基于过程神经元网络的动态预测模型及其应用

〗针对动态系统过程预测预报问题，提出了一种基于过程神经元网络的动态预测方法．过程神经元网络的输入/输出均可以是时变函数，其时空聚合运算和激励可同时反映时变输入信号的空间聚合作用和输入过程中的阶段时间累积效应．基于过程神经元网络的动态预测模型能同时满足对系统的非线性辨识和过程预测，在机制上对动态预测预报问题有较好的适应性．文中给出了基于函数基展开和梯度下降法的学习算法，以电力负荷预报为例验证了模型和算法的有效性．     

新激活函数下前馈型神经网络及其在天气预报中的应用

本文为提高基于ＢＰ算法的人工神经元网络的学习速度，提出新组合激活函数并取得了显著效果的基础上，又应用于天气预报中，并与基于ＢＰ算法的神经网络（标准和带动量项）以及多自适应性单元的神经元网络进行仿真比较，在预报准确纺和学习速度方面获得了令人比较温度的结果，本模拟程序在Ｔｕｒｂｏ－Ｐａｓｃａｌ／６．０环境下编制，在ＩＢＭ ＰＣ３８６和４８６机器上调试通过并运行。     

中国自动化学会第十一届青年学术年会( YAC’9 6) 征文通知

中国自动化学会第十一届青年学术年会将于１９９６年８月中旬召开（会址为武夷山市），这又将是一次促进我国自动化界青年科技工作者迅速成长，促进自动控制及相关学科青年学者学术交流的盛会．届时还将邀请国内有关专家、学者做综述或专题报告，组织专题讨论；同时还将举办小型高新技术产品展示会．一、征文范围（１）线性与非线性系统控制；（２）自适应控制、最优控制；（３）智能控制、模糊控制与专家系统；（４）系统辨识、滤波与预报；（５）故障诊断与容错控制；（６）神经元网络及其应用；（７）工业自动化仪表与过程控制；（８）计…     

工业锅炉燃烧过程智能控制系统

针对典型的大时滞，非线形的工业锅炉燃烧控制系统．本文提出了一种基于PID神经元网络的工业锅炉燃烧控制系统．在仿真实验的基础上。对PID神经元网络控制与传统的PID控制进行比较和分析，仿真结果表明．PID神经元网络控制方法具有良好的鲁棒性和抗干扰性。其控制效果优于传统的PID解耦控制。     

基于自校正支持向量回归的锌产量在线预报模型及应用

提出了基于自校正支持向量回归的密闭鼓风炉锌产量在线预报模型，以便根据预报结果来调整参数，实现锌产量最大．在该模型中，支持向量回归的数学模型被转换成与支持向量分类一样的格式，然后采用简化的SMO方法训练回归系数向量a-a*和阈值b，并在训练过程中动态调整惩罚系数C．最后，给出锌产量的在线预报算法．仿真结果表明，该预报模型在只有较少的样本数的情况下，在有效误差范围内预报精度能达到90％，且具有很好的实时性．     

氧化铟半导体薄膜厚度控制的支持向量回归模型

将支持向量回归（SVR）方法用于氧化铟薄膜的厚度控制。取已有的实验数据作为模式识别训练样本，以样品中氧化铟的重量百分含量，原料的粘度，添加剂的重量百分含量以及两个处理工艺条件提拉速度和提拉次数作为特征变量，得到了用于计算薄膜厚度的回归方程式。用“留一法”检验所得数学模型的预报能力，并将结果与传统的模式识别方法（Fisher法和KNN）进行了比较，结果表明：SVR的预报准确率比Fisher和KNN方法高。因此SVR方法有望成为一种新的实验设计的手段。     

杀幼（虫）剂1－（Substitutedbenzoyl）－2－benzoyl－1－tert－butylhydrazines的QSAR研究

使用ＣＡＳＡＣ软件中的逐步回归和改进的神经网络（ＡＮＮ）方法，对Ｎ．Ｏｉｋａｗａ等研究合成的杀幼（虫）剂进行了计算．其中，４４个化合物作为训练基，１１个化合物作为未知样本，获得良好的预报结果，与Ｎ．Ｏｉｋａｗａ等使用Ｈａｎｓｃｈ方法计算所取得的结论一致．不同的是本文所使用的物化参数除Ｂ５和Ｌ１之外，都能够方便的计算．改进的神经网络（ＡＮＮ）方法提高了模型质量和预报结果的精度．     

