Power signal classification using dynamic wavelet network

A new approach to classification of non-stationary power signals based on dynamic wavelet has been considered. This paper proposes a model for non-stationary power signal disturbance classification using dynamic wavelet networks (DWN). A DWN is a combination of two sub-networks consisting of a wavelet layer and adaptive probabilistic network. The DWN has the capability of automatic adjustment of learning cycles for different classes of signals, for minimizing error. DWN models are specifically suitable for application in dynamic environments with time varying non-stationary power signals. The test results showed accurate classification, fast and adaptive learning mechanism, fast processing time and overall model effectiveness in classifying various non-stationary power signals. The classification result of the DWN has been compared with that of the probabilistic neural network (PNN).     

Local recurrent sigmoidal-wavelet neurons in feed-forward neural network for forecasting of dynamic systems: Theory

In this paper different structure of the neurons in the hidden layer of a feed-forward network, for forecasting of the dynamic systems, are proposed. Each neuron in the network is a combination of the sigmoidal activation function (SAF) and wavelet activation function (WAF). The output of the hidden neuron is the product of the output from these two activation functions. A delay element is used to feedback the output of the sigmoidal and the wavelet activation function to each other. This arrangement leads to proposed five possible configurations of recurrent neurons. Besides proposing these neuron models, the presented paper tries to compare the performance of wavelet function with sigmoid function. To guarantee the stability and the convergence of the learning process, upper bound for the learning rates has been investigated using the Lyapunov stability theorem. A two-phase adaptive learning rate ensures this upper bound. Universal approximation property of the feed-forward network with the proposed neurons has also been investigated. Finally, the applicability and comparison of the proposed recurrent networks has been weathered on two benchmark problem catering different types of dynamical systems.     

高压动态校准的数据建模与补偿

提出采用小波包相关阈值法对测量数据进行去噪,对处理后的数据采用基于减法聚类和LMS算法的RBF神经网络来建立并补偿传感器模型。研究结果表明:小波包相关阈值法去噪优于常规的去噪方法,所提出的算法简单、收敛速度快、建立的模型精度高,并使传感器的非线性得到了有效的校正。     

基于动态粒度小波神经网络的空气质量预测

针对空气质量预测,提出了基于动态粒度小波神经网络的预测方法。为了选取合适的粒度,结合实际问题采用不断尝试的方法动态选取最优粒度,在最优粒度空间中求解问题。粒度变换后可以改变空气质量预测问题的求解空间,提高预测的精确度。实验也验证了动态选取的最优粒度作为小波神经网络的输入进行空气质量预测,可以取得更好的预测准确率。     

A dynamic watermarking scheme for quantum images using quantum wavelet transform

In this paper, a novel watermarking scheme based on quantum wavelet transform (QWT) is proposed. Firstly, the wavelet coefficients are extracted by executing QWT on quantum image. Then, we utilize a dynamic vector for controlling embedding strength instead of a fixed parameter for embedding process in other schemes. Analysis and results show that the proposed dynamic watermarking scheme has better visual quality under a higher embedding capacity and outperforms the existing schemes in the literature.     

Supervised linear dynamic system model for quality related fault detection in dynamic processes

Dynamic and uncertainty are two main features of industrial processes data which should be paid attentions when carrying out process monitoring and fault diagnosis. As a typical dynamic Bayesian network model, linear dynamic system (LDS) can efficiently deal with both dynamic and uncertain features of the process data. However, the quality information has been ignored by the LDS model, which could serve as a supervised term for information extraction and fault detection. In this paper, a supervised form of the LDS model is developed, which can successfully incorporate the information of quality variables. With this additional data information, the new supervised LDS model can provide a quality related fault detection scheme for dynamic processes. A detailed industrial case study on the Tennessee Eastman benchmark process is carried out for performance evaluation of the developed method.     

动态博弈框架下的分布式动态优化

为了实时在线求解复杂的大规模动态优化问题,本文基于动态博弈理论提出了一种分布式动态优化方案,滚动合作博弈优化(RCGO).首先基于滚动时域优化框架,该方案将原本复杂的大规模动态优化问题分解为若干简单的小规模局部优化子问题,使得计算复杂度降低从而保证优化求解的实时性.之后本文基于动态博弈提出了分解迭代法求解各局部动态优化子问题,并对RCGO优化方案下系统稳定性进行分析.最后本文选择一个化工过程网络作为仿真案例,基于RCGO方案得到了极大化经济效益下该网络的最优操作.优化结果表明在求解复杂大规模动态优化问题时, RCGO方案较传统的集中式优化方案在由系统经济效益、闭环控制性能及优化求解实时性等组成的综合指标上有较大优势.     

