Intelligent Neural Network-Based Fast Power System Harