Temperature decoupling control of double-level air flow field dynamic vacuum system based on neural network and prediction principle

Double-level air flow field dynamic vacuum (DAFDV) system is a strong coupling, large time-delay, and nonlinear multi-input–multi-output system. Decoupling and overcoming the impact of time-delay are two keys to obtain rapid, accurate and independent control for two air temperatures in two concatenate chambers of the DAFDV system. A predictive, self-tuning proportional-integral-derivative (PID) decoupling controller based on a modified output–input feedback (OIF) Elman neural model and multi-step prediction principle is proposed for the nonlinearity, time-lag, uncertainty and strong coupling characteristics of the system. A multi-step ahead prediction algorithm is presented for temperature prediction to eliminate the effects of time-delays. To avoid getting into a local optimization, an improved particle swarm optimization is applied to optimize the weights of the OIF Elman neural network during modeling. By using the modified OIF Elman neural network identifier, the DAFDV system is identified and the parameters of PID controller are tuned on-line. The experimental results for two typical cases indicate that the settling times are obviously shorten, steady-state performances are improved and more important is that one temperature no longer fluctuates along the other, which verify the proposed adaptive PID decoupling control is effective.     

改进的Elman模型与递归反传控制神经网络

在Elman网络的基础上提出了两种改进网络:输出-输入反馈Elman网络和输出-隐层反馈Elman网络模型,并以前者作为误差反传的通道,建立了递归反向传播控制神经网络模型.在Lyapunov稳定性意义下分别给出了改进网络的稳定性证明,得到了保证网络稳定收敛的最佳自适应学习速率.分别用Elman网络及其改进网络对超声马达进行了模拟.利用改进的Elman网络模型,除了可以较好地模拟马达速度以外,还得到了一些有意义的结果,据此可以根据现场数据采样的情况,选用不同的网络模型.模拟实验结果表明,递归反向传播控制神经网络对多种形式的超声马达参考速度都有很好的控制效果.     

引入惩罚收益因素OIF Elman神经网络及其应用*

通过在OIF Elman (Output-Input Feedback Elman)神经网络模型中引入惩罚收益因素,提出了一种基于OIF Elman神经网络的改进模型,并将其用于大气质量的预测和评价.实验模拟结果证明,引入惩罚收益因素OIF Elman模型能够明显提高网络的预测精度,具有极佳的逼近性能,所得预测数据和评价结果与实际结果基本吻合.利用该模型对大气质量进行预测和评价是可行而有效的,具有较好的应用潜能;并为大气环境整治规划提供了一种新的技术和方法.     

基于Elman网络的非线性系统神经元自适应预测控制

提出在非线性系统的E1man网络辨识模型的基础上，用单神经元设计预测控制器的方案。Elman网络在BP网络的基础上，加入反馈信号，利用内部状态反馈来描述系统的非线性动力学行为，提高了学习速度，适合于动态系统的实时辨识。神经元结构简单，且有很强的自学习和自适应能力，它根据系统的期望输出与一步超前预测输出之间的偏差，并通过某种特定的学习算法在线调整控制器的参数，使控制器能够适应对象参数的变化，从而实现对一类非线性系统的有效控制。仿真实验证明了该方案的有效性。     

基于PCA优化的神经网络飞机燃油消耗预测方法

针对传统方法存在的不足,提出了基于主成分分析法优化的Elman神经网络飞机燃油消耗预测方法。利用主成分分析法降低神经网络输入维数。构建主成分分析与Elman神经网络模型,进行基于飞参数据的实例分析,并将几种神经网络的预测效果进行了对比;提出了基于K-S检验法预测结果冗余修正法并进行了修正。误差指标和预测图像表明与主成分分析结合后Elman神经网络对飞机燃油消耗的预测性能优于其他传统神经网络,且K S检验法能够有效实现对预测结果的修正。     

一种改进的Eiman神经网络及其在股市中的应用

通过在具有动态反馈机制的Elman神经网络的基础上引入时间收益因素，提出了一种改进的Elman神经网络模型并将其用于对股票的综合指数进行预测，进而求其收益率。实验模拟结果表明：将改进的Elman模型用于股市投资是可行的，有效的，具有一定的应用潜能，谊模型不仅可以明显提高网络的预测精度，达到快速收敛。而且还能够明显提高股民投资的利润率，实现较大幅度地获得收益的目的。     