基于粒子群优化和支持向量机的花粉浓度预测模型

为了提高花粉浓度预报的准确率，解决现有花粉浓度预报准确率不高的问题，提出了一种基于粒子群优化（PSO）算法和支持向量机（SVM）的花粉浓度预报模型。首先，综合考虑气温、气温日较差、相对湿度、降水量、风力、日照时数等多种气象要素，选择与花粉浓度相关性较强的气象要素构成特征向量；其次，利用特征向量与花粉浓度数据建立SVM预测模型，并使用PSO算法找出最优参数；然后利用最优参数优化花粉浓度预测模型；最后，使用优化后的模型对花粉未来24 h浓度进行预测，并与未优化的SVM、多元线性回归法（MLR）、反向神经网络（BPNN）作对比。此外使用优化后的模型对某市南郊观象台和密云两个站点进行逐日花粉浓度预测。实验结果表明，相比其他预报方法，所提方法能有效提高花粉浓度未来24 h预测精度，并具有较高的泛化能力。     

一种分式过程神经元网络及其应用研究

针对带有奇异值复杂时变信号的模式分类和系统建模问题，提出了一种分式过程神经元网络．该模型是基于有理式函数具有的对复杂过程信号的逼近性质和过程神经元网络对时变信息的非线性变换机制构建的。其基本信息处理单元由两个过程神经元成对偶组成。逻辑上构成一个分式过程神经元，是人工神经网络在结构和信息处理机制上的一种扩展．分析了分式过程神经元网络的连续性和泛函数逼近能力，给出了基于函数正交基展开的学习算法．实验结果表明，分式过程神经元网络对于带有奇异值时变函数样本的学习性质和泛化性质要优于BP网络和一般过程神经元网络。网络隐层数和节点数可较大减少，且算法的学习性质与传统BP算法相同．     

一个基于BP网络的字符识别器

本文简单介绍了人工神经元网络的背景知识,提出了一种利用传统BP（Back-Propagation误差逆传播）网络识别印刷字符的方法,用C语言对其进行了实现．在进行了大量实验之后,实验结果表明该字符识别器具有较好的有效性和正确性,能够在合理的误差范围内以较好的效率成功识别字符．     

离散时间反馈神经网络的渐近行为研究

Hopfield神经网络是一类应用非常成功的人工神经网络模型，它是研究这个反馈神经网络的基础．该文主要研究离散时间、连续状态的反馈神经网络，它是Hopfield神经网络的推广．众所周知，研究反馈神经网络的稳定性不仅被认为是神经网络最基本、最主要的问题之一，同时也是神经网络各种应用的基础．文中主要研究离散时间反馈神经网络的稳定性，给出了连接权矩阵非对称的并且输入-输出函数是一般的S-函数的新的渐近收敛性条件及相应的收敛性结论．所获结果不仅推广了一些已有的结论，而且为反馈神经网络的应用提供了一定的理论基础．     

Multilayer recurrent neural networks for on-line synthesis of asymptotic state estimators for linear dynamic systems

Two multilayer recurrent neural networks are presented for on-line synthesis of asymptotic state estimators for linear dynamical systems. The first recurrent neural network is composed of two layers to compute output gain matrices with desired poles. The second recurrent neural network is composed of four layers to compute output gain matrices with desired poles and minimal norm. The proposed multilayer recurrent neural networks are shown to be capable of synthesizing asymptotic slate estimators for linear dynamic systems in real time. The operating characteristics of the recurrent neural networks for state estimation are demonstrated by three illustrative examples     

Recurrent neural networks for minimum infinity-norm kinematiccontrol of redundant manipulators

This paper presents two neural network approaches to minimum infinity-norm solution of the velocity inverse kinematics problem for redundant robots. Three recurrent neural networks are applied for determining a joint velocity vector with its maximum absolute value component being minimal among all possible joint velocity vectors corresponding to the desired end-effector velocity. In each proposed neural network approach, two cooperating recurrent neural networks are used. The first approach employs two Tank-Hopfield networks for linear programming. The second approach employs two two-layer recurrent neural networks for quadratic programming and linear programming, respectively. Both the minimal 2-norm and infinity-norm of joint velocity vector can be obtained from the output of the recurrent neural networks. Simulation results demonstrate that the proposed approaches are effective with the second approach being better in terms of accuracy and optimality     

