Dynamic prediction of gas emission based on wavelet neural network toolbox

This paper presents a method for dynamically predicting gas emission quantity based on the wavelet neural network （WNN） toolbox. Such a method is able to predict the gas emission quantity in adjacent subsequent time intervals through training the WNN with even time-interval samples. The method builds successive new model with the width of sliding window remaining invariable so as to obtain a dynamic prediction method for gas emission quantity. Furthermore, the method performs prediction by a self-developed WNN toolbox. Experiments indicate that such a model can overcome the deficiencies of the traditional static prediction model and can fully make use of the feature extraction capability of wavelet base function to reflect the geological feature of gas emission quantity dynamically. The method is characterized by simplicity, flexibility, small data scale, fast convergence rate and high prediction precision. In addition, the method is also characterized by certainty and repeatability of the predicted results. The effectiveness of this method is confirmed by simulation results. Therefore, this method will exert practical significance on promoting the application of WNN.

ADAPTIVE FLIGHT CONTROL SYSTEM OF ARMED HELICOPTER USING WAVELET NEURAL NETWORK METHOD

A discussion is devoted to the design of an adaptive flight control system of the armed helicopter using wavelet neural network method. Firstly, the control loop of the attitude angle is designed with a dynamic inversion scheme in a quick loop and a slow loop. respectively. Then, in order to compensate the error caused by dynamic inversion, the adaptive flight control system of the armed helicopter using wavelet neural network method is put forward, so the BP wavelet neural network and the Lyapunov stable wavelet neural network are used to design the helicopter flight control system. Finally, the typical maneuver flight is simulated to demonstrate its validity and effectiveness. Result proves that the wavelet neural network has an engineering practical value and the effect of WNN is good.

Discussion of stability in a class of models on recurrent wavelet neural networks

Based on wavelet neural networks （WNNs） and recurrent neural networks （RNNs）, a class of models on recurrent wavelet neural networks （RWNNs） is proposed. The new networks possess the advantages of WNNs and RNNs. In this paper, asymptotic stability of RWNNs is researched.according to the Lyapunov theorem, and some theorems and formulae are given. The simulation results show the excellent performance of the networks in nonlinear dynamic system recognition.

Self-Constructing Neural Network Modeling and Control of an AGV

Tracking precision of pre-planned trajectories is essential for an auto-guided vehicle (AGV). The purpose of this paper is to design a self-constructing wavelet neural network (SCWNN) method for dynamical modeling and control of a 2-DOF AGV. In control systems of AGVs, kinematical models have been preferred in recent research documents. However, in this paper, to enhance the trajectory tracking performance through including the AGV’s inertial effects in the control system, a learned dynamical model is replaced to the kinematical kind. As the base of a control system, the mathematical models are not preferred due to modeling uncertainties and exogenous inputs. Therefore, adaptive dynamic and control models of AGV are proposed using a four-layer SCWNN system comprising of the input, wavelet, product, and output layers. By use of the SCWNN, a robust controller against uncertainties is developed, which yields the perfect convergence of AGV to reference trajectories. Owing to the adaptive structure, the number of nodes in the layers is adjusted in online and thus the computational burden of the neural network methods is decreased. Using software simulations, the tracking performance of the proposed control system is assessed.

基于自回归小波神经网络的机械臂自适应滑模控制

针对机械臂存在模型不确定和未知扰动的问题,提出一种动力学模型参数分块逼近的神经网络非奇异终端滑模(nonsingular terminal sliding mode, NTSM)控制方法.为加快系统跟踪误差的收敛速度,避免传统终端滑模存在的奇异性问题,采用一种非奇异终端滑模面.利用多组自回归小波神经网络(self-recurrent wavelet neural network, SRWNN)分块逼近系统未知的动力学模型参数,并采用自适应更新律调整权重.通过积分控制项补偿SRWNN的逼近误差,并使用Lyapunov稳定性理论证明了系统稳定性.使用MATLAB进行仿真分析,分块SRWNN滑模控制与滑模控制、整体SRWNN滑模控制相比,关节角度跟踪误差的平均稳态误差分别降低了31.9%、76.5%,表明此方法是一种可靠、有效的轨迹跟踪控制方法.

