蚁群聚类算法的T-S模糊模型辨识

基于T-S模型,提出一种非线性系统的模型辨识方法。利用蚁群聚类算法来进行结构辨识,确定系统的模糊空间和模糊规则数。在聚类的基础上,利用遗传算法辨识模糊模型的后件加权参数,得到一个精确的模糊模型,从而实现参数辨识。仿真结果验证了该方法的有效性,表明该方法能够实现非线性系统的辨识,辨识精度高,可当作复杂系统建模的一种有效手段。     

基于自组织神经网络的非线性系统建模

针对基于T-S模糊模型的非线性系统建模问题,提出了一种基于自组织神经网络的新方法.在T-S模糊模型的建模中,目前常用的模糊C均值聚类算法存在迭代次数多,计算耗时的缺点.首先,利用竞争学习算法对输入空间进行聚类,基于此结果,借助于模糊C均值聚类算法进一步优化聚类结果,提取T-S模糊模型的规则前件隶属函数参数.然后,采用最小二乘法求得T-S模糊模型的规则后件参数,从而建立起非线性系统的T-S模糊模型.最后,仿真结果表明,该方法可以为模糊建模提供好的模型结构,并且有较高的计算效率和精度.     

基于蚁群聚类算法的非线性系统辨识

基于T-S模型提出一种非线性系统的模型辨识方法.利用蚁群聚类算法进行结构辨识,确定系统的模糊空间和模糊规则数.在聚类的基础上,利用遗传算法辨识模糊模型的后件加权参数,得到一个精确的模糊模型,从而实现了参数辨识.仿真结果验证了所提出方法的有效性,表明该方法能够实现非线性系统的辨识,而且辨识精度较高.     

模糊聚类与最小二乘相结合建立非线性系统模型

提出一种模糊聚类与最小二乘相结合的辨识方法.该方法利用基于模糊似然函数的模糊聚类算法确定系统的模糊划分数目,进而对应聚类个数建立相应的Takagi-Sugeno局部线性化模型,并结合递推最小二乘法,完成系统的辨识.该方法可使模糊模型的结构辨识和参数辨识同时完成,从而实现模糊模型的在线辨识.该方法辨识速度快,精确度高.仿真结果验证了该方法的有效性.     

基于T-S模糊模型的神经网络的系统辨识

基于T-S模糊模型,提出了利用神经网络实现非线性系统的辨识。首先,利用一种无监督的聚类算法分析输入输出数据生成初始的结构模型,确定系统的模糊空间和模糊规则数,构造神经网络辨识模型前提参数,使前提参数自适应变化,有较好的自学习能力和优化能力,采用最小二乘法取得结论参数。仿真结果验证了该方法是有效和可行的。     

采用改进PSO的非线性系统T-S模糊模型辩识

提出了一种新的T-S模糊模型的非线性系统辨识方法。采用自适应模糊C均值聚类算法确定模糊模型的前件结构及参数,用改进的粒子群优化(PSO)算法来辩识模糊模型的结论参数以获得系统参数的最优估计。仿真结果表明该方法是有效的。     

基于模糊分类的模糊神经网络辨识方法及应用

基于改进的T-S模型，提出一种自适应模糊神经网络模型(AFNN)，给出了网络的连接结构和学习算法。基于竞争学习算法的模糊分类器确定系统的模糊空间和模糊规则数，并得出每个样本对每条规则的适用程度。利用卡尔曼滤波算法在线辨识删的后件参数。AFNN结构简洁，逼近能力强，能够显著提高辨识精度，并且在线辨识的模糊模型简单有效。将该AFNN用于非线性系统的模糊辨识和化工过程连续搅拌反应器(CSTR)的建模中，仿真结果验证了该方法的有效性，表明该网络能够实现复杂非线性系统的建模，而且建模精度高、收敛速度快。可当作复杂系统建模的一种有效手段。     

基于T-S模型的非线性系统模糊聚类辨识方法

提出一种基于T-S模型的非线性系统模糊聚类辨识方法,对T-S模糊模型的前提部分和结论部分进行分开辨识,既简化该模型的辨识步骤,又提高它的泛化能力,同时也解决了T-S模糊模型随辨识系统复杂程度提高而规则数增大的问题。对一个非线性系统辨识的仿真结果验证了这种模糊聚类辨识方法的有效性。     

