基于函数连接神经网络的传感器Hammerstein模型辨识研究

针对非线性动态传感器模型辨识问题,提出利用函数连接神经网络算法对非线性系统的Hammerstein模型进行一步辨识的方法。以多项式逼近传感器中的静态非线性环节,同时结合动态线性环节的差分方程,建立关于直接输入输出的离散数据表达式,利用改进FLANN训练求解Hammerstein模型参数。采用变学习因子的方法对FLANN算法进行改进,提高了收敛速率和稳定性。实验结果表明,该辨识方法简单有效且具有更快的收敛速度。     

基于模糊神经网络的建筑结构系统辨识

本文提出一种基于模糊神经网络和建筑结构系统辨识方法。利用模糊神经网络强大的非线性映射能力与学习能力以实测的结构动力响应数据建立起结构的动力特性模型。不但可以克服以往传统与智能辨识方法中存在的种种弊病,而且还将土一结构相互作用以及结构自身非线性对结构动力特性的影响考虑在内,使得结构系统辨识更具客观性。具有物理意义明确,可扩展性强,能够用于实时在线控制与健康诊断等优点。     

遗传算法在非线性回归模型辨识中的应用

对遗传算法在非线性回归模型辨识中的应用进行了探讨，切削温度回归模型辨识的实例表明，该方法是有效的。     

非线性振动系统神经网络自适应控制方法研究

将人工神经网络理论引入振动控制工程领域，并将现代控制理论中的状态反馈理论与人工神经网络理论相结合，提出了一种基于ＢＰ网络的自适应控制方法。给出了该方法的学习算法和网络参数选择原则，分析了它在建模和控制方面所具有的优点，并就典型的非线性振动ＶａｎＤｅｌＰｏｌ和Ｄｕｆｉｎｇ方程进行了辨识和控制，仿真结果表明该方法对于非线性振动系统具有较强的辨识和控制能力。     

基于最小二乘支持向量机的传感器非线性动态系统辨识

讨论了一种基于最小二乘支持向量机的非线性动态传感器系统辨识方法,并给出了相应的推导过程和学习算法.首先,将传感器的非线性动态系统分解为静态非线性子环节和动态线性子环节串联--Hammerstein模型;然后,建立类似线性的中间模型,通过该模型能将Hammerstein模型的非线性传递函数转换为等价的类线性形式;再通过LS-SVM线性回归算法求取中间模型参数;最后推导出中间模型参数与Hammerstein模型参数之间的关系,并通过该关系反演出原传感器系统的Hammerstein模型参数,实现传感器非线性动态辨识.仿真与实际传感器系统辨识的实验结果均表明该方法可行.     

基于模糊逻辑的舰船维修经费预测

针对多输入、单输出的复杂非线性系统，基于Takagi-Sugeno模糊规则给出了一种系统预测模型，分别用模糊C- 值聚类算法和线性回归方法导出模型参数。利用该模型对舰船维修经费进行了预测，并进行了精度分析。     

一种辨识Hammerstein模型的新方法

为了提高非线性Hammerstein模型的辨识精度,提出一种利用混合优化算法对非线性模型进行辨识的新方法。该算法的基本思想是把非线性系统的参数辨识问题转化为参数空间上的函数优化问题,然后利用遗传算法和改进的粒子群优化算法相结合寻求并获得参数问题的最优解。最后通过仿真研究表明,该方法对于非线性辨识具有较好的有效性和鲁棒性,获得了良好的辨识效果,是一种可行的解决非线性辨识问题的方法。     

一类混杂系统的模糊建模方法

针对混杂系统的非线性特性,提出利用模糊推理规则描述动态混杂系统。根据系统的实际输入输出数据,通过GK聚类算法和最小二乘辨识方法得到了混杂系统的T—S模糊模型。基于建立的等价T—S模糊模型,分别与实际模型和MLD模型进行比较,仿真结果表明,用模糊推理建模方法得到的混杂系统的模型关于真实模型具有较高的逼近精度。     

基于B样条函数的模糊神经网络

通过研究Ｂ样条函数在模糊系统和神经网络系统中的应用，探讨了通过Ｂ样条函数，结合模糊系统和神经网络的各自特点，构造模糊神经网络的方法，并提出了具体的网络模型以及相应的学习方法。     

基于部分可辨识振动系统的载荷恢复方法

在复模态分析和参数辨识的基础上,对部分可辨识振动系统的载荷识别问题进行了研究,提出了基于部分可辨识复模态参数的载荷恢复方法。恢复模型存在幅值模糊和相位模糊,不存在排列模糊。数值仿真验证了该方法的有效性,并讨论了提高恢复精度的方法。     

模糊聚类分析在模糊神经网络结构优化中的应用

研究了模糊聚类分析在多变量模糊神经网络的结构确定中的应用,在传统的模糊C－均值算法的基础上,给出了一个衡量聚类有效性的函数和确定模糊指数的启发式方法,并给出了应用该算法的具体的模糊神经网络模型。     

