一种基于遗传算法与进化编程的系统辨识方法

分析比较了遗传算法（GA）和进化编码（EP）在解决系统辨识问题中的优劣，提出一种将GA和EP相结合的新的系统辨识方法，该方法既不依赖于种群的初始值，又具有较强的稳定性。仿真结果表明了该方法的有效性和独到之处。     

基于混合进化策略的非线性系统辨识

进化策略是一类适用于非线性、不可微和多峰值复杂函数的优化方法。提出了基于混合进化策略的非线性系统辨识方法。方法的基本思想是将非线性系统辨识问题转化为参数空间上的函数优化问题,然后应用一种新的混合进化策略对整个参数空间进行搜索以获得系统参数的最优估计。仿真结果显示了该方法的有效性。     

基于协同进化算法的TS模糊模型设计

提出一种基于协同进化算法的TS模糊模型设计方法．该方法由以下两步组成：（1）采用模糊聚类算法辨识初始的模糊模型；（2）利用协同进化算法对所获得的初始模糊模型进行结构和参数的优化．协同进化算法由两类种群组成：规则前件种群和隶属函数参数种群；其适应度函数同时考虑模型的精确性和解释性，采用两种群合作计算的策略；为提高模型的解释性，在协同进化算法中利用基于相似性的模型简化方法对模型进行约简．最后，利用该方法对Mackey-Glass系统进行辨识，仿真结果验证了方法的有效性．     

混沌时间序列的自适应变异差分进化ANFIS预测

提出了一种基于自适应变异差分进化（AMDE）算法的ANFIS模型对混沌时间序列进行预测的方法,该方法采用自适应变异差分进化算法和最小二乘法相结合的混合学习算法对ANFIS网络结构参数进行优化设计,利用差分进化算法的全局寻优能力对ANFIS网络前件参数进行优化,而网络的结论参数采用最小二乘法优化,混合学习算法提高了网络参数辨识的收敛速度和系统的全局收敛性,仿真实验结果表明了该方法的有效性。     

基于结构自适应滤波方法的非线性系统辨识

针对非线性系统辨识中定结构参数辨识局限性高和辨识率低的问题，将结构自适应引入辨识的优化，提出一种基于子系统的结构自适应滤波（SSAF）方法。该方法的模型由若干子系统级联而成，每一个子系统均为线性-非线性混合结构。子系统的线性部分是一个一阶或二阶可选的无限脉冲响应滤波器（IIR），非线性部分则是一个静态的非线性函数。初始化中，子系统的参数随机产生，生成的若干子系统按照设定的连接规则进行随机连接，而不含反馈的连接机制确保了非线性系统的有效性。采用一种自适应多精英引导的复合差分进化（AMECoDEs）算法用于自适应模型循环优化，直至找到最优的结构和参数，即全局最优。实验结果表明，SSAF方法在非线性测试函数以及真实数据集上的表现优异，辨识率高且收敛性好，与聚焦时滞递归神经网络（FTLRNN）相比，它所用参数的个数仅为FTLRNN的1/10，且适应值精度提高了7%，验证了所提方法的有效性。     

基于Pareto协同进化算法的TS模糊模型设计

提出一种可同时构造多个精确性和解释性较好折中的TS模糊模型的设计方法．该方法由以下两步组成：1）采用模糊聚类算法辨识初始模型;2）利用Pareto协同进化算法对所获得的初始模型进行结构和参数优化．Pareto协同进化算法由规则前件种群和隶属函数种群组成,其目标函数同时考虑模型的精确性和解释性,采用一种新的基于非支配排序的多种群合作策略．利用该方法对一类合成非线性动态系统进行建模,仿真结果验证了该方法的有效性．     

具有非参数化不确定系统的无偏辨识

本文研究了具有参数和非参数不确定性系统的集员辨识问题：分析表明利用我们在文（５）中提出的ＢＥＬＳ方法可以消除集员辨识中观测噪声引起的偏差，文中通过对系统输入数据的预滤波将已知零点嵌入系统，利用这些零点提供的信息将观测噪声引起的辨识偏差予以消除。     

基于GEP和GA技术的非线性系统辨识研究

给出了利用基因表达式编程（GEP）进行非线性系统辨识的方法,弥补了传统辨识方法需要过多预知信息的不足,有着比遗传编程（GP）更简洁有效的系统模型结构表达方式.利用改进的遗传算法（GA）并行地进行模型参数进化,可以在有限的给定数据内得到合适的模型.关于模型适应度的定义,综合考虑了精确性和复杂性因素,能够获取一种比较折中的辨识结果.仿真结果表明,这种方式可以快速、准确地获取非线性模型.     