模糊预测控制在pH中和过程中的应用

针对pH中和过程,提出了一种基于T-S模型的模糊预测控制算法,以实现系统的滚动优化控制。T-S模糊模型的前件和后件参数分别采用模糊C均值聚类(FCM)和正交最小二乘法(OLS)进行离线或在线辨识。在每一个采样时刻以当前辨识出的T-S模型为基础实现系统的局部动态线性化,再根据线性化模型对pH过程实施广义预测控制(GPC),得到当前的控制量。仿真表明了该控制方法具有较小的超调性质,且在扰动作用下能快速跟踪到设定值,具有很强的鲁棒性。     

基于支持向量机回归的T-S模糊模型自组织算法及应用

结合模糊聚类算法和支持向量机回归算法提出了一种新的T-S模糊模型自组织算法. 该算法首先利用一种改进模糊聚类算法提取模糊规则和辨识前件参数,然后将T-S模糊模型后件变换为标准线性支持向量机回归模型,并利用支持向量机回归算法辨识后件参数. 仿真结果表明,相比现有的自组织算法,本文提出的T-S模糊模型自组织算法在规则数较少的情况下,仍然具有较高的辨识精度和较好的泛化能力. 最后,利用提出的T-S模糊模型自组织算法较好地建立了直拉硅单晶炉加热器和空气预热器的温度模型.     

Online learning with hidden markov models

We present an online version of the expectation-maximization (EM) algorithm for hidden Markov models (HMMs). The sufficient statistics required for parameters estimation is computed recursively with time, that is, in an online way instead of using the batch forward-backward procedure. This computational scheme is generalized to the case where the model parameters can change with time by introducing a discount factor into the recurrence relations. The resulting algorithm is equivalent to the batch EM algorithm, for appropriate discount factor and scheduling of parameters update. On the other hand, the online algorithm is able to deal with dynamic environments, i.e., when the statistics of the observed data is changing with time. The implications of the online algorithm for probabilistic modeling in neuroscience are briefly discussed.     

基于模糊建模的冷凝器污脏软测量

提出了一种基于模糊建模的冷凝器污脏软测量方法.该方法选取传热端差作为研究对象,应用模糊建模技术分离出冷凝器污脏对端差的影响.在模糊建模中,采用T-S模型描述变工况传热端差,研究了一种相似度判别法则以确定最优模型结构,并采用实数编码的遗传算法同时优化模型前、后件参数,从而获得了规则简化、精度较高的模糊模型.根据此方法,设计了试验系统,并进行了现场试验.试验结果表明:该方法能有效地在线监测冷凝器污脏,并在冷凝器出现堵管或空气漏入量较大时,取得比热阻法、传热系数法更可靠的测量结果.     

Fuzzy neural network with general parameter adaptation for modelingof nonlinear time-series

By taking advantage of fuzzy systems and neural networks, a fuzzy-neural network with a general parameter (GP) learning algorithm and heuristic model structure determination is proposed in this paper. Our network model is based on the Gaussian radial basis function network (RBFN). We use the flexible GP approach both for initializing the off-line training algorithm and fine-tuning the nonlinear model efficiently in online operation. A modification of the robust unbiasedness criterion using distorter (UCD) is utilized for selecting the structural parameters of this adaptive model. The UCD approach provides the desired modeling accuracy and avoids the risk of over-fitting. In order to illustrate the operation of the proposed modeling scheme, it is experimentally applied to a fault detection application.     

An approach to online identification of Takagi-Sugeno fuzzy models.

An approach to the online learning of Takagi-Sugeno (TS) type models is proposed in the paper. It is based on a novel learning algorithm that recursively updates TS model structure and parameters by combining supervised and unsupervised learning. The rule-base and parameters of the TS model continually evolve by adding new rules with more summarization power and by modifying existing rules and parameters. In this way, the rule-base structure is inherited and up-dated when new data become available. By applying this learning concept to the TS model we arrive at a new type adaptive model called the Evolving Takagi-Sugeno model (ETS). The adaptive nature of these evolving TS models in combination with the highly transparent and compact form of fuzzy rules makes them a promising candidate for online modeling and control of complex processes, competitive to neural networks. The approach has been tested on data from an air-conditioning installation serving a real building. The results illustrate the viability and efficiency of the approach. The proposed concept, however, has significantly wider implications in a number of fields, including adaptive nonlinear control, fault detection and diagnostics, performance analysis, forecasting, knowledge extraction, robotics, behavior modeling.     

