected during the process of software testing or experimental operation. An overview of existing ontologies of domain «Information Systems Graphic Interface» is given. We propose an open model of user activity data in the form of ontology based on the OWL 2 DL language. The main classes, properties, and axioms of this model are covered in the report. This model differs from the other existing ontologies in that it is focused on user activity data rather than the interface and its elements. In addition, it is based on description logic SHOIQ (D), which makes it possible to draw logical conclusions in the process of analysis by experts of the system usability. We also present the structure of software developed for user activity data collection which allows filling the ontology with specific data on the user experience with the interface. As an example, we describe possible tasks where the model and collected data can be used.
Tatiana Shulga, Alexander Sytnik, Nikita Danilov, Denis Palashevskii

Selection of Components of a Composite Material Under Fuzzy Information Conditions

The task of selecting components of a composite material from an indefinite set in the system “polymer matrix + filler + ingredients” is considered. The initial information is fuzzy, therefore the formalization of the initial data and further analysis were carried out using fuzzy numbers. At the first stage, a parametric space is formed, describing the composite material as a multicomponent physical system. Then, the index of compliance of each system parameter with the specified physicomechanical requirements was calculated, which made it possible to go over to the relative dimensionless real values characterizing each component of the composite material. The standard weighted voting procedure was used as an aggregate function. The obtained numerical values reflect an integral measure of the conformity of the ingredient as a component of the designed composite material. The results of theoretical analysis expand and complement the mathematic support of profiled intelligent decision support systems in the scientific and technical activities of the constructor and technologist when modeling technical objects in conditions of uncertainties, including linguistic ones. The chapter provides a general and particular solution.
I. V. Germashev, M. A. Kharitonov, E. V. Derbisher, V. E. Derbisher

Big Data Analysis in Film Production

The article analyzes the current trends of digitalization for large innovative industrial production, which are international, large-capacity, distributed in different geographical locations and having several production lines at each plant. Such trends of digitalization as predictive analytics and 6 sigma methodology, which includes Ishikawa diagram and DMAIC (definition, measure, analysis, improvement, control) cycle, are considered. The novelty of the work lies in the application of methods and technologies of intellectual analysis of large industrial data for production of polymeric films and in the application of mathematical models that allow online calculation of uncontrolled consumer characteristics of products (thickness, color of polymeric films) and integrate them into one single system of data mining. Developed software solution includes visualization unit, forecast unit, statistical data analysis unit. Software solution allows us: determine the types of films with the best yield; check the production data for normalcy; calculate process capability index; calculate key performance indicators. Application and testing of the big data analysis system on the example of large industrial Corporation Kloeckner Pentaplast proved its efficiency.
T. B. Chistyakova, F. Kleinert, M. A. Teterin

Algorithm for Calculating the Reliability of Chemical-Engineering Systems Using the Logical-and-Probabilistic Method in MATLAB

An algorithm for calculating the reliability using the logical-and-probabilistic method was developed in the MATLAB software package. An algorithm is applicable for inclusion in the module of a cyber-physical system for design and optimization of the chemical-engineering systems reliability. The accuracy of the algorithm was checked for systems of varying complexity with number of elements from 5 to 10. An example of program calculations is also presented. Using the developed algorithm, the reliability of the hydrotreating unit of a catalytic reforming unit under uncertainty was calculated.
Anastasiya Zakharova, Tatiana Savitskaya, Alexander Egorov

Cyber-Physical Systems and Digital Twins


Assessment of the State of Production System Components for Digital Twins Technology

The problem of assessment of the state of production systems is considered. The chapter is suggested applying the technology of digital twins to solve the problem of diagnosing and predicting the state of the components of the production system. The hierarchical structure of modern production is described, as well as the interaction of the production system and its digital twin. The correspondence of the system components and models of their state assessment is indicated. Methods and tools for assessing the state of the components of different hierarchical levels of the production system representation are proposed. As an example, the assessment of the state of stamp-tool production is considered and the models for assessing the state of its components for the digital twin are given. Also, a criterion and method for assessing the state of the upper organizational and technical level of this system are proposed.
T. I. Buldakova, S. I. Suyatinov

Proactive and Predictive Maintenance of Cyber-Physical Systems

The following chapter describes a concept model for proactive decision support system based on (real-time) predictive analytics and designed for maintenance of cyber-physical systems (CPSs) in order to optimize its downtime. This concept later is referred to as proactive and predictive maintenance decision support systems or P2M for short. The concept is based on (i) the axioms of predictive decisions making, (ii) the proactive computing principles and (iii) models and methods for intelligent data processing. The aforementioned concept extends an idea of data-driven intelligent systems by using two approaches. The first approach implements predictive analytics, i.e. detection of a pre-failure event (called a proactive event) over a certain time period. This approach is based on the sequence of the following operational processes: to detect–to predict–to decide–to act. The second approach helps to automate maintenance decisions, which allows to exclude operational roles and move to supervisory level positions in the operational management structure. The concept includes the following primary components: ontology, a data warehouse (data lake), data factory as a set of data processing methods, flexible pipelines for data handling and processing and business processes with predictive decision logic for cyber-physical systems maintenance. This concept model is considered as the platform for the design of cyber-physical asset performance management systems.
Maxim V. Shcherbakov, Artem V. Glotov, Sergey V. Cheremisinov

