基于神经网络的模糊推理

为了使模糊推理符合推理原则，目前已定义了１０多种模糊关系，但各种模糊关系定义都存在一定的缺陷。本文提出的基于神经网络的模糊推理，能很好地符合模糊推理原则。     

Fuzzy Entropy： Axiomatic Definition and Neural Networks Model

The measure of uncertainty is adopted as a measure of information. The measures of fuzziness are known as fuzzy information measures. The measure of a quantity of fuzzy information gained from a fuzzy set or fuzzy system is known as fuzzy entropy. Fuzzy entropy has been focused and studied by many researchers in various fields. In this paper, firstly, the axiomatic definition of fuzzy entropy is discussed. Then, neural networks model of fuzzy entropy is proposed, based on the computing capability of neural networks. In the end, two examples are discussed to show the efficiency of the model.     

基于模糊聚类分析的小波神经网络模型在径流预测中的应用

提出了一种在对预报因子集进行模糊聚类分析基础上构建径流预测模型的新方法:先通过模糊C-均值聚类将历史径流数据进行分类,然后利用小波神经网络分别建立预报因子集类别变量特征值与观测值之间的局部预测模型,并设计了特征值分类识别器,自动搜寻相适应的局部网络模型进行预测.通过西南某水库2011年日平均入库来流的计算实例对简单小波神经网络预测模型和所建的基于FCM与小波神经网络的预测模型进行了比较,结果较为满意.     

Performance Analysis of Adaptive Genetic Algorithms with Fuzzy Logic and Heuristics

In this paper, we propose some genetic algorithms with adaptive abilities and compare with them. Crossover and mutation operators of genetic algorithms are used for constructing the adaptive abilities. All together four adaptive genetic algorithms are suggested: one uses a fuzzy logic controller improved in this paper and others employ several heuristics used in conventional studies. These algorithms can regulate the rates of crossover and mutation operators during their search process. All the algorithms are tested and analyzed in numerical examples. Finally, a best genetic algorithm is recommended.     

基于GA-BP的模糊神经网络控制器与Elman辨识器的系统设计

提出了一种基于神经网络的模糊控制系统 ,该系统由模糊神经网络控制器和模型辨识网络组成 .文中介绍了模糊神经网络控制器采用遗传算法离线优化与 BP算法在线调整 ,给出了具体控制算法 ,推导了变形 Elmam网络的系统辨识算法 .仿真结果表明了此法的可行性和有效性 .     

故障诊断中模糊神经网络的应用研究

文章给出了利用模糊神经网络诊断故障的数学模型、基本原理、方法、步骤 ,和模糊网络的学习流程 ,并利用梯度法推导出两种诊断算法 ;在对某发动机滑油典型故障样本的仿真过程中 ,结果完全正确 ,对非样本故障的仿真 ,准确率达 90 % .     

A Learning Framework for Neural Networks Using Constrained Optimization Methods

Conventional supervised learning in neural networks is carried out by performing unconstrained minimization of a suitably defined cost function. This approach has certain drawbacks, which can be overcome by incorporating additional knowledge in the training formalism. In this paper, two types of such additional knowledge are examined: Network specific knowledge (associated with the neural network irrespectively of the problem whose solution is sought) or problem specific knowledge (which helps to solve a specific learning task). A constrained optimization framework is introduced for incorporating these types of knowledge into the learning formalism. We present three examples of improvement in the learning behaviour of neural networks using additional knowledge in the context of our constrained optimization framework. The two network specific examples are designed to improve convergence and learning speed in the broad class of feedforward networks, while the third problem specific example is related to the efficient factorization of 2-D polynomials using suitably constructed sigma-pi networks.     

Toward Fuzzy Optimization without Mathematical Ambiguity

Fuzzy programming has been discussed widely in literature and applied in such various disciplines as operations research, economic management, business administration, and engineering. The main purpose of this paper is to present a brief review on fuzzy programming models, and classify them into three broad classes: expected value model, chance-constrained programming and dependent-chance programming. In order to solve general fuzzy programming models, a hybrid intelligent algorithm is also documented. Finally, some related topics are discussed.     

变时滞随机模糊细胞神经网络稳定性分析(英文)

本文旨在研究一类带变时滞的随机模糊细胞神经网络的稳定性.通过构造恰当的Lyapunov泛函并运用线性矩阵不等式(LMI)理论,作者给出了保证这类神经网络全局渐近稳定的充分条件.本文推导出两个定理:一个用以判定文中模型的全局渐进稳定性,一个用以判定该模型在均方意义下的全局渐近稳定性.     

