复Gaussian小波核函数及多参数同步优化策略

对复Gauss ian小波满足Mercy条件及其在Hilbert空间具有再生性的命题作了证明．用复Gaussian小波构建出一种核函数，与主成分分析方法相结合，对非线性非平稳信号进行参数辨识和预测．针对多参数模型优化时间过长，不利于工程应用的问题，提出了一种多参数同步优化策略．仿真实验验证了该方法的可行性和有效性，表明该方法具有较好的实用价值．     

基于一种改进提升小波变换的轧辊偏心自寻优控制

为了提高传统小波变换的性能，使用提升小波变换提取轧辊偏心信号，并对其进行在线自寻优控制． 采用一种改进的蚁群算法优化小波阈值，并运用自寻优策略对系统参数进行优化．提升小波不依赖傅里叶变换，计 算简单，运行速度快．仿真试验表明，该方法是有效的，对外界环境干扰具有很好的适应性，能够实现轧辊偏心信 号的实时动态控制．     

一种级联混合小波神经网络盲均衡算法

针对严重非线性失真信道,提出了一种级联混合小波神经网络自适应盲均衡器．这种均衡器在小波网 络输入层之前级联一个横向滤波器,横向滤波器的节点输出作为小波网络的输入．利用常数模代价函数分别获得横 向滤波器和小波网络的梯度信息,将两个梯度信息进行加权融合处理,可以得到混合小波网络参数调整的梯度信 息．级联混合小波网络盲均衡器实现了对非凸性误差性能曲面的线性和非线性寻优的组合．普通电话信道和非线性 信道条件下的仿真结果表明,级联混合小波网络盲均衡与前馈网络盲均衡以及传统小波网络盲均衡相比较,具有更 好的均衡性能．     

基于智能方法的真空退火炉建模与控制

真空退火炉中工件温度的精确控制是一个具有非线性和不确定性的复杂控制问题．为了实现工件温度的精确控制，以现场实际采集的数据为基础，采用小波神经网络建立对象的模型,利用自适应免疫遗传算法对小波神经网络的权值、小波基的个数和伸缩、平移因子等进行优化，提出了一种精确控制真空退火炉工件温度的优化数学模型，仿真与实验研究表明，用此方法建立的模型,其控制效果优于BP神经网络所建立模型的控制；同时，加快了网络训练速度，提高了系统的稳态精度，使系统具有较强的实时性和鲁棒性．     

小波网络在控制系统中的应用

小波分析是80年代中期发展起来的一门新兴的 数学理论和方法,小波网络是在小波分析研究获得突破的基础上提出的一种前馈型网络．本 文对小波网络的结构形式、学习算法以及在控制方面的主要应用进行了综述,并将小波网络 与常规的前馈神经网络作了比较,最后对小波网络在控制系统中的应用提出了几点展望．     

基于小波网络的非线性系统建模与控制

提出了种基于小波网络的非线性系统的建模和控制方法。使用小波网络对未知控制系统建立一步预测模型,基于Ｄｓａｖｉｄｏｎ最小二乘法得到自适应控制律。小波网络的权值由广义递推最小二乘法来学习,尺度参数和平移参数通过稳定的Ｄａｖｉｄｏｎ最小二乘法来获得。仿真结果表明了该方法的有效性。     

基于改进小波神经网络的网络流量预测研究

采用小波神经网络对网络流量数据的时间序列进行建模与预测。针对传统小波神经网络训练算法的不足,提出了自适应量子粒子优化算法——AQPSO,用于训练小波神经网络,优化网络参数,建立基于AQPSO算法优化的小波网络预测模型。实验结果表明,该模型对网络流量的短期预测是有效可行的,并具有良好的收敛性和稳定性。     

一种新的小波网络设计方法及其在非线性模型辨识中的应用

模拟生物进化过程,将进化算法与小波网络相结合,提出利用自适应进化方法实现一次对网络的拓扑结构和网络参数全局优化的算法。     

高维小波网络及其在丙烯腈收率预测中的应用

针对基于单尺度小波框架的高维小波网络,提出一种系统化的设计方法．首先在小波框架内提出一种小波基初始化方法;然后根据样本的分布特点,提出一种改进的小波基粗选方法;最后将自适应投影算法与AIC准则相结合,对小波基进行精选,同时完成网络参数的辨识．将该方法应用于丙烯腈收率的预测,研究结果表明了该方法的有效性．     

基于紧框架小波神经网络的抽油机井故障诊断

所提出的小波网络包括初始的学习网络和训练过程中根据精度要求而自适应并入的子网络．通过对各维输入信号的综合时域分析,选择合适的尺度参数和位移参数构造单尺度下的小波紧框架,以构成各级子网络,进而解决多维小波网络中存在的“维教灾”问题．针对对角回归结构．推导出带遗忘因子的动态递推最小二乘法对网络的参数进行训练．将该网络应用于抽油机井的故障诊断,得到了较好的效果。     

A new class of wavelet networks for nonlinear system identification

A new class of wavelet networks (WNs) is proposed for nonlinear system identification. In the new networks, the model structure for a high-dimensional system is chosen to be a superimposition of a number of functions with fewer variables. By expanding each function using truncated wavelet decompositions, the multivariate nonlinear networks can be converted into linear-in-the-parameter regressions, which can be solved using least-squares type methods. An efficient model term selection approach based upon a forward orthogonal least squares (OLS) algorithm and the error reduction ratio (ERR) is applied to solve the linear-in-the-parameters problem in the present study. The main advantage of the new WN is that it exploits the attractive features of multiscale wavelet decompositions and the capability of traditional neural networks. By adopting the analysis of variance (ANOVA) expansion, WNs can now handle nonlinear identification problems in high dimensions.     

A Wavelet Neural Network Based Non-linear Model Predictive Controller for a Multi-variable Coupled Tank System

In this paper, a novel real time non-linear model predictive controller(NMPC) for a multi-variable coupled tank system(CTS) is designed. CTSs are highly non-linear and can be found in many industrial process applications. The involvement of multi-input multi-output(MIMO) system makes the design of an effective controller a challenging task. MIMO systems have inherent couplings,interactions in-between the process input-output variables and generally have an complex internal structure. The aim of this paper is to design, simulate, and implement a novel real time constrained NMPC for a multi-variable CTS with the aid of intelligent system techniques. There are two major formidable challenges hindering the success of the implementation of a NMPC strategy in the MIMO case. The first is the difficulty of obtaining a good non-linear model by training a non-convex complex network to avoid being trapped in a local minimum solution. The second is the online real time optimisation(RTO) of the manipulated variable at every sampling time.A novel wavelet neural network(WNN) with high predicting precision and time-frequency localisation characteristic was selected for an MIMO model and a fast stochastic wavelet gradient algorithm was used for initial training of the network. Furthermore, a genetic algorithm was used to obtain the optimised parameters of the WNN as well as the RTO during the NMPC strategy. The proposed strategy performed well in both simulation and real time on an MIMO CTS. The results indicated that WNN provided better trajectory regulation with less mean-squared-error and average control energy compared to an artificial neural network. It is also shown that the WNN is more robust during abnormal operating conditions.     

Wavelet networks for nonlinear system modeling

This study presents a nonlinear systems and function learning by using wavelet network. Wavelet networks are as neural network for training and structural approach. But, training algorithms of wavelet networks is required a smaller number of iterations when the compared with neural networks. Gaussian-based mother wavelet function is used as an activation function. Wavelet networks have three main parameters; dilation, translation, and connection parameters (weights). Initial values of these parameters are randomly selected. They are optimized during training (learning) phase. Because of random selection of all initial values, it may not be suitable for process modeling. Because wavelet functions are rapidly vanishing functions. For this reason heuristic procedure has been used. In this study serial-parallel identification model has been applied to system modeling. This structure does not utilize feedback. Real system outputs have been exercised for prediction of the future system outputs. So that stability and approximation of the network is guaranteed. Gradient methods have been applied for parameters updating with momentum term. Quadratic cost function is used for error minimization. Three example problems have been examined in the simulation. They are static nonlinear functions and discrete dynamic nonlinear system.     