Conceptual Approach to Building a Digital Twin of the Production System

The digital twin is an important component of the cyber-physical system. This new structure of the production system was the result of the development of information technology. The article shows that, despite the long history and success in the development of production information systems, the concept of building digital twins of production systems is at an early stage. One of the problems in creating digital twins is the need for integration and joint processing of a large amount of heterogeneous information. It is shown that the problem of reflecting the current state of the production system is in many ways similar to the problem of the internal representation of the surrounding world in living systems. It is proposed to choose the theory of the levels of the physiologist N. A. Bernstein as the basis of the conceptual approach to the development of digital twins. The mechanisms of forming models of the external world at every level are outlined. A description of the hierarchical system for processing different types of information and obtaining an invariant representation of the external world are presented. The principles of constructing a virtual image in the organization of motor activity are formulated. The implementation of these principles when building a digital twin of the production process will improve the efficiency of integration methods and joint processing of information.
S. I. Suyatinov

Deep Neural Networks Application in Models with Complex Technological Objects

A method for creation of computer models in complex multiply connected technological objects based on the application of machine learning methods is described. For technological information processing hierarchical neural network structure integrated into cyber-physical systems of control is developed. It allows to monitor an object condition and forecast its development trends. A description for the algorithm and program, which performs the proposed method of model building, is given.
Valeriy Meshalkin, Andrey Puchkov, Maksim Dli, Yekaterina Lobaneva

Intelligent Technologies in the Diagnostics Using Object’s Visual Images

The problem of complex industrial equipment diagnostics using images in different spectral ranges is considered. An intelligent method for technical states classification according to images of a control object is proposed. Considered a neural network analyzer designed as a two-branch neural network. Convolutional neural network processes simultaneously three object’s images obtained in the visual, ultraviolet and infrared bands. The properties of the dataset for learning the neural network are investigated using the dimensionality reduction methods. Examples of the developed method and the neural network analyzer application for monitoring various industrial facilities are given.
Sergey Orlov, Roman Girin

Modeling Cyber-Physical System Object in State Space (on the Example of Paver)

We has considered results of theoretical description of the cyber-physical system object’s model—asphalt paver with a compacting working body of increased efficiency based on the state space method are considered. The working body includes a tamper, screed and pressure bar. The mathematical model of the process of interaction of the object with the compacting road-building material takes into account the masses of the main structural elements of the working body and pavement. A rheological model of a viscoelastic Kelvin–Voight body is using to describe the compacted material. Suitability of developed mathematical model experimentally confirmed by simulation modelling of the system using program MATLAB/Simulink.
Andrey Prokopev, Zhasurbek Nabizhanov, Vladimir Ivanchura, Rurik Emelyanov

Accelerometer Data Based Cyber-Physical System for Training Intensity Estimation

The correctness of athlete’s behavior can be controlled by health care cyber-physical system containing distributed (mobile) sensors and intelligent data processing. Such cyber-physical systems determine a concrete set of events, such as jumps or falls and identify events parameters, e.g. height and duration. The proposed accelerometer data based cyber-physical system differs from existed ones by an original method for detection of various types of athlete’s behavior. A proposed cyber-physical system contains on three modules: the data acquisition module, the data processing module and the processed data visualization module. A method for jump recognition is based on high frequency accelerometer data. The system is developed using Android Studio, R Studio development environments. The results provided by accelerometer data based cyber-physical system might be used for coaches and doctor in sports medicine for decisions regarding the optimal load in future training sessions. Use cases including different experimental setup shows the efficiency of the proposed system.
Igor D. Kazakov, Nataliya L. Shcherbakova, Adriaan Brebels, Maxim V. Shcherbakov

Assembly and Service Robotic Space Module. Mathematical Model of the Reduced System

Despite the significant achievements of the last decades in the field of space robotics, the task of automated Assembly and maintenance of large space objects continues to be relevant. At the same time, it is advisable to consider the set of serviced facilities and maintenance facilities of robotics in the future as a single cyber-physical system. Its key element is the assembly and service robotic space module (ASRSM). An important feature of the ASRSM as an element of the cyber-physical system is the potential variety of possible modes of controlled motion. The mentioned feature is of fundamental importance in the development of a complex of Autonomous robotic means interacting with a complex technical object in extreme conditions. The study of the characteristics of dynamic regimes ASRSM is advantageously carried out with the use of model problems involving the study of simplified models with the subsequent generalization of the results. It provides both theoretical and practical interest to mechanical design scheme ASRSM of the “movable base—massless single-stage handling mechanism payload”. It is shown that in the absence of external forces, a nonlinear oscillatory system with one degree of freedom can be put in correspondence with this system. This system is described by an independent Routh equation, and, in accordance with the terminology adopted in analytical mechanics, is called reduced. The methodical features of the mathematical description of the reduced system for the model problem are considered. It is shown that the Routh function considered as the Lagrange function of the reduced system can be excluded from the term corresponding to zero gyroscopic force and being a full derivative in time from some function of positional velocity and coordinate. In the absence of a control moment, an integral of energy can be written in the hinge, which has the form of the sum of the kinetic and potential energy of the reduced system, and determines the family of phase trajectories of the system’s own motions. The considered problem is of both applied and methodological interest. Qualitative generalization of the obtained results in the case of spatial reduced systems with several degrees of freedom is relevant from the point of view of using their own inertial motions in the construction of control.
Pavel P. Belonozhko
Additional information

Premium Partner

    Image Credits