基于DWNN的机电作动器渐变性故障诊断

飞机飞行控制系统机电作动器(EMA)的渐变性故障很难准确预判,若不能及早发现而任其发展就会影响到飞机的飞行安全性。针对EMA的渐变性故障,提出一种基于动态小波神经网络(DWNN)的故障诊断方法。首先,利用EMA在电机电枢绕组匝间短路、传动装置丝杆和滚珠磨损等多种渐变性故障状态下的运行数据来训练DWNN故障诊断模型;然后,利用训练好的DWNN模型对EMA渐变性故障进行诊断。创新之处在于DWNN模型利用小波分解算法去除了传感器测量信号中高频分量的影响,利用反馈神经网络的记忆能力融合了过去输入的信息和过去预测的信息,提高了对EMA渐变性故障诊断的准确性。通过对某型EMA进行故障诊断实验,仿真结果表明所提出的DWNN方法可以实现对EMA部件渐变性故障的准确诊断。

基于WOSA-BP的车辆动态称重算法研究

测量精度一直是影响车辆动态称重系统有效可靠性的主要因素。针对车辆动态称重系统测量精度较低这个问题,提出了一种基于鲸鱼优化(Whale Optimization Algorithm,WOA)算法和模拟退火(Simulated Annealing,SA)算法混合优化的BP神经网络(Back Propagation Neural Network)动态称重模型。首先,简单介绍了动态称重系统的结构和原理。然后,通过小波变换对动态称重系统的采样信号进行过滤重构处理,经过计算得到的动态车重、车速和轴数作为BP神经网络模型的输入参数。其次,建立了一个由WOSA算法优化的BP神经网络来预测实际车辆总重和轴重。最后,比较了WOSA算法优化的BP神经网络模型的预测能力并得出结论。仿真结果表明,WOSA-BP车辆动态称重模型收敛速度快,精度高,最大总重的相对误差为0.58%,最大轴重相对误差为6.73%。

静止无功补偿器的小波神经网络PID控制方法研究

静止无功补偿器(SVC)是电力系统中应用广泛的动态无功补偿装置。针对传统比例积分微分(PID)在SVC动态调节过程中由于控制器参数固定而存在动态响应、自适应能力差的问题,提出了一种基于小波神经网络PID(WNNPID)的SVC电流反馈电压稳定控制方法。首先,分别选取SVC的电压差ΔUr、电压误差ΔU和补偿电压USL作为WNNPID控制器的输入信号,而控制器的输出为SVC的参考电纳。然后,采用小波神经网络(WNN)和增量式PID控制对WNNPID控制器的结构进行设计。最后,采用Matlab/Simulink仿真平台对所提控制方法进行仿真,并与基于反向传播(BP)神经网络PID的控制效果进行了对比。仿真结果表明,所提WNNPID控制方法具有更稳定的电压控制效果、较快的响应速度、较好的动静态响应性能和较强的自适应能力。

基于拉普拉斯小波滤波和SA-DS-CNN的滚动轴承故障诊断

针对基于深度学习模型的滚动轴承故障诊断方法易受环境噪声干扰的问题,提出了一种基于拉普拉斯小波滤波(LWF)和自注意力机制-动态选择-卷积神经网络(SA-DS-CNN)的滚动轴承故障诊断模型。首先,提出一种拉普拉斯小波阻尼参数自适应选取策略,使用拉普拉斯小波对采集的滚动轴承振动信号进行相关滤波并进行功率谱变换;其次,基于卷积神经网络框架,引入自注意力机制和动态选择机制,构造SA-DS-CNN;最后,利用SA-DS-CNN提取功率谱特征,根据轴承的不同故障状态定位相关特征信息,实现故障特征的提取和诊断。对N205EM圆柱滚子轴承的故障诊断试验表明:LWF降噪效果较好,能为SA-DS-CNN模型提供优秀的训练样本;SA-DS-CNN模型能抑制无用通道信息,增强网络特征学习能力;LWF和SA-DS-CNN组合模型的故障诊断准确率达到99.65%,优于其他组合模型。

基于事件触发GrHDP碳纤维角联织机张力控制方法

针对碳纤维角联织机经纱张力控制中存在的张力控制精度低与通信网络资源受限问题,提出一种基于事件触发目标再现启发式动态规划(event-triggered goal representation heuristic dynamic programing,ET-GrHDP)的张力控制方法。首先,分析碳纤维织机的织造原理,构建张力系统控制模型。其次,在GrHDP算法的基础上,采用小波神经网络(wavelet neural network,WNN)设计评价网络,BP神经网络(back propagation neural network,BPNN)设计执行网路和目标网络,以增强GrHDP近似最优控制的能力,同时引入事件触发机制,实现小波GrHDP张力控制器仅在事件触发时刻更新控制信号。最后,使用MATLAB软件对张力系统进行仿真控制实验。与经典GrHDP张力控制相比,所提控制策略在系统状态跟踪响应时间上缩短近22.9%,送经、卷取线速度均无超调量,张力超调量为1.8%,且抗干扰能力强,提高了张力系统的控制性能。在事件触发机制下,张力控制器降低近84%的计算次数,有效减少了通信资源的浪费。