基于动态阈值的网络异常检测

基于Hurst指数进行异常检测的模型多采用固定阈值的方法,不能很好的适应动态变化的网络环境.针对该问题设计了一种基于动态阈值的检测方法,该方法在采用Hurst指数分析的基础上,通过EWMA和滑动窗口模型控制有效数据的个数并根据网络的变化动态调整检测阈值,提高了模型的检测能力.实验结果表明,在采用动态阈值进行DDOS异常检测时具有较高的检测率.     

基于VMD-CNN的高噪声动态生产过程质量异常监控

针对由智能制造现场动态生产过程的复杂随机因素影响造成的高噪声和质量异常监控方法效率低等问题,将变分模态分解方法(variational mode decomposition,VMD)与深度卷积神经网络(convolutional neural network,CNN)相结合,提出一种基于VMD-CNN的实时质量监控新方法.首先,利用VMD方法,将高噪声动态过程原始数据分解为包含质量异常特征和噪声信息的两类本征模态函数,通过去除噪声数据的本征模态函数,消除动态生产过程的高噪声干扰;进而,采用灰度变换将保留原始质量异常特征的本征模型函数转化为质量异常图像,构建VMD-CNN模型对质量异常图像进行识别,并提出基于VMD-CNN的高噪声动态过程质量异常实时监控框架;最后,通过实验验证所提方法的有效性,并与小波去噪方法和CNN识别模型进行对比分析,实验结果显示所提方法的识别精确度显著优于现有的动态过程质量异常监控方法.     

Discrete-time weight updates in neural-adaptive control

Typical neural-adaptive control approaches update neural-network weights as though they were adaptive parameters in a continuous-time adaptive control. However, requiring fast digital rates usually restricts the size of the neural network. In this paper we analyze a delta-rule update for the weights, applied at a relatively slow digital rate. We show that digital weight update causes the neural network to estimate a discrete-time model of the system, assuming that state feedback is still applied in continuous time. A Lyapunov analysis shows uniformly ultimately bounded signals. Furthermore, slowing the update frequency and using the extra computational time to increase the size/accuracy of the neural network results in better performance. Experimental results achieving link tracking of a two-link flexible-joint robot verify the improved performance.     

循环流化床锅炉燃烧过程建模研究

针对具有多维非线性和纯滞后特性的循环流化床锅炉燃烧过程,采用基于PLS学习算法和OLS学习算法的径向基函数(RBF)神经网络进行建模研究。首先通过循环流化床锅炉仿真平台产生用于建模实验的网络训练数据和泛化数据,然后分别采用OLS算法和PLS算法进行网络训练和泛化研究,最后讨论了影响建模结果的算法参数及其选取方法,重点讨论了PLS算法的4个网络参数的影响和选取。与基于小波网络的建模实验比较,对具有复杂特性的循环流化床锅炉燃烧过程,采用RBF网络建模在保证建模精度的同时,算法参数的选取也较为方便易行。     

基于小波变换的动态关联规则元规则挖掘方法

针对动态关联规则元规则挖掘中规则预测精度不高的问题,提出了一种把小波变换应用到动态关联规则元规则挖掘中以提高规则预测精度的方法。首先利用Daubechies小波对挖掘出的动态关联规则元规则支持度计数进行变换;其次通过小波变换的多分辨率特点提取出近似部分和细节部分;然后利用两部分进行曲线的误差计算与小波变换分解层次的选择控制,用过滤的近似信号进行逆变换和曲线拟合进而进行规则预测;最后用预测的数据进行验证证明其预测精度达到90%以上。实验结果表明所提方法能更好地反映规则随时间变化的动态信息和变化趋势,从而使动态关联规则挖掘在合理的元规则指导下得到更精确的结果。     

Adaptive control of harmonic drive with parameter varying friction using structurally dynamic wavelet network

In this paper, an adaptive controller with structurally dynamic wavelet network is developed for a harmonic drive subject to parameter varying friction. The control architecture integrates a proportional controller, a feedback adaptive component and sliding component to adaptively compensate for the friction to achieve accurate position tracking. Global asymptotic stability of the algorithm is proved by using Lyapunov function. In parallel to the adaptive controller, a fuzzy reconfiguration scheme is devised to change the structure of the network along with weights updating to improve the system tracking performance and robustness. Experimental tests on a harmonic drive manipulator verify the effectiveness of the proposed control method.     