基于高阶神经网络扩展卡尔曼滤波器逆算法的非线性挠性结构的姿态控制

本文针对非线性挠性结构的姿态控制,提出了一种基于高阶神经网络及径向基函数网络（ＲＢＦＮ）相结合的网络模型,用于非线性挠性结构的动态系统辨识,以及基于卡尔曼滤波器（ＥＫＦ）逆算法的控制策略。针对神经网络辨识时的模型误差,提出了一种简单有效的补偿方法,给出了建模误差补偿与补偿时仿真结果。仿真得出,该方法具有收敛快,算法简单,并能有效消除建模误差等优点。     

基于自适应云粒子群算法的Wiener模型辨识

针对非线性系统Wiener模型的系统辨识问题,提出一种基于自适应云模型的粒子群优化(ACMPSO)算法的辨识方法。ACMPSO算法利用云模型实现优秀粒子的遗传和进化操作,根据进化状况动态调整云模型的参数,自适应地控制云模型算法的寻优范围和精度,有较强的全局搜索和局部求精能力。仿真实验证明该算法寻优精度高于其他主要PSO算法;将该算法应用于Wiener模型的系统辨识,通过实验证明了该辨识方法优于当前其他方法。     

Stability and weighted sensitivity analysis of robust controller for heat exchanger

This study presents a parametric system identification approach to estimate the dynamics of a chemical plant from experimental data and develops a robust PID controller for the plant. Parametric system identification of the heat exchanger system has been carried out using experimental data and prediction error method. The estimated model of the heat exchanger system is a time-delay model and a robust PID controller for the time-delayed model has been designed considering weighted sensitivity criteria. The mathematical background of parametric system identification, stability analysis, and ${{\rm H}_\infty }$ weighted sensitivity analysis have been provided in this paper. A graphical plot has been provided to determine the stability region in the $( {{K_{\rm p}},{K_{\rm i}}} )$, $( {{K_{\rm p}},{K_{\rm d}}} )$ and $( {{K_{\rm i}},{K_{\rm d}}} )$ plane. The stability region is a locus dependent on parameters of the controller and frequency, in the parameter plane.     

A differential evolution based neural network approach to nonlinear system identification

This paper addresses the effectiveness of soft computing approaches such as evolutionary computation (EC) and neural network (NN) to system identification of nonlinear systems. In this work, two evolutionary computing approaches namely differential evolution (DE) and opposition based differential evolution (ODE) combined with Levenberg Marquardt algorithm have been considered for training the feed-forward neural network applied for nonlinear system identification. Results obtained envisage that the proposed combined opposition based differential evolution neural network (ODE-NN) approach to identification of nonlinear system exhibits better model identification accuracy compared to differential evolution neural network (DE-NN) approach. The above method is finally tested on a one degree of freedom (1DOF) highly nonlinear twin rotor multi-input–multi-output system (TRMS) to verify the identification performance.     

Capturing aesthetic intention during interactive evolution

Interactive Evolutionary Systems (IES) are capable of generating and evolving large numbers of alternative designs. When using such systems, users are continuously required to interact with the system by making evaluations and selections of the designs that are being generated and evolved. The evolutionary process is therefore led by the visual aesthetic intentions of the user. However, due to the limited size of the computer screen and fuzzy nature of aesthetic evaluations, evolution is usually a mutation-driven and divergent process. The convergent mechanisms typically found in standard Evolutionary Algorithms are more difficult to achieve with IES.To address this problem, this paper presents a computational framework that creates an IES with a higher level of convergence without requiring additional actions from the user. This can be achieved by incorporating a Neural Network based learning mechanism, called a General Regression Neural Network (GRNN), into an IES. GRNN analyses the user's aesthetic evaluations during the interactive evolutionary process and is thereby able to approximate their implicit aesthetic intentions. The approximation is a regression of aesthetic appeals conditioned on the corresponding designs. This learning mechanism allows the framework to infer which designs the users may find desirable. For the users, this reduces the tedious work of evaluating and selecting designs.Experiments have been conducted using the framework to support the process of parametric tuning of facial characters. In this paper we analyze the performance of our approach and discuss the issues that we believe are essential for improving the usability and efficiency of IES.     

Making use of population information in evolutionary artificialneural networks

This paper is concerned with the simultaneous evolution of artificial neural network (ANN) architectures and weights. The current practice in evolving ANN's is to choose the best ANN in the last generation as the final result. This paper proposes a different approach to form the final result by combining all the individuals in the last generation in order to make best use of all the information contained in the whole population. This approach regards a population of ANN's as an ensemble and uses a combination method to integrate them. Although there has been some work on integrating ANN modules, little has been done in evolutionary learning to make best use of its population information. Four linear combination methods have been investigated in this paper to illustrate our ideas. Three real-world data sets have been used in our experimental studies, which show that the recursive least-square (RLS) algorithm always produces an integrated system that outperforms the best individual. The results confirm that a population contains more information than a single individual. Evolutionary learning should exploit such information to improve generalization of learned systems.     

Non‐Parametric Identification Method of Volterra Kernels for Nonlinear Systems Excited by Multitone Signal

To solve the problem of Volterra frequency‐domain kernels (VFKs) of nonlinear systems, which can be difficult to identify, we propose a novel non‐parametric identification method based on multitone excitation. First, we have studied the output properties of VFKs of nonlinear systems excited by the multitone signal, and derived a formula for identifying VFKs. Second, to improve the efficiency of the non‐parametric identification method, we suggest an increase in the number of tones for multitone excitation to simultaneously identify multi‐point VFKs with one excitation. We also propose an algorithm for searching the frequency base of multitone excitation. Finally, we use the interpolation method to separate every order output of VFK and extract its output frequency components, then use the derived formula to calculate the VFKs. The theoretical analysis and simulation results indicate that the non‐parametric method has a high precision and convenience of operation, improving the conventional methods, which have the defects of being unable to precisely identify VFKs and identification results are limited to three‐order VFK.     

