Multi‐Variable Direct Self‐Organizing Fuzzy Neural Network Control for Wastewater Treatment Process

A multi‐variable direct self‐organizing fuzzy neural network control (M‐DSNNC) method is proposed for the multi‐variable control of the wastewater treatment process (WWTP). In this paper, the proposed control system is an essential multi‐variable control method for the WWTP. No exact plant model is required, which avoids the difficulty of establishing the mathematics model of WWTP. The M‐DSNNC system is comprised of a fuzzy neural network controller and a compensation controller. The fuzzy neural network is used for approximating the ideal control law under a general nonlinear system. Moreover, the neural network is designed in a self‐organizing mode to adapt the uncertainty environment. Simulation results, based on the international benchmark simulation model No.1 (BSM1), demonstrate that the control accuracy is improved under the proposed M‐DSNNC method, and the controller has a much stronger decoupling ability.     

污水处理过程中对泥龄的模糊神经网络控制

针对污水处理过程的高度非线性、进水流量及水质变化剧烈、各状态变量之间存在强耦合关系等特性，提出了一种自适应模糊神经网络控制方法，以泥龄作为运转控制参数，调节排出的污泥量．仿真结果表明该控制器能够在线调整输入变量的隶属函数、优化控制规则，将其应用于活性污泥法污水处理系统中，可以快速地去除污水中的污染物，使污泥具有良好的去污能力和沉淀性能，并且具有很强的鲁棒性．     

神经网络滑模变结构控制研究综述

综述了近年来将人工神经网络控制和滑模变结构控制相结合的研究工作．从神经网络在滑模变结构控制中不同的应用方式出发，论述了神经网络在提高和改善滑模变结构系统性能方面的理论和方法，分析了它们各自的特点与相互之间的联系．最后展望了该领域未来的研究方向．     

多输出非线性系统神经网络变结构控制的算法及其实现

在变结构控制系统中，切换函数的实际值与理想值之差反映了模型与实际系统的差别，引入神经网络的目的是在线辨识出这种差别。方法实现了对输入多输出非线性系统轨迹踊跃的控制，且对摄动具有很强的鲁棒性，大大减小了系统在切换面上的抖动。     

Event‐triggered Control for Cluster Consensus in Multi‐agent Networks

This paper considers the issue of cluster consensus for multiple agents in fixed and undirected networks. Agents in a network are supposed to split into several clusters, and a fraction of the agents in each cluster are pinned by virtual leaders. According to the Lyapunov stability theory and graph theory, some appropriate event‐triggered protocols are developed for consensus of the agents belonging to the same cluster, which can greatly reduce both the number of communication updates and that of control actuation updates. Finally, a numerical example is shown to demonstrate the effectiveness of the proposed theoretical results.     

Multi‐Tracking of First Order Multi‐Agent Networks Via Self‐Triggered Control

A multi‐tracking problem of multi‐agent networks is investigated in this paper where multi‐tracking refers to that the states of multiple agents in each subnetwork asymptotically converge to the same desired trajectory in the presence of information exchanges among subnetworks. The multi‐tracking of first order multi‐agent networks with directed topologies was studied. Self‐triggered protocols were proposed along with triggering functions to solve the stationary multi‐tracking and bounded dynamic multi‐tracking. The self‐triggered scheduling is obtained, and the system does not exhibit Zeno behavior. Numerical examples are provided to illustrate the effectiveness of the obtained criteria.     

注塑机料筒多段温度PID神经网络解耦控制系统

注塑机料筒温度是一类多变量、强耦合、大惯性控制对象,本文根据注塑机料筒温度控制的要求,利用PID神经网络构成多变量解耦控制系统。文中分析了注塑机温度控制的特点,给出了网络的结构和算法,对多段温度系统进行了实时仿真,显示了PID神经网络对注塑机料筒温度控制的良好解耦性能和自学习控制特性。     

变结构神经网络

针对神经网络结构、性能不佳的普通状况,本文提出变结构的神经网络。先后研究了神经网络单隐层和多隐层的变化情况。仿真试验结果证明是有效的。     

基于RBF神经网络的热电偶建模方法

针对热电偶的测量精度问题,建立了热电偶传感器的数学模型。此数学模型采用RBF神经网络,利用带遗忘因子的梯度下降算法进行网络参数的调整,并给出了建模步骤。实际结果表明,该模型具有较高的精度。     

序批式反应器污水处理工艺建模与控制研究

近年来采用序批式反应器工艺进行生化污水处理的研究日益受到关注.在工艺流程设计、模型建立、操作优化、控制器设计等都取得大量的成果.􀁱本文综述了这个领域一些最新的!与未来应用有关的研究进展.􀁱     

多变量强耦合时变系统的PID神经网络控制

介绍了一种新的神经网络———PID神经网络及其多变量强耦合时变控制系统。文中给出了网络的结构和算法,分析了时变对象的特点,对一组二变量强耦合时变系统进行了实时仿真。仿真结果显示:PID神经网络对多变量强耦合时变对象具有良好的解耦性能和自学习控制特性。     