A model for dynamic adaptive coscheduling

is paper proposes a dynamic adaptive coscheduling model DASIC to take advantage of excess available resources in a network of workstations(NOW). Besides coscheduling related subtasks dynamically,DASIC can scale up or down the process space depending upon the number of available processors on an NOW. Based on the dynamic idle processor group(IPG),DASIC employs thre modules:the coscheduling module,the scalabele scheduling module and the load balancing module,and uses six algorithms to achieve scalability.A simplified DASIC was also implemented,and experimental results are presented in this paper,which show that it can maximize system utilization,and achieve task parallelism as much as possible.     

具有动态补偿能力的神经网络模型及其在动态系统建模中的应用

本文在多层前馈神经网络模型基础上，引入误差动态反馈环节，从而形成一种新的具有动态补偿能力的神经网络模型。新模型的训练利用反向传播原理实现。采用该模型对非线性动态系统进行建模时，能显著提高建模精度，特别是在网络模型工作时，对新出现的输出误差具有动态补偿能力，文中给出了新网络模型的结构和学习算法，最后是仿真实例。     

一种级联过程神经网络动态预测模型及其应用

针对非线性动态系统分阶段指标预测问题,提出了一种基于级联过程神经元网络和相空间重构技术的动态预测模型和方法。考虑实际系统各个变量在运行过程中不同阶段可能具有不同的作用关系和信息变换机制,以及各阶段系统状态的连续性,采用若干过程神经元子网络构成级联结构建立系统动态预测模型;同时,为弥补实际采样数据的不足和提高数据信息的利用率,利用相空间重构理论构造训练样本集。给出了预测模型的信息处理机制和学习算法,以油田开发三次采油过程仿真为例,实验结果验证了模型和方法的有效性。     

A dynamic K-winners-take-all neural network

In this paper, a dynamic K-winners-take-all (KWTA) neural network, which can quickly identify the K-winning neurons whose activations are larger than the remaining ones, is proposed and analyzed. For N competitors, the proposed KWTA network is composed of N feedforward hardlimit neurons and three feedback neurons, which are used to determine the dynamic threshold. From theoretical analysis and simulation results, we found that the convergence of the proposed KWTA network, which requires Log(2)(N+1) iterations in average to complete a KWTA process, is independent of K, the number of the desired winners, and faster than that of the existing KWTA networks.     

Optimum design of structures against earthquake by adaptive genetic algorithm using wavelet networks

Optimum design of structures against earthquake is achieved by a modified genetic algorithm. Some features of the simulated annealing are used to control various parameters of the genetic algorithm. To reduce the computational work, a fast wavelet transform is used by which the number of points in the earthquake record is decreased. For this purpose, the record is decomposed into two parts. One part contains the low frequency and the other possesses the high frequency of the record. The low-frequency part is used for dynamic analysis. Then, by using a wavelet network, the dynamic responses of the structures are approximated. By such approximation, the dynamic analysis of the structure is not necessary during the optimisation process. Thus, wavelet neural networks have been employed as a general approximation tool for the time-history dynamic analysis and estimation of the dynamic responses in the process of optimisation. A number of structures are designed for optimal weight against El Centro earthquake and the results are compared with those of the exact approach.     

基于不完全树结构小波变换及模糊聚类神经网络的纹理分割

提出了一种新的不完全树结构小波变换用于纹理特征提取,给出了一种一人类视觉过程相一致的多分辨率多通道纹理分析方法,它由：1）特征提取：使用不完全树结构小波变换抽取纹理特征;2）基于模糊神经 网络的特征粗分类：①基于样本分布密度的模糊Kohonen聚类网络权植初始化,②使用缩减的特征向量对网络进行训练,得到粗分割结果;3）细化粗分割结果等几部分构成。实验结果证明了其有效性。     

自组织覆盖网络QoS组播动态路由优化研究

针对覆盖组播节点的动态特性,研究自组织覆盖网络带度和延时约束的组播动态路由问题,提出了动态覆盖组播路由算法AHMQ。组播树由目的节点驱动动态渐近形成,动态路由优化在通信过程中进行。协议是软状态的,仅要求节点维护局部状态信息,同时利用覆盖网络技术和无线媒质的广播能力,降低了网络负载,提高了重构能力。对算法进行了分析研究,通过实验验证了该算法具有较好的性能。