一种改进的Elman神经网络及其在股市中的应用

通过在具有动态反馈机制的Elman神经网络的基础上引入时间收益因素,提出了一种改进的Elman神经网络模型并将其用于对股票的综合指数进行预测,进而求其收益率。实验模拟结果表明:将改进的Elman模型用于股市投资是可行的,有效的,具有一定的应用潜能,该模型不仅可以明显提高网络的预测精度,达到快速收敛,而且还能够明显提高股民投资的利润率,实现较大幅度地获得收益的目的。     

一种引入混沌机制的新型Elman网络及其应用

针对一大类未知、时滞、高阶非线性动态系统的建模问题,提出了一种新的改进Elman网络模型——HF Elman,在Lyapounov稳定意义下证明了网络的稳定性,并在网络权值的训练过程中引入了混沌搜索机制,利用混沌固有的全局游动性有效地消除了Elman网络易陷入局部极值的缺点,改善了网络的学习性能。仿真结果表明,新的模型及算法有效提高了网络的训练速度及乙烯质量指标的预测精度。     

多变量自适应PID型神经网络控制器及其设计方法

提出一种PID型神经网络控制器（PID-like Neural Network Controller，PIDNNC）及其设计方法．基于PID的简单结构和良好性能优势以及神经网络的自调节和自适应的特长，创建一种具有PID结构的多变量自适应的PID型神经网络控制器．该网络控制器的隐含层由带有输出反馈和激活反馈的混合局部连接递归网络组成．通过定义误差函数作为设计目标，采用弹性BP算法，并用变化率以及弹性BP算法中的符号法来处理某些求导关系，获得适于实时在线调整网络权值的修正公式．根据李亚普诺夫稳定性定理推导出确保控制系统稳定的学习速率的取值范围．最后通过实例进一步说明所提出网络控制器的优越性．     

基于神经网络的自治水下机器人广义预测控制

针对自治式水下机器人高度非线性和时变性的特点,提出了一种基于神经网络的水下机器人广义预测控制策略．利用改进型Elman网络作为多步预测模型,在对网络学习算法进行改进的基础上,实现了Elman网络的在线学习,并提出了用于求解神经广义预测控制律的灵敏度公式．进行了具有神经网络在线学习功能和不具有在线学习功能的水下机器人的速度控制实验,并就预测控制效果进行了对比分析．实验结果表明,具有自适应学习功能的水下机器人速度控制法的精度要优于不具有在线学习功能的速度控制法,且当水下机器人动态特性发生变化时具有较强的自适应能力．     

A modified particle swarm optimization-based dynamic recurrent neural network for identifying and controlling nonlinear systems

In this paper, we first present a learning algorithm for dynamic recurrent Elman neural networks based on a modified particle swarm optimization. The proposed algorithm computes concurrently both the evolution of network structure, weights, initial inputs of the context units and self-feedback coefficient of the modified Elman network. Thereafter, we introduce and discuss a novel control method based on the proposed algorithm. More specifically, a dynamic identifier is constructed to perform speed identification and a controller is designed to perform speed control for Ultrasonic Motors (USM). Numerical experiments show that the novel identifier and controller based on the proposed algorithm can both achieve higher convergence precision and speed than other state-of-the-art algorithms. In particular, our experiments show that the identifier can approximate the USM’s nonlinear input–output mapping accurately. The effectiveness of the controller is verified using different kinds of speeds of constant, step and sinusoidal types. Besides, a preliminary examination on a randomly perturbation also shows the robust characteristics of the two proposed models.     

基于改进Elman网络的软测量建模方法

针对静态前馈网络和Elman网络在软测量建模中的不足,提出了一种新的改进的Elman网络模型,并将此模型应用于精馏塔出口成分含量的软测量建模中。实验模拟结果表明：改进的Elman网络模型具有更高的预测精度和较快的收敛速度,能够更好地实现精馏塔出口成分含量的软测量建模,为进一步实现产品质量控制提供了保证。     