基于混合智能的电火花加工电参数学习模型的研究

提出了一个基于混合智能的电火花加工电参数学习模型,它模仿熟练操作者的决策过程,由于工艺数据库、加工规则库、学习模块和推理模块组成。在学习模块中利用遗传算法从工艺数据库中抽取出反映电参数和加工结果之间关系的模糊产生式规则,存储在规则库中。推理模块基于这些规则利用模糊拄是对新加的要求提供合适的电参数。     

An efficient genetic algorithm for TSK‐type neural fuzzy identifier design

Abstract

In this paper, an efficient genetic algorithm (EGA) of the Takagi‐Sugeno‐Kang (TSK) ‐type neural fuzzy identifier (TNFI) is proposed for solving various identification problems. For the proposed EGA method, the better chromosomes will be initially generated while the better mutation points will be determined to perform efficient mutation. The advantages of the proposed learning algorithm are that, first, it converges quickly and the obtained fuzzy rules are precise. Secondly, the proposed EGA method only requires a small population sizes.     

基于混沌优化的板形信号模式识别的研究

针对传统的基于最小二乘法板形信号模式识别方法抗千扰能力差、精度低,神经网络识别方法在实际应用中效果不佳的问题,通过对板形信号和板形识别数学模型的分析,首先将板形信号模式识别过程转化为函数的优化问题。为提高板形信号识别的精度和速度,以勒让德正交多项式作为板形缺陷的基模式,用模糊识别理论与混沌优化方法对该函数进行优化求解。采用模糊理论作为初步识别,用以降低混沌优化的求解维数和缩小搜索空间,借助梯度下降法的思想对混沌优化的局部搜索能力进行改善,从而进一步提高了混沌优化对板形信号模式识别的识别速度和精度。     

A fuzzy model of the penetration resistance of concrete targets

The penetration resistance of a concrete target varies greatly with the strike velocity of the projectile from low and intermediate impact velocities to high impact velocities. A fuzzy model of the penetration resistance of a concrete target is proposed to describe this characteristic. A complete analysis is conducted of the penetration process during which a rigid projectile penetrates a semi-infinite concrete target based on the proposed fuzzy model. Good agreement is observed between the experimental and predicted results based on the proposed fuzzy model.     

双模模糊滑模控制裹包机交流转矩系统

针对接缝式裹包机交流伺服系统控制精度差的问题,采用了双模模糊滑模变结构控制器,仿真结果表明该方案有效地消除了抖动问题,具有优良的动静态性能,证明了双模模糊滑模变控制方法的合理和优越。     

应用自适应模糊神经网络进行摩擦补偿的研究

在分析了摩探性及其对伺服系统低速特性的影响的基础上,提出了一种基于自适应模糊神经网络的摩探辨识和补偿方法,该方法既可实现摩探力矩的在线辨识和补偿,又能保证系统的稳定性。仿真结果表明,该方法是有效的,而且便于工程应用。     

Adaptation of TS fuzzy models without complexity expansion: HOSVD-based approach

One direction of measured data-set based modeling applies fuzzy logic identification tools and results in a fuzzy rule-base model. A typical problem of fuzzy identification methods is that the complexity of the resulting fuzzy rule-base, namely the number of rules in the rule-base, explodes with the modeling accuracy. As a result, the topic of fuzzy rule-base complexity reduction techniques emerged in the last decade. A common disadvantage of fuzzy rule-base complexity reduction methods is that the resulting complexity minimized fuzzy-rule bases cannot be simply adapted to new information. If we have new information that cannot be described by the fuzzy rules of the complexity minimized fuzzy rule-base, then we have two choices. The first choice is to add new fuzzy rules to the fuzzy rule-base until the new information can be described. The second choice is to modify the new information until it can be described by the fuzzy rule-base without using additional fuzzy rules. This second case has the prominent role if the number of fuzzy rules in the fuzzy rule-base is limited. This paper proposes a method for the second choice. The proposed method minimizes the necessary modification of the new information. This paper focuses attention on a recent complexity reduction method, termed Higher Order Singular Value Decomposition (HOSVD)-based complexity reduction, and Takagi-Sugeno (TS) inference operator-based fuzzy rule-bases. An example is used to provide the validation of the proposed method. In order to demonstrate the effectiveness of the proposed method, a control system of a differential-steered automatic guided vehicle is modeled in the paper.     

模糊聚类分析法及计算机实现

模糊聚类分析法是一种适用于机械制造中的多品种、中小批量条件下精节生产的零件分类成组的新方法。具有根据市场变化而变化的动态特征。本文给出了用模糊等价关系来评价零件之间相似性的模糊和计算机辅助分类成组过程。     

A fuzzy expected value-based goal programing model for product planning using quality function deployment

Product planning is one of four important processes in new product development using quality function deployment (QFD), which is a widely used customer-driven approach. In this article, a hierarchical framework for product planning using QFD is developed. To tackle the fuzziness in functional relationships between customer requirements and engineering characteristics (ECs) in product planning, the least squares method is incorporated into fuzzy regression to investigate those functional relationships, by which a more central tendency can be obtained. Furthermore, a fuzzy expected value-based goal programing model is proposed to specify target values of ECs. Different from some fuzzy product planning approaches for QFD, the proposed programing model has unambiguous interpretations. An illustrated example of a quality improvement problem of emulsification dynamite-packing machine design is given to demonstrate the application and performance of the proposed approach.