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.

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.

The Golden Ratio Theorem: A Framework for Interchangeability and Self-Similarity in Complex Systems

The Golden Ratio Theorem, deeply rooted in fractal mathematics, presents a pioneering perspective on deciphering complex systems. It draws a profound connection between the principles of interchangeability, self-similarity, and the mathematical elegance of the Golden Ratio. This research unravels a unique methodological paradigm, emphasizing the omnipresence of the Golden Ratio in shaping system dynamics. The novelty of this study stems from its detailed exposition of self-similarity and interchangeability, transforming them from mere abstract notions into actionable, concrete insights. By highlighting the fractal nature of the Golden Ratio, the implications of these revelations become far-reaching, heralding new avenues for both theoretical advancements and pragmatic applications across a spectrum of scientific disciplines.

A novel fractional-order hyperchaotic complex system and its synchronization

A novel fractional-order hyperchaotic complex system is proposed by introducing the Caputo fractional-order derivative operator and a constant term to the complex simplified Lorenz system. The proposed system has different numbers of equilibria for different ranges of parameters. The dynamics of the proposed system is investigated by means of phase portraits, Lyapunov exponents, bifurcation diagrams, and basins of attraction. The results show abundant dynamical characteristics. Particularly, the phenomena of extreme multistability as well as hidden attractors are discovered. In addition, the complex generalized projective synchronization is implemented between two fractional-order hyperchaotic complex systems with different fractional orders. Based on the fractional Lyapunov stability theorem, the synchronization controllers are designed, and the theoretical results are verified and demonstrated by numerical simulations. It lays the foundation for practical applications of the proposed system.

Celebrating the 70th Anniversary--National University of Defense Technology,1953-2023 Special Section on Complex Systems Theory and Practice

In the 21st century,a new round of scientifi c and technological revolution represented by digitalization,networking and intelligence has caused a change in the scientific research paradigm,and the research of complex systems has become the main driving force for the change of the scientific research paradigm.

Exploration and Practice of Rubber Based Agroforestry Complex Systems in China

Agroforestry ecosystems are constructed by simulating natural ecosystems, applying the principles of symbiosis in nature, and organizing multiple plant populations to coexist, while conducting targeted cultivation and structural control scientifically. Rubber agroforestry complex ecosystems aim for sustainable development in terms of industry, ecology, resource utilization, and the livelihoods of producers. Rubber agroforestry complex ecosystems create a complex production structure system that integrates biology, society, and the economy through species combinations. Rubber trees and associated biological components coordinate with each other, mutually promote growth, and yield a variety of products for producers. Cultivation techniques and patterns of rubber agroforestry are essential components of these ecosystems. This study analyzes the production practices of rubber agroforestry complex cultivation, with a focus on the development and characteristics (complexity, systematicity, intensity, and hierarchy) of rubber agroforestry systems using a literature analysis and a survey approach. It explores the types and scales of complex planting, specifications and forms, and major effects of complex cultivation. This study identifies successful rubber agroforestry cultivation patterns and practical techniques, as well as the potential benefits of developing rubber agroforestry cultivation. It also points out the shortcomings in the development of complex planting, including an emphasis on production practices but insufficient theoretical research, a focus on production but inadequate attention to the market, and an emphasis on yield while overlooking the improvement of standards, brands, and added value. There are various complex patterns for young rubber plantations, but relatively fewer for mature plantations. Based on this analysis, this study suggests that future efforts should focus on in-depth research on interspecies and environmental interactions in rubber agroforestry ecosystems, clearly define key roles, accelerate the innovation of development patterns, and strengthen the foundation for development. It recommends promoting and demonstrating successful rubber agroforestry complex patterns and providing technical training, developing product branding for rubber agroforestry patterns, enhancing product value, expanding the application functions of rubber-forest mixed crop products, and establishing a stable and sustainable industry chain. This study provide practical experience and theoretical insights in rubber agroforestry complex systems from China the potential to enrich the knowledge of rubber agroforestry composite systems, provide practical experience to improve the operating income of smallholders, and even promote the sustainable development of rubber plantations.

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.

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

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.

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.

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.

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.

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.

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.

Study of electrophysical properties of metal–semiconductor contact by the theory of complex systems

The purpose of this work is to analyze the electrical properties of the metal–semiconductor contact(MSC)in the framework of the theory of complex systems.The effect of inhomogeneity of the different microstructures:polycrystalline,monocrystalline,amorphous metal–semiconductor contact surface is investigated,considering a Schottky diode(SD)as a parallel connection of numerous subdiodes.It has been shown that the polycrystallinity of the metal translates a homogeneous contact into a complex system,which consists of parallel connected numerous elementary contacts having different properties and parameters.

A study of TCM master Yan Zhenghua’s medication rule in prescriptions for digestive system diseases based on Apriori and complex system entropy cluster

Objective:To explore Yan Zhenghua’s drug selection rule for treating digestive system diseases using data mining.Methods:The 609 medical records of digestive system diseases treated by Yan Zhenghua were collected and the herbs in these recipes were examined using a data mining technique.The correlativity between herb pairs and association rules was studied using an Apriori algorithm and the correlativity among multi-herbs was studied using a complex system entropy cluster technique.Results:Yan Zhenghua’s treatment of digestive system diseases featured 15 herbs prescribed at least 159 times each,22 herb pairs prescribed at least 155 times each,and eight frequently used herb core combinations.A confidence greater than 0.91 and a support level greater than 20%were achieved using the modified mutual information method.Conclusion:The data mining results conformed to findings from clinical practice.The data mining method is a valuable technique with which to study the experience of famous,elderly traditional Chinese medicine physicians.

Complex Systems Are Not Black Boxes but Solvable Systematical Problems;Proven by Simulation and New Conception

This paper presents an innovative solution regarding complex systems to scientists, and prepares a novel system simulator for complex systems. A complex system in nature is not a black box but a solvable systematic problem. The solution is not derived from conventional physics based on reductionism, but rather from engineering sciences such as the feedback systems analysis method and engineering principles. Furthermore, this paper presents the conception of the solution to scientists for solving the problem. Moreover, nobody can doubt this research based on simulator. Complex systems are not mysterious science and not black box.