基于Elman网络的时延预测及其改进

分析了网络传输时延的组成和特点,提出了利用Elman神经网络预测网络传输时延,运用Matlab软件对其预测进行仿真,结果证明Elman神经网络能很好地预测网络时延,为了进一步提高神经网络的逼近能力和动态特性,提出了一种改进的基于输入层、隐藏层、输出层神经元的动态递归神经网络。实验证明,改进的Elman神经网络比原来的网络具有更好的动态性能。     

基于改进Elmam神经网络的网络流量预测模型

提出了一种改进Elman动态回归神经网络,在此基础上建立了一种网络流量预测模型,该模型相对于传统的线性模型和BP神经网络模型具有更高的预测精度和更好的自适应性,利用某大学校园网统计得到的实际网络流量数据进行仿真实验,结果表明该模型具有良好的预测效果。     

基于AQPSO算法优化的Elman网络模型及其应用

Elman神经网络是一种典型的递归神经网络。提出了自适应量子粒子群优化（Adaptive Quantum-Behaved Particle Swarm Optimization,AQPSO）算法,用于训练Elman网络参数,改进了Elman网络的泛化能力。利用中集集团股票数据进行预测,实验结果表明,采用AQPSO算法获得的Elman网络模型不但具有很强的泛化能力,而且具有良好的稳定性,在股票数据预测中具有一定的实用价值。     

Robust stochastic moment control via genetic-pole placement in communication network parameter setting

In this paper, the problems of stochastic robust approximate covariance assignment and robust covariance feedback stabilization, which are applied to variable parameters of additive increase/multiplicative decrease (AIMD) networks, are considered. The main idea of the developed algorithm is to use the parameter settings of an AIMD network congestion control scheme, where parameters may assign the desired network’s window covariance, with respect to the current network conditions. The aim is to search for the optimal AIMD parameters of a feedback gain matrix such that the objective functions defined via appropriate robustness measures and covariance assignment constraints can be optimized using an adaptive genetic algorithm (AGA). It is shown that the results can be used to develop tools for analyzing the behavior of AIMD communication networks. Quality of service (QoS) and other performance measures of the network have been improved by using the proposed congestion control. The accuracy of the controller is demonstrated by using MATLAB and NS software programs.     

不同节点动态的复杂网络外部同步牵制控制

研究节点动态不同的两个复杂网络的外部同步问题。运用牵制控制方法,网络模型选取节点输出线性耦合模型,基于输出控制思想,设计结构简单的牵制控制器,对响应网络中的部分节点施加输出反馈控制,使得两个复杂动态网络达到外部同步,即实现响应网络与驱动网络的渐近同步。根据李雅普诺夫稳定性理论,推出相应的同步准则,得到控制器参数选择条件。仿真时,驱动网络和响应网络分别选取Lorenz系统和Lu系统,对全局耦合网络和最近邻耦合网络两个典型网络拓扑进行仿真,验证了所提方法的有效性。     

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。     

CDM-based design and performance evaluation of a robust AQM method for dynamic TCP/AQM networks

A new robust AQM strategy for dynamically varying TCP/AQM networks is proposed and its performance is investigated through computer simulations in MATLAB and ns-2 environments. The developed AQM is designed based on coefficient diagram method (CDM), which is a new indirect pole placement method that considers the speed, stability and robustness of the closed loop system in terms of time domain specifications. Simulation results indicate that the new method (CDM-AQM) performs very well for network variations both in topology and traffic. Besides, a new adaptive controller based on CDM as an AQM method is introduced. In the developed adaptive AQM (ACDM), the output feedback pole placement is implemented in an indirect model reference adaptive control (MRAC) scheme, in which the closed loop characteristic polynomial is determined by CDM and the system parameters are estimated using a modified recursive gradient method. This method preserves the existing features of CDM controller in the control of networks with unknown or time-varying parameters. Simulation results illustrate high capability of the controller in coping with the network variations.     

Control of Nonlinear Systems Using a Self-Organising Neural Network

Two applications of Self Organising Map (SOM) networks in the context of nonlinear control are introduced, one in approximate feedback linearisation and the second in optimal control. It is shown that a modified SOM can be used to approximately Input/Output (I/O) linearise and to control nonlinear systems using a combination of the SOM learning algorithm, and a biologically inspired optimisation algorithm known as chemotaxis. A proof to guarantee the stability of the closed loop during the training of the network and the operation of the whole system is included. The results are illustrated with simulations of a single link manipulator.