A Health State Prediction Model Based on Belief Rule Base and LSTM for Complex Systems

In industrial production and engineering operations,the health state of complex systems is critical,and predicting it can ensure normal operation.Complex systems have many monitoring indicators,complex coupling structures,non-linear and time-varying characteristics,so it is a challenge to establish a reliable prediction model.The belief rule base(BRB)can fuse observed data and expert knowledge to establish a nonlinear relationship between input and output and has well modeling capabilities.Since each indicator of the complex system can reflect the health state to some extent,the BRB is built based on the causal relationship between system indicators and the health state to achieve the prediction.A health state prediction model based on BRB and long short term memory for complex systems is proposed in this paper.Firstly,the LSTMis introduced to predict the trend of the indicators in the system.Secondly,the Density Peak Clustering(DPC)algorithmis used todetermine referential values of indicators for BRB,which effectively offset the lack of expert knowledge.Then,the predicted values and expert knowledge are fused to construct BRB to predict the health state of the systems by inference.Finally,the effectiveness of the model is verified by a case study of a certain vehicle hydraulic pump.

Auxiliary Software for Defining the Parameters of the Structural Organization of a Complex System

The developed auxiliary software serves to simplify, standardize and facilitate the software loading of the structural organization of a complex technological system, as well as its further manipulation within the process of solving the considered technological system. Its help can be especially useful in the case of a complex structural organization of a technological system with a large number of different functional elements grouped into several technological subsystems. This paper presents the results of its application for a special complex technological system related to the reference steam block for the combined production of heat and electricity.

Hierarchical Self-organization of Complex Systems

Researches on organization and structure in complex systems are academic and industrial fronts in modern sciences. Though many theories are tentatively proposed to analyze complex systems, we still lack a rigorous theory on them. Complex systems possess various degrees of freedom, which means that they should exhibit all kinds of structures. However, complex systems often show similar patterns and structures. Then the question arises why such similar structures appear in all kinds of complex systems. The paper outlines a theory on freedom degree compression and the existence of hierarchical self-organization for all complex systems is found. It is freedom degree compression and hierarchical self-organization that are responsible for the existence of these similar patterns or structures observed in the complex systems.

Engineering complex systems applied to risk management in the mining industry

Related to complexity, there is a wide diversity of concepts, ranging from ‘‘systemic" to ‘‘complex", implying a need for a unified terminology. Per different authors, the main drivers of complexity can be found in human behaviour and uncertainty. This complexity, structural or dynamic can be organizational, technological, or nested in their relationship. ISO international standard 31000:2009 definition of risk management ‘‘coordinated activities to direct and control an organization with regard to risk", when applied to economic sectors, industry, services, project, or activity, it requires the use of models or theories as guidelines. Therefore, as its basic elements comprehend human behaviour and/or uncertainty, risk management to be effective and adapted as much as possible to reality, must be operational within complex systems, as already demonstrated in different R&D environments. Risk management faces demanding challenges when approaching specific and endogenous needs, such as the mining sector. This paper presents a multivariable function analysis methodology approach based on complex system modelling and through real data corresponding to a risk management tool in the mining sector.

Research on basic characteristics of complex system brittleness

The goal of this paper is to research one new characteristic of complex system. Brittleness, which is one new characteritic of complex system, is presented in this paper. The linguistic and qualitative descriptions of complex system are also given in this paper. Otherwise, the qualitative description of complex system is presented at first. On the basis of analyzing the existing brittleness problems, linguistic description and mathematic description of brittleness are given as well. Three kinds of phenomena to judge brittleness of complex system are also given, based on catastrophe theory. Basic characteristics of brittleness are given on the basis of its mathematic description. Two critical point sets are defined by using catastrophe theory. The definition of brittleness and its related theory can serve the control of complex system, and provide theoretical basis for the design and control of complex system.

Brittleness research on complex system based on brittle link entropy

As the scale of complex system is growing larger and larger, interferences from internal and outer system can result in the collapse of one subsystem in a complex system. They will not only make one subsystem collapse but also influence the other subsystems. Moreover, the whole complex system can collapse consequently. The mechanism of collapse of complex system is clue to the brittleness of complex system that is presented and argued as the basic characteristic in this paper. It is the brittleness link entropy between subsystems that leads to the collapse of whole system. Effective ways that can be adopted to reduce the brittleness entropy can see the successful control of brittleness.