A Fuzzy Neural Network Based Dynamic Data Allocation Model on Heterogeneous Multi-GPUs for Large-scale Computations

The parallel computation capabilities of modern graphics processing units （GPUs） have attracted increasing attention from researchers and engineers who have been conducting high computational throughput studies. However, current single GPU based engineering solutions are often struggling to fulfill their real-time requirements. Thus, the multi-GPU-based approach has become a popular and cost-effective choice for tackling the demands. In those cases, the computational load balancing over multiple GPU ＂nodes＂ is often the key and bottleneck that affect the quality and performance of the real=time system. The existing load balancing approaches are mainly based on the assumption that all GPU nodes in the same computer framework are of equal computational performance, which is often not the case due to cluster design and other legacy issues. This paper presents a novel dynamic load balancing （DLB） model for rapid data division and allocation on heterogeneous GPU nodes based on an innovative fuzzy neural network （FNN）. In this research, a 5-state parameter feedback mechanism defining the overall cluster and node performance is proposed. The corresponding FNN-based DLB model will be capable of monitoring and predicting individual node performance under different workload scenarios. A real=time adaptive scheduler has been devised to reorganize the data inputs to each node when necessary to maintain their runtime computational performance. The devised model has been implemented on two dimensional （2D） discrete wavelet transform （DWT） applications for evaluation. Experiment results show that this DLB model enables a high computational throughput while ensuring real=time and precision requirements from complex computational tasks.

Crack identification in functionally graded material framed structures using stationary wavelet transform and neural network

In this paper,an integrated procedure is proposed to identify cracks in a portal framed structure made of functionally graded material(FGM)using stationary wavelet transform(SWT)and neural network(NN).Material properties of the structure vary along the thickness of beam elements by the power law of volumn distribution.Cracks are assumed to be open and are modeled by double massless springs with stiffness calculated from their depth.The dynamic stiffness method(DSM)is developed to calculate the mode shapes of a cracked frame structure based on shape functions obtained as a general solution of vibration in multiple cracked FGM Timoshenko beams.The SWT of mode shapes is examined for localization of potential cracks in the frame structure and utilized as the input data of NN for crack depth identification.The integrated procedure proposed is shown to be very effective for accurately assessing crack locations and depths in FGM structures,even with noisy measured mode shapes and a limited amount of measured data.

静止无功补偿器自适应动态规划电压控制方法

为解决传统比例?积分?微分(proportional integral differential,PID)控制应用于静止无功补偿器(static var compensator,SVC)非线性控制系统存在的不足,提出了一种基于自适应动态规划(adaptive dynamic programming,ADP)的SVC自适应优化控制策略。采用小波神经网络和BP神经网络分别设计执行依赖启发式动态规划(action dependent heuristic dynamic programming,ADHDP)的执行网络和评价网络,以增强ADHDP对性能指标函数的逼近能力和控制律优化能力,然后用其设计了SVC控制系统的电压调节器。在Matlab/Simulink仿真平台对所提出的ADHDP控制方法进行了仿真,并与执行网络、评价网络均采用BP神经网络设计的经典ADHDP控制方法的控制效果进行了对比,验证了基于ADHDP的SVC电压优化控制方法的可行性和有效性。相比之下,所提出的ADHDP控制方法具有更好的电压稳定和控制效果,控制系统具有较快的响应速度、较好的动态和静态稳定性和较强的自适应能力。

基于动力补偿的液压并联运动平台控制策略

针对所研制的飞行模拟器用大负载液压六自由度并联运动平台,在对系统闭环动力学模型进行详细分析的基础上,依据系统数学模型存在外扰力、摩擦力及不确知参数等因素影响的控制特性,利用系统闭环动力学模型的动力补偿特性,采用六维动力补偿器,提出一种PD控制器加小波神经网络补偿器进行在线动力学补偿的实时控制策略,并通过实验验证了其控制的有效性.结果表明:该方法具有良好的跟踪特性,能够提高系统响应快速性、运动精度及抗负载扰动能力,很大程度上克服了系统的动力耦合及参数时变和未知力扰动带来的影响,为多自由度运动系统的高性能实时控制开辟了崭新途径.