NNs‐Based Event‐Triggered Consensus Control of a Class of Uncertain Nonlinear Multi‐Agent Systems

We are concerned with the consensus problem for a class of uncertain nonlinear multi‐agent systems (MASs) connected through an undirected communication topology via event‐triggered approaches in this paper. Two distributed control strategies, the adaptive centralized event‐triggered control one and adaptive distributed event‐triggered control one, are presented utilizing neural networks (NNs) and event‐driven mechanisms, where the advantages of the proposed control laws lie that they remove the requirement for exact priori knowledge about parameters of individual agents by taking advantage of NNs approximators and they save computing and communication resources since control tasks only execute at certain instants with respect to predefined threshold functions. Also, the trigger coefficient can be regulated adaptively with dependence on state errors to ensure not only the control performance but also the efficiency of the network interactions. It is proven that all signals in the closed‐loop system are bounded and the Zeno behavior is excluded. Finally, simulation examples are presented for illustration of the theoretical claims.     

控制中的一种神经网络结构

本文介绍通过利用神经网络计算算法怎样将神经网络两个重要的计算特点用于自适应控制。以单自由度机械手为例,对神经形态控制方法和模型参考自适应控制方法进行比较,对很大规模的系统,利用神经网络作为自适应控制提供定速,比传统的方法优越。     

基于Elman神经网络的网络流量建模及预测

根据实际网络中测量得到的网络流量数据,建立一个基于Elman神经网络的流量模型,介绍Elman神经网络的架构设计,并提出一种基于正交最小二乘的学习算法,在此基础上对网络流量进行预测。仿真实验结果表明,该模型具有良好的预测效果,相对于传统线性模型及BP神经网络模型具有更高的预测精度和更好的自适应性。     

基于遗传算法的控制系统在废水处理中的应用

为了结合MATLAB软件和组态软件MCGS的优点,通过OPC通讯技术实现两者之间的数据交换;同时引入遗传算法对人工神经网络进行优化,实现了遗传神经网络控制算法和MCGS的有机结合。仿真结果表明,人工神经网络的预测值与实际值之间的最大相对误差为10.28%,最小相对误差为5.28%,平均相对误差为7.82%,平均绝对百分比误差为0.12%;经过遗传算法优化之后,这些误差分别降为6.25%,1.67%,4.30%,0.073%。说明经过遗传算法优化后的人工神经网络具有更好的性能,遗传神经网络控制算法和MCGS的有机结合对废水处理过程可以实现有效的控制。     

T-S模糊神经网络应用于变参数系统的控制研究

针对基于模型的传统控制策略在线性时变系统中的应用受到系统的时变性和不确定性限制,通常难以获得理想的控制性能这一问题,提出了线性时变系统的一种变参数系统模型。该模型具有有界性和不确定性特点,利用模糊神经网络具有的自学习能力强、模型依赖性小以及鲁棒性强的优点,提出一种基于遗传算法的T-S模糊神经网络控制器对其进行控制研究,并通过仿真实验证明了该模糊神经网络控制器对变参数系统控制的可行性与有效性,为线性时变系统的控制问题提供了一种新思路。     

质子交换膜燃料电池的神经网络建模与控制

该文从设计质子交换膜燃料电池（PEMFC）控制方案的角度出发,首先提出了采用Elman动态神经网络对PEMFC系统进行建模的新方法,以实验中采样到的PEMFC系统的工作温度输入输出数据训练网络,并采用动态反向传播学习算法根据误差不断调整网络参数直至达到要求精度;Elman神经网络辨识可使辨识过程简化并提高了辨识精度。然后在此基础上设计了自适应模糊神经网络控制器。最后的仿真实验以Elman神经网络模型为参考模型,使用自适应神经网络控制算法控制PEMFC的工作温度,取得了较好的控制效果。结果显示所设计的控制系统适合于控制PEMFC这样一类复杂非线性系统。     

Stability of Local On‐Ramp Metering Control Laws

A framework for stability analysis of local on‐ramp metering control strategies based on the cell transmission model is presented. Within this framework, it is possible to formulate Lyapunov and input‐state stability results for on‐ramp metering control strategies in an open section of highway with on‐ramps. Using this analysis, recommendations for the design of on‐ramp metering control laws set points are derived. Two examples on the use of such analysis are presented. One deals with the stability analysis of a local on‐ramp metering control law and the other with the design of a disturbance observer that, used in combination with the local on‐ramp metering control law, provides a more robust response to traffic regulation. Simulation results are included that confirm the possibility of using this framework to test the impact of local on‐ramp metering control strategies.     

正交神经网络的动态建模方法研究

This paper presents a dynamic modeling method based on orthogonal neural network, it fully uses the characteristics of the nonlinear processing ability of neural networks and the efficient disposal of the large scaling sparse problems that Givens transform can process. It can not only train the notwork quickly, but also can optimize the structure of the networks. Simulating experiments show that the new modeling method is a simple universal modeling method for the nonlinear systems.