Cascading failure prevention of complex systems based on brittleness entropy game

A non-cooperative game model based on brittleness entropy is formulated for preventing cascading failure of complex systems.Subsystems of a complex system are mapped to the players of the game.The influence of collapsed subsystems to other subsystems is also taken into account in the definition of payoff function except for their own entropy increase.This influence is named brittleness entropy.Each player has two optional strategies;rational for negative entropy and irrational for negative entropy.The model is designed to identify the players who select an irrational strategy for negative entropy.The players who select the irrational strategy for negative entropy continue to compete for negative entropy after the recovery of ordered state and make other subsystems can' t get enough negative entropy to reduce entropy increase.It leads to cascading failure of the complex system in the end.Genetic algorithm is used to seek the solution of game model,and the simulation result verifies the effectiveness of the proposed model.The model provides a new way to prevent cascading failure of complex systems.

A Novel Evolutionary-Fuzzy Control Algorithm for Complex Systems

This paper presents an adaptive fuzzy control scheme based on modified genetic algorithm. In the control scheme, genetic algorithm is used to optimze the nonlinear quantization functions of the controller and some key parameters of the adaptive control algorithm. Simulation results show that this control scheme has satisfactory performance in MIMO systems, chaotic systems and delay systems.

IoT-based Smart and Complex Systems：A Guest Editorial Report

THE Industrial Revolution starting from about 1760 and ending at around 1840 has been viewed as the first Industrial Revolution.It features with the replacement of human and animal muscle power with steam and mechanical power.Human income per capita had taken 800 years to double by

Clustering-based maintainability demonstration for complex systems with a mixed maintenance time distribution

During maintainability demonstration,the maintenance time for complex systems consisting of mixed technologies generally conforms to a mixture distribution.However existing maintainability standards and guidance do not explain explicitly how to deal with this situation.This paper develops a comprehensive maintainability demonstration method for complex systems with a mixed maintenance time distribution.First of all,a K-means algorithm and an expectation-maximization(EM)algorithm are used to partition the maintenance time data for all possible clusters.The Bayesian information criterion(BIC)is then used to choose the optimal model.After this,the clustering results for equipment are obtained according to their degree of membership.The degree of similarity for the maintainability of different kinds of equipment is then determined using the projection method.By using a Bootstrap method,the prior distribution is obtained from the maintenance time data for the most similar equipment.Then,a test method based on Bayesian theory is outlined for the maintainability demonstration.Finally,the viability of the proposed approach is illustrated by means of an example.

The Fuzzy Modeling Algorithm for Complex Systems Based on Stochastic Neural Network

A fuzzy modeling method for complex systems is studied. The notation of general stochastic neural network (GSNN) is presented and a new modeling method is given based on the combination of the modified Takagi and Sugeno's (MTS) fuzzy model and one-order GSNN. Using expectation-maximization(EM) algorithm, parameter estimation and model selection procedures are given. It avoids the shortcomings brought by other methods such as BP algorithm, when the number of parameters is large, BP algorithm is still difficult to apply directly without fine tuning and subjective tinkering. Finally, the simulated example demonstrates the effectiveness.

Robust synchronization of uncertain complex systems with time-varying delays

Synchronization analysis and design problems for uncertain time-delayed high-order complex systems with dynamic output feedback synchronization protocols are investigated. By stating projection on the synchronization subspace and the complement synchronization subspace, synchronization problems are transformed into simultaneous stabilization problems of multiple subsystems related to eigenvalues of the Laplacian matrix of the interaction topology of a complex system. In terms of linear matrix inequalities(LMIs), sufficient conditions for robust synchronization are presented, which include only five LMI constraints.By the changing variable method, sufficient conditions for robust synchronization in terms of LMIs and matrix equalities are given,which can be checked by the cone complementarily linearization approach. The effectiveness of theoretical results is shown by numerical examples.

PANSYSTEMS CLUSTERING ANALYSIS OF COMPLEX SYSTEMS

In this paper, by use of equivalence operators δi and semi-equivalence operators Εi we study the clustering problems of complex systems, present δ (1,3) disconnection principle, dual transformation principle and large-scale systems decomposition principle for analizing and operating complex systems, discuss interconnectivity and disconnectivity of complex systems in detail and present some related theorems. Finally, we discuss the levels of systems according to pansystems clustering approach proposed in this paper.

Complex systems and network science:a survey

Complex systems widely exist in nature and human society.There are complex interactions between system elements in a complex system,and systems show complex features at the macro level,such as emergence,self-organization,uncertainty,and dynamics.These complex features make it difficult to understand the internal operation mechanism of complex systems.Networked modeling of complex systems is a favorable means of understanding complex systems.It not only represents complex interactions but also reflects essential attributes of complex systems.This paper summarizes the research progress of complex systems modeling and analysis from the perspective of network science,including networked modeling,vital node analysis,network invulnerability analysis,network disintegration analysis,resilience analysis,complex network link prediction,and the attacker-defender game in complex networks.In addition,this paper presents some points of view on the trend and focus of future research on network analysis of complex systems.