Evolution of mathematical models of chaotic systems based on multiobjective genetic programming

This work is concerned with the identification of models for nonlinear dynamical systems using multiobjective evolutionary algorithms. Systems modelling involves the processes of structure selection, parameter estimation, model performance and model validation and involves a complex solution space. Evolutionary Algorithms (EAs) are search and optimisation tools founded on the principles of natural evolution and genetics, which are suitable for a wide range of application areas. Due to the versatility of these tools and motivated by the versatility of genetic programming (GP), this evolutionary paradigm is proposed for this modelling problem. GP is then combined with a multiobjective function definition scheme. Multiobjective genetic programming (MOGP) is applied to multiple, conflicting objectives and yields a set of candidate parsimonious and valid models, which reproduce the original system behaviour. The MOGP approach is then demonstrated as being applicable for system modelling with chaotic dynamics. The circuit introduced by Chua, being one of the most popular benchmarks for studying nonlinear oscillations, and the Duffing–Holmes oscillator are the systems to test the evolutionary-based modelling approach introduced in this paper.     

Efficiency determination of induction motors using multi-objective evolutionary algorithms

This paper introduces a method based on multi-objective evolutionary algorithms for the determination of in-service induction motor efficiency. In general, the efficiency is determined by accumulating multiple objectives into one objective by a linear combination and optimizing the resulting single-objective problem. The approach has some drawbacks such that exact information about solution alternatives will not be readily visible. In this paper the multi-objective evolutionary optimization algorithms, the Non-dominated Sorting Genetic Algorithm-II (NSGA-II) and Strength Pareto Evolutionary Algorithm-2 (SPEA2), are successfully applied to the efficiency determination problem in induction motor. The performances of algorithms are compared on the basis of the obtained results.     

A hybrid approach to parallelize a fast non‐dominated sorting genetic algorithm for phylogenetic inference

The field of computational biology encloses a wide range of optimization problems that show non‐deterministic polynomial‐time hard complexities. Nowadays, phylogeneticians are dealing with a growing amount of biological data that must be analyzed to explain the origins of modern species. Evolutionary relationships among organisms are often described by means of tree‐shaped structures known as phylogenetic trees. When inferring phylogenies, two main challenges must be addressed. First, the inference of reliable evolutionary trees on data sets where different optimality principles support conflicting evolutionary hypotheses. Second, the processing of enormous tree searches spaces where traditional sequential strategies cannot be applied. In this sense, phylogenetic inference can benefit from the combination of high performance computing and evolutionary computation to carry out the reconstruction of complex evolutionary histories in reduced execution times. In this paper, we introduce multiobjective phylogenetics, a hybrid OpenMP/MPI approach to parallelize a well‐known multiobjective metaheuristic, the fast non‐dominated sorting genetic algorithm (NSGA‐II). This algorithm has been designed to conduct phylogenetic analyses on multi‐core clusters in accordance with two principles: maximum parsimony and maximum likelihood. The main goal is to combine the benefits of shared‐memory and distributed‐memory programming paradigms to efficiently infer a set of high‐quality Pareto solutions. Experiments on six real nucleotide data sets and comparisons with other hybrid parallel approaches show that multiobjective phylogenetics is able to achieve significant performance in terms of parallel, multiobjective, and biological results. Copyright © 2014 John Wiley & Sons, Ltd.     

Monte Carlo Filter in Mobile Robotics Localization: A Clustered Evolutionary Point of View

Localization, i.e., estimating a robot pose relative to a map of an environment, is one of the most relevant problems in mobile robotics. The research community has devoted a big effort to provide solutions for the localization problem. Several methodologies have been proposed, among them the Kalman filter and Monte Carlo Localization filters. In this paper, the Clustered Evolutionary Monte Carlo filter (CE-MCL) is presented. This algorithm, taking advantage of an evolutionary approach along with a clusterization method, is able to overcome classical MCL filter drawbacks. Exhaustive experiments, carried on the robot ATRV-Jr manufactured by iRobot, are shown to prove the effectiveness of the proposed CE-MCL filter.     

Evolutionary fuzzy clustering and functional modular neural network-based human recognition

Computational intelligence shows its ability for solving many real-world problems efficiently. Synergism of fuzzy logic, evolutionary computation, and neural network can lead to development of a computational efficient and performance-rich system. In this paper, we propose a new approach for solving the human recognition problem that is the fusion of evolutionary fuzzy clustering and functional modular neural networks (FMNN). Evolutionary searching technique is applied for finding the optimal number of clusters that are generated through fuzzy clustering. The functional modular neural network has been used for recognition process that is evaluated with the help of integration based on combining the outcomes of FMNN. Performance of the proposed technique has been empirically evaluated and analyzed with the help of different parameters.