自适应GA优化WNN的模拟电路软故障诊断方法*

在小波神经网络(WNN)的模拟电路故障诊断系统中,普遍采用的梯度下降算法在训练时易使网络陷入局部最优,而网络结构的冗余也会造成训练收敛方向偏离全局最优点,降低推广能力和增加误诊率。用自适应遗传算法优化WNN,以克服上述缺陷。采用该方法可简化小波神经网络的结构和优化参数,在滤波器电路的软故障识别中获得满意的效果。与常规的WNN故障诊断方法相比,有效地提高了故障诊断的效率和正确率。     

Lattice Dynamical Wavelet Neural Networks Implemented Using Particle Swarm Optimization for Spatio–Temporal System Identification

In this brief, by combining an efficient wavelet representation with a coupled map lattice model, a new family of adaptive wavelet neural networks, called lattice dynamical wavelet neural networks (LDWNNs), is introduced for spatio-temporal system identification. A new orthogonal projection pursuit (OPP) method, coupled with a particle swarm optimization (PSO) algorithm, is proposed for augmenting the proposed network. A novel two-stage hybrid training scheme is developed for constructing a parsimonious network model. In the first stage, by applying the OPP algorithm, significant wavelet neurons are adaptively and successively recruited into the network, where adjustable parameters of the associated wavelet neurons are optimized using a particle swarm optimizer. The resultant network model, obtained in the first stage, however, may be redundant. In the second stage, an orthogonal least squares algorithm is then applied to refine and improve the initially trained network by removing redundant wavelet neurons from the network. An example for a real spatio-temporal system identification problem is presented to demonstrate the performance of the proposed new modeling framework.     

二进离散小波神经网络在传感器逆向建模中的应用

给出了快速收敛的离散二进小波神经网络的初始化,构造和权值确定的详细方法。并将这类小波神经网络应用于传感器的非线性校正,并给出了仿真实验结果。相对使用随机贪心算法训练的神经网络,快速收敛小波神经网络利用离散二进小波变换的便利,采用启发式的构造算法;具有构造过程复杂度低,构造完成后高度接近目标模型,训练次数少,并可有效避免陷入局部极小点的优点。有效解决了小波神经网络尺度和平移系数在训练时需对小波函数进行求导而影响网络收敛速度的问题。     

A novel approach for high dimension 3D object representation using Multi-Mother Wavelet Network

In this paper, we present a novel approach for 3D objects representation. Our idea is to prove that wavelet networks are capable for reconstruction and representing irregular 3D objects used in computer graphics. The major contribution consist to transform an input surface vertices into signals and to provide instantaneously an estimation of the output values for input values. To prove this, we will use a new structure of wavelet network founded on several mother wavelet families. This structure uses several mother wavelet, in order to maximize best wavelet selection probability. An algorithm to construct this structure is presented. First, Data is taken from 3D object. The vertices and their corresponding normal values of a 3D object are used to create a training set. To this stage, the training set can be expressed according to three functions, which interpolates all their vertices. Second we approximate each function using wavelet network. To achieve a better approximation, the network is trained several iterations to optimize wavelet selection for every mother. To guarantee a small error criterion, we adjust wavelet network parameters (weight, translation and dilation) by using an improved Orthogonal Least Squares method version. We consider our proposed approach on some 3D examples to prove that the new approach is able to approximate 3D objects with a good approximation ability.     

采用正交小波网络的非线性系统辨识方法

基于多分辨分析的递阶思想,采用正交小波网络研究了输入样本空间分布非均匀时非线性系统的辨识问题,重点讨论了样本非均匀时网络系的设计问题,并给出了基于该网络系的在线递阶辨识算法,最后利用正交小波网络分别对非线性静态和动态系统进行了仿真辨识。     

图像的二维提升小波变换的FPGA实现

研究了图像的5/3提升小波变换算法原理,根据提升算法的系数分布存在的特点,提出二维提升小波变换硬件实现的简化VLSI硬件结构,并在对系统进行了综合、仿真后,在FPGA芯片上实现。实验证明,系统改进的简化硬件结构,提高了系统运行速度,保证了系统的实时性要求。