Robust finite-time stabilization of unified chaotic complex systems with certain and uncertain parameters

This paper deals with the finite-time stabilization of unified chaotic complex systems with known and unknown parameters. Based on the finite-time stability theory, nonlinear control laws are presented to achieve finite-time chaos control of the determined and uncertain unified chaotic complex systems, respectively. The two controllers are simple, and one of the uncertain unified chaotic complex systems is robust. For the design of a finite-time controller on uncertain unified chaotic complex systems, only some of the unknown parameters need to be bounded. Simulation results for the chaotic complex Lorenz, Lu¨ and Chen systems are presented to validate the design and analysis.

Simulation calculation of solubility of insoluble compound M_mA_a in complex system

A simulation calculation model for the solubility of insoluble compound MmAa in complex system was established.According to coordination equilibrium principle,relevant dissociation reaction,complexation reaction,self-complexation reaction and protonation reaction during insoluble compound dissolving were considered and then the mass balance equations about solubility calculation were obtained.In the case analysis,the solubility of silver chloride in ammonia system was obtained by simulation calculation,and curved surface charts of thermodynamic equilibrium about the total concentration of silver ions,pH and concentration of ammonia ions were drawn correspondingly.The results show that under the conditions of room temperature and 6 mol/L ammonia concentration,the calculated solubility value of silver chloride(34 g/L) is close to the actual value(31 g/L),demonstrating that this model is suitable for solubility calculation of insoluble compound MmAa in the complex system.

A numerical study of coupled maps representing energy exchange processes between two environmental interfaces regarded as biophysical complex systems

The field of environmental sciences is abundant with various interfaces and is the right place for the application of new fundamental approaches leading towards a better understanding of environmental phenomena. Following the definition of environmental interface by Mihailovic and Bala? [1], such interface can be, for example, placed between: human or animal bodies and surrounding air, aquatic species and water and air around them, and natural or artificially built surfaces (vegetation, ice, snow, barren soil, water, urban communities) and the atmosphere, cells and surrounding environment, etc. Complex environmental interface systems are (i) open and hierarchically organised (ii) interactions between their constituent parts are nonlinear, and (iii) their interaction with the surrounding environment is noisy. These systems are therefore very sensitive to initial conditions, deterministic external perturbations and random fluctuations always present in nature. The study of noisy non-equilibrium processes is fundamental for modelling the dynamics of environmental interface regarded as biophysical complex system and for understanding the mechanisms of spatio-temporal pattern formation in contemporary environmental sciences. In this paper we will investigate an aspect of dynamics of energy flow based on the energy balance equation. The energy exchange between interacting environmen- tal interfaces regarded as biophysical complex systems can be represented by coupled maps. Therefore, we will numerically investigate coupled maps representing that exchange. In ana- lysis of behaviour of these maps we applied Lyapunov exponent and cross sample entropy.

APPLICATION OF ARTIFICIAL NEURAL NETWORK IN COMPLEX SYSTEMS OF REGIONAL SUSTAINABLE DEVELOPMENT

Meeting the challenge of sustainable development requires substantial advances in understanding the interaction of natural and human systems. The dynamics of regional sustainable development could be addressed in the context of complex system thinking. Three features of complex systems are that they are uncertain, non-linear and self-organizing. Modeling regional development requires a consideration of these features. This paper discusses the feasibility of using the artificial neural networt(ANN) to establish an adjustment prediction model for the complex systems of sustainable development (CSSD). Shanghai Municipality was selected as the research area to set up the model, from which reliable prediction data were produced in order to help regional development planning. A new approach, which could help to manage regional sustainable development, is then explored.

A GENERAL MATHEMATICAL FRAMEWORK OF COMPLEX SYSTEMS(Ⅰ)

The fundamental and simplest structure of a complex system is a network.According to this idea,we plan to develop a general methematical framework of complex systems.In this paper,we discuss in detail the concept of systems,a general description of systems:System=(Hardware,Software,Environment),and whole-part relations,including relations between elements and systems,subsystems and systems,and between systems.The rules of operations of systems are given,and the induced transformations between hardware and software of systems are briefly discussed.

Safety control program for complex system based on behavior science

To control complex system's safety effectively,safety control program was supported based on the principles of behavioral science that shapes organizational be- havior,and organizational behavior produced individual behavior.The program can be structured into a model that consists of three modules including individual behavior rectifi- cation,organization behavior diagnosis and model of safety culture.The research result not only reveals the deep cause of complex system accidents but also provides structural descriptions with the accidents cause.