Almost Sure Exponential Stability of Recurrent Neural Networks With Markovian Switching

This paper presents new stability results for recurrent neural networks with Markovian switching. First, algebraic criteria for the almost sure exponential stability of recurrent neural networks with Markovian switching and without time delays are derived. The results show that the almost sure exponential stability of such a neural network does not require the stability of the neural network at every individual parametric configuration. Next, both delay-dependent and delay-independent criteria for the almost sure exponential stability of recurrent neural networks with time-varying delays and Markovian-switching parameters are derived by means of a generalized stochastic Halanay inequality. The results herein include existing ones for recurrent neural networks without Markovian switching as special cases. Finally, simulation results in three numerical examples are discussed to illustrate the theoretical results.     

Rule revision with recurrent neural networks

Recurrent neural networks readily process, recognize and generate temporal sequences. By encoding grammatical strings as temporal sequences, recurrent neural networks can be trained to behave like deterministic sequential finite-state automata. Algorithms have been developed for extracting grammatical rules from trained networks. Using a simple method for inserting prior knowledge (or rules) into recurrent neural networks, we show that recurrent neural networks are able to perform rule revision. Rule revision is performed by comparing the inserted rules with the rules in the finite-state automata extracted from trained networks. The results from training a recurrent neural network to recognize a known non-trivial, randomly-generated regular grammar show that not only do the networks preserve correct rules but that they are able to correct through training inserted rules which were initially incorrect (i.e. the rules were not the ones in the randomly generated grammar)     

递归神经网络的结构研究

从非线性动态系统的角度出发，对递归动态网络结构及其功能进行详尽的综述。将递归动态网络分为三大类：全局反馈递归网络、前向递归网络和混合型网络。每一类网络又可分为若干种网络。给出了每种网络描述网络特性的结构图，同时还对多种网络进行了功能对比，分析了各种网络的异同。     

Memetic evolutionary training for recurrent neural networks: an application to time-series prediction

Abstract: Artificial neural networks are bio-inspired mathematical models that have been widely used to solve complex problems. The training of a neural network is an important issue to deal with, since traditional gradient-based algorithms become easily trapped in local optimal solutions, therefore increasing the time taken in the experimental step. This problem is greater in recurrent neural networks, where the gradient propagation across the recurrence makes the training difficult for long-term dependences. On the other hand, evolutionary algorithms are search and optimization techniques which have been proved to solve many problems effectively. In the case of recurrent neural networks, the training using evolutionary algorithms has provided promising results. In this work, we propose two hybrid evolutionary algorithms as an alternative to improve the training of dynamic recurrent neural networks. The experimental section makes a comparative study of the algorithms proposed, to train Elman recurrent neural networks in time-series prediction problems.     

Improved conditions for global exponential stability of recurrent neural networks with time-varying delays

This paper presents new theoretical results on global exponential stability of recurrent neural networks with bounded activation functions and time-varying delays. The stability conditions depend on external inputs, connection weights, and time delays of recurrent neural networks. Using these results, the global exponential stability of recurrent neural networks can be derived, and the estimated location of the equilibrium point can be obtained. As typical representatives, the Hopfield neural network (HNN) and the cellular neural network (CNN) are examined in detail.     

递归神经网络的设计与应用

结合实例,给出了递归神经网络的完整设计步骤,包括网络结构的选定,学习算法的选择和网络参数的训练过程。重点研究了学习速率的初始值选取及其调整顺序。给出的递归网络的设计方法,可以适用于多种递归神经网络。     

Exponential Synchronization of Memristive Chaotic Recurrent Neural Networks Via Alternate Output Feedback Control

This paper considers the global exponential synchronization problem of two memristive chaotic recurrent neural networks with time‐varying delays using periodically alternate output feedback control. First, the periodically alternate output feedback control rule is designed for the global exponential synchronization of two memristive chaotic recurrent neural networks. Then, according to the Lyapunov stability theory, we construct an appropriate Lyapunov‐Krasovskii functional to derive several new sufficient conditions guaranteeing exponential synchronization of two memristive chaotic recurrent neural networks under periodically alternate output feedback control. Compared with existing results on synchronization conditions on the basis of linear matrix inequalities of memristive chaotic recurrent neural networks, the derived results complement, extend earlier related results, and are also easy to validate in this paper. An illustrative example is provided to illustrate the effectiveness of the synchronization criteria.