基于改进CFD与小波混合神经网络组合的风电场功率预测方法

风的间歇性和时变性制约电力系统能量平衡,准确的风电功率预测有助于电网减小旋转备用、合理制定检修计划。为减小预测误差,提出一种基于多计算流体力学(computational fluid dynamics,CFD)模型的新型风电场组合功率预测方法。首先,利用小波混合神经网络对数值天气预报降尺度;其次,提出了考虑多重尾流的风电场物理CFD模型,并建立了根据测风塔风速外推各台风电机组风速的加速比相关系数;最后,提出了仅考虑自由流场和带有激盘模型的变权重组合流场模型。实际算例仿真证明,所提出的预测方法更准确地反映了风电场实际运行状态,有效提高了预测准确性。

基于小波变换和动态神经网络的温室黄瓜蒸腾速率预测

针对作物蒸腾速率与温室环境参数间非线性耦合时延性关系,以温室环境参数:空气温度、空气湿度、太阳辐射度、土壤温度、叶面温度、土壤含水量的时间序列为输入量,温室黄瓜蒸腾速率时间序列为输出量,采用小波分解重构方法,分别建立低频时间序列和高频时间序列的非线性自回归动态神经网络(NARX)子网络预测模型,以子网络的预测叠加值为蒸腾速率预测值。结果表明:1层小波分解重构的低频时间序列A1和高频时间序列D1的子网络预测值与蒸腾速率分解重构目标值间相关性决定系数R2分别为0.949和0.853,平均绝对误差(MAE)分别为5.36和2.00 g·h-1。2层小波分解重构的低频时间序列A2和高频时间序列D2的子网络预测值与蒸腾速率分解重构目标值间相关性决定系数R2分别为0.983和0.849,MAE分别为2.88和2.56 g·h-1。1层小波分解重构的时间序列的NARX子网络预测值合成值(A1+D1),2层小波分解重构的时间序列的NARX子网络预测值合成值(A2+D2+D1)和未小波分解重构的原时间序列的NARX预测值与蒸腾速率测量值间相关性决定系数R2分别为0.945、0.974和0.857,MAE分别为5.76、4.42和10.09 g·h-1。小波分解重构的高频和低频时间序列预测合成,能够提高时间序列的预测准确性。同时采用相同网络结构的BP神经网络和NAR动态神经网络预测蒸腾速率时间序列,其预测值与测量值间决定系数R2分别为0.596和0.839,MAE分别为19.55和9.45 g·h-1。NARX预测性能优于NAR和BP神经网络的预测性能,能够应用该方法预测温室黄瓜的蒸腾速率。该方法可推广至多变量非线性强耦合时延性系统中的变量预测。

基于数据驱动的短期风电出力预估–校正预测模型

提高风电出力的预测精度可降低含高渗透率风电电力系统调度、优化、规划等策略的保守性和控制策略的复杂性。该文在分析风电出力历史数据与气象因素关系的基础上,建立了基于风电出力数据驱动的短期风电功率预估–校正预测模型。采用具有较高精度的小波神经网络预测模型实现预估环节,以自适应动态规划作为附加优化结构,利用风电出力实测数据及时更新预估模型中的参数,实现校正环节,使得预估模型能够适应风机在额定风速以下运行区域内多变的运行点。测试结果表明,该方法在风机出力变化频繁时,能获得比BP、GABP预测模型更高的精度。

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。

基于小波包神经网络的岩巷掘进机动载荷识别方法

针对岩巷掘进机工作时负载多变,动载荷实时识别难度大等问题,提出了一种基于小波包特征能量的神经网络动载荷识别新方法。实时采集截割机构的振动信号、截割电动机的电流及液压缸压力信号,应用小波包分解得到相应信号的特征量,并将其作为神经网络的输入样本,训练神经网络并对网络进行测试。结果表明,动载荷实时识别准确率可达0.93,该识别方法能够满足动载荷实时识别系统的要求。

大坝安全诊断的混沌优化神经网络模型

为了提高大坝变形的预测精度,采用小波变换和分形理论对大坝位移观测数据的非线性动力学特性进行了分析,揭示了其具有低维混沌动力特性,这为大坝变形预测模型的建立提供了理论依据和先验知识。基于低维混沌动力特性,设计了能捕获大坝位移观测数据全局动力特性,兼具神经网络模型结构优化和动力机制时新的混沌优化神经网络大坝变形预测模型。在工程实例中,由多个度量指标组成量化评价体系,对模型预测性能进行综合评价,结果表明,所建模型比传统BP神经网络和ARMA模型具有更高的预测精度。