遗传算法与神经网络相结合的降水预报模型

针对目前BP神经网络在实际应用中,网络结构难以确定以及网络极易陷入局部解问题,用遗传算法优化神经网络的连接权和网络结构,在遗传进化过程中采取保留最佳个体的方法,建立基于遗传算法的BP网络模型,同时通过实例说明该模型在降水预测中的应用,计算结果表明该方法的预测精度较高。     

Approximate String Matching Using Deformed Fuzzy Automata: A Learning Experience

Deformed fuzzy automata are complex structures that can be used for solving approximate string matching problems when input strings are composed by fuzzy symbols. Different string similarity definitions are obtained by the appropriate selection of fuzzy operators and parameters involved in the calculus of the automaton transitions. In this paper, we apply a genetic algorithm to adjust the automaton parameters for selecting the ones best fit to a particular application. This genetic approach overcomes the difficulty of using common optimizing techniques like gradient descent, due to the presence of non-derivable functions in the calculus of the automaton transitions. Experimental results, obtained in a text recognition experience, validate the proposed methodology.     

军队知识管理模糊神经网络评估

根据军队知识管理的特点,构建了军队知识管理水平评价指标体系,指标体系从组织结构、人力、技术及知识系统4个一级指标和12个二级指标体系,运用四层模糊神经网络确定模糊综合评价中的权重值,同时采用改进的反向传播算法,用样本对网络进行训练,逐步修正网络的连接权值,使权重值更符合实际情况,最后用训练好的样本对六个单位的知识管理进行评估,结果表明,训练好的模糊神经网络可以对军队的知识管理进行评估,并得到很好的结果。     

模糊环境下的柔性工作车间调度模型的研究

本首先引入了柔性生产系统下的调度过程中存在的不确定性问题，接着对存在模糊操作时间间隔的柔性工作车间调度问题及相关概念进行了描述，并且给出了以最小makespan为目标的基于模糊逻辑和遗传优化的调度模型，最后通过实例验证了模型的可行性。     

关于多层前馈神经网络学习能力的一个注记

给出一种通过适当地选择输入层与隐层间的连接权,来减少单隐层前馈型神经网络隐层节点的个数的方法.应用此方法,分析了具有两个隐层节点的标准单隐层网络的学习能力,并对二元和三元XOR问题中的权值的选择问题进行了详细的讨论.     

基于群决策模糊聚类和模糊神经网络的建筑分包商选择研究

把建筑分包商的选择分为两个阶段,包括预选择阶段和决策选择阶段,并分别建立了两个阶段的评价准则体系.然后,基于群决策模糊聚类、群决策模糊神经网络两种模型和方法,给出了建筑分包商预选择和决策选择的具体实施步骤.最后的实证分析表明,对于建筑分包商的选择,该选择过程是实用和有效的.     

随机变时滞模糊神经网络的均方指数稳定性

利用Lyapunov泛函和随机分析的方法,研究了一类具有变时滞随机模糊细胞神经网络的均方指数稳定性,得到了这类神经网络均方指数稳定性的充分条件.数值例子说明了得到的结果的有效性.     

遗传算法优化神经网络的汛期降水模型

针对目前神经网络在实际应用中,网络结构难以确定以及网络极易陷入局部解问题,用遗传算法优化神经网络的连接权和网络结构,并在遗传进化过程中采取保留最佳个体的方法,建立基于遗传算法的神经网络模型,实例研究结果表明该方法可以取得较高的预测精度.     

一种新型的模糊神经网络及其应用

本文提出了一种新型的模糊神经网络，从理论上论证了其推理的合理性和逼近能力，同时应用于系统辩识，取得较好的效果。     

飞行事故的一种自适应模糊神经网络预测方法研究

飞行事故预测对于预防飞行事故具有十分重要的意义.首先系统分析了空军飞行事故的主要影响因素,对其中的定性因素进行了量化;然后利用系统分析的成果和历史统计数据建立了空军飞行事故的自适应模糊神经网络预测模型.整个预测过程突破了纯数学模型预测的局限性,实现了预测的定性和定量的结合;由于预测中使用了一种基于高木.关野模糊模型的自适应模糊神经网络,从而使预测模型具有很强的自适应能力,预测结果也比较令人满意.     

模糊神经网络方法在定点定量降水预报中的应用研究

以单站24小时降水量作为预报对象,采用模糊神经网络方法进行了新的数值预报产品释用预报方法研究.首先通过对T 213、ECMW F预报因子场以及高空气象探测资料进行处理,有效浓缩多种物理量因子场的实况及预报信息,并进一步建立了南宁、桂林、河池、百色4站的降水模糊神经网络释用预报模型.运用与实际业务相同的预报方法对2006年6—8月进行逐日的降水量预报试验,并与相同时次的T 213降水预报产品进行对比分析.结果表明,4个单站的定点、定量模糊神经网络降水预报模型,在预报性能上明显优于同期T 213数值预报模式的降水预报结果.