Influence of Defuzzification Methods on the Rate of Tuning a Fuzzy Model

The results of computer experiments performed to determine the influence of defuzzification methods on the rate of tuning fuzzy models are presented. The experiments were conducted for the defuzzification methods of the center of gravity and center of maxima and for the median method. The defuzzification method of the center of gravity was found to be the best method providing the highest tuning rate and exactness.     

模糊控制系统的Matlab仿真过程

以一个车辆速度控制系统为例，阐述了使用Matlab仿真模糊控制系统的一般步骤。通过仿真试验，着重介绍了模糊控制环节各个要素对控制系统的影响。     

线阵干涉仪解模糊算法研究

针对线阵干涉仪在测向过程中由于相位周期性模糊导致的测向模糊问题,比较了长短基线法和统计相位方差法的不同特点。在不同信噪比条件下及不同短基线间距条件下,对两方法进行理论分析与仿真对比。结果表明,在低信噪比条件下统计相位方差法相对于长短基线法有较高的解模糊准确度和稳定度,对信号的适应能力强。而短间距的改变对统计相位方差法的测量误差影响大。     

On methods of defuzzification of parametrically represented fuzzy numbers

A comparative analysis of such methods of defuzzification of fuzzy numbers as WABL (Weighted Averaging Based on Levels), centroid, and mean of maxima (MOM) is presented in the study. Analytic formulas are presented for calculating the defuzzification values for parametrically represented fuzzy numbers of triangular and trapezoidal form.     

模糊控制在除氧系统中的应用

除氧系统具有多输入、多输出、大滞后、时变性、非线性等一系列特点,除氧器的温度和压力相互影响,是一种强耦合系统,其精确数学模型难以建立。为了达到除氧目的,必须保证温度和压力的恒定,而常规的基于PID算法的控制器很难保证运行指标。提出了一种基于模糊控制理论的设计方法,采用M at-lab对设计的系统进行仿真,结果表明:模糊控制效果优于传统的PID控制。     

Developments of fuzzy PID controllers

Abstract: This paper describes the development and tuning methods for a novel self-organizing fuzzy proportional integral derivative (PID) controller. Before applying fuzzy logic, the PID gains are tuned using a conventional tuning method. At supervisory level, fuzzy logic readjusts the PID gains online. In the first tuning method, fuzzy logic at the supervisory level readjusts the three PID gains during the system operation. In the second tuning method, fuzzy logic only readjusts the proportional PID gain, and the corresponding integral and derivative gains are readjusted using the Ziegler–Nichols tuning method while the system is in operation. For the compositional rule of inferences in the fuzzy PID and the self-organizing fuzzy PID schemes two new approaches are introduced: the min implication function with the mean of maxima defuzzification method, and the max-product implication function with the centre of gravity defuzzification method. The fuzzy PID controller, the self-organizing fuzzy PID controller and the PID controller are all applied to a non-linear revolute-joint robot arm for step input and path tracking experiments using computer simulation. For the step input and path tracking experiments, the novel self-organizing fuzzy PID controller produces a better output response than the fuzzy PID controller; and in turn both controllers exhibit better process output than the PID controller.     

基于模糊推理的边缘检测算法

提出了基于模糊理论进行边缘检测的一种新方法.该方法首先通过计算边缘梯度和标准偏差,把得到的两组集合作为模糊系统的输入,接着根据高斯函数、模糊推理系统判断每一个像素所适用的推理规则,最后对推理结果进行去模糊化,并判断该像素是否为边界像素.本文采用经典的Sobel、Prewit和LoG算法作为比较,实验结果也证明了本文所提出方法的有效性.     

A cascade-type hierarchical fuzzy system with additional defuzzification of layers for the automatic power quality diagnosis

In general the power quality diagnosis of low-voltage electrical systems is a difficult issue due to the nuances of different power quality standards around the world and the uncertainties characteristics of the evaluation parameters. In this framework, this paper proposes a new methodology for diagnosing the power quality by means of a cascade-type hierarchical fuzzy system with additional defuzzification of layers (C-HFS-ADL), also proposed in this paper, which is able to evaluate the power quality indices in steady-state (total harmonic distortions, power factor, voltage variation, and unbalance voltage) considering several standards and provides a proper and complete diagnosis of the power quality in electrical systems. In the proposed C-HFS-ADL each output of a subsystem is transferred between inner layers of the hierarchical system and a total power quality diagnosis is obtained taking into account a secondary decision-making process with additional defuzzification in order to have a partial diagnosis for each subsystem of the hierarchy. In addition, an algorithm was implemented considering different inference systems for analyzing the behavior of the C-HFS-ADL on a database (power quality indices) obtained from a real electrical substation for observing its advantages and disadvantages.     

一类区间二型模糊PI控制器设计算法

区间二型模糊控制器在处理不确定性方面优于传统的模糊控制器,但带来的一个问题就是区间二型模糊控制器需要降阶过程。常用的KM等迭代式降阶算法效率低下,难以用于实时性较高的场合。本文利用直接降阶算法和动态解模糊化算法,提出了一类区间二型模糊PI控制器设计算法。该算法在降阶过程中考虑偏差和偏差变化量对控制器输出的影响,避免了KM等迭代式降阶过程。通过二阶迟延对象以及一个非线性对象的仿真实验表明,本文算法能够有效降低系统超调,降低系统的稳态时间,控制器在设定值附近的输出更为平滑。     

改进的模糊C-均值聚类医学图像分割算法

针对模糊C-均值聚类算法分割图像时容易产生模糊边缘的缺点,提出了一种结合图像梯度和模糊C-均值聚类的图像分割方法.该方法利用图像梯度反映出来的目标边界,对由模糊C-均值聚类所获得的聚类区域进行分割,把因模糊性而划分到目标区域的像素点与目标区域进行分离,同时利用区域增长方法找出干扰区域并删除.将该算法应用到胰腺ERCP图像分割,实验表明,改进算法能够比较准确地分割出图像中的目标,减少因模糊聚类产生的模糊边缘.