Neuro-f uzzy system modeling based on automatic f uzzy clustering

A neuro-fuzzy system model based on automatic fuzzy clustering is proposed. A hybrid model identification algorithm is also developed to decide the model structure and model parameters. The algorithm mainly includes three parts :1) Automatic fuzzy C-means (AFCM) , which is applied to generate fuzzy rules automatically , and then fix on the size of the neuro-fuzzy network , by which the complexity of system design is reducesd greatly at the price of the fitting capability; 2)Recursive least square estimation ( RLSE) . It is used to update the parameters of Takagi-Sugeno model , which is employed to describe the behavior of the system;3) Gradient descent algorithm is also proposed for the fuzzy values according to the back propagation algorithm of neural network. Finally ,modeling the dynamical equation of the two- link manipulator with the proposed approach is illustrated to validate the feasibility of the method.     

Neuro-fuzzy system modeling based on automatic fuzzy clustering

A neuro-fuzzy system model based on automatic fuzzy dustering is proposed. A hybrid model identification algorithm is also developed to decide the model structure and model parameters. The algorithm mainly includes three parts：1） Automatic fuzzy C-means （AFCM）, which is applied to generate fuzzy rttles automatically, and then fix on the size of the neuro-fuzzy network, by which the complexity of system design is reducesd greatly at the price of the fitting capability; 2） R.ecursive least square estimation （RLSE）. It is used to update the parameters of Takagi-Sugeno model, which is employed to describe the behavior of the system;3） Gradient descent algorithm is also proposed for the fuzzy values according to the back propagation algorithm of neural network. Finally,modeling the dynamical equation of the two-link manipulator with the proposed approach is illustrated to validate the feasibility of the method.     

基于遗传算法和强化学习的贝叶斯网络结构学习算法

遗传算法是基于自然界中生物遗传规律的适应性原则对问题解空间进行搜寻和最优化的方法。贝叶斯网络是对不确定性知识进行建模、推理的主要方法,Bayesian网中的学习问题(参数学习与结构学习)是个NP-hard问题。强化学习是利用新顺序数据来更新学习结果的在线学习方法。介绍了利用强化学习指导遗传算法,实现对贝叶斯网结构进行有效学习。     

模糊树模型及其在复杂系统辨识中的应用

基于二叉树和模糊逻辑理论,提出了一种用于复杂系统建模的模糊树模型.将线性 模型和模糊集组织在树结构上,并给出了更新线性模型系数和模糊集隶属度函数的混合算 法.与其他建模方法相比,如ANFIS,模糊树模型计算量小,精度高,尤其在高维数据建模中 更为明显.仿真结果描述了这种方法的性能.     

基于联合滤波算法的复杂时变系统在线自适应逆控制

针对一类结构和参数均具备时变特性的复杂时变系统,提出一种新的基于联合滤波算法的在线自适应逆控制方法.该方法在处理参数时变问题的同时可兼顾系统的结构时变特性,实现复杂动态系统的在线跟踪控制.同时提出新的联合Volterra核函数滤波算法,该算法克服了原Volterra滤波器计算复杂运算速度慢的缺点,实现了动态非线性系统的在线跟踪控制.通过仿真分析可以得出,对于此类线性、非线性复杂时变系统,基于新的联合滤波器的自适应逆控制方法可以快速有效的实现动态对象在线建模与控制.     

基于在线分裂合并EM算法的高斯混合模型分类方法*

为了解决传统高斯混合模型中期望值EM处理必须具备足够数量的样本才能开始训练的问题,提出了一种新的高斯混合模型在线增量训练算法。本算法在Ueda等人提出的Split-and-Merge EM方法基础上对分裂合并准则的计算进行了改进,能够有效避免陷入局部极值并减少奇异值出现的情况;通过引入时间序列参数提出了增量EM训练方法,能够实现增量式的期望最大化训练,从而能够逐样本在线更新GMM模型参数。对合成数据和实际语音识别应用的实验结果表明,本算法具有较好的运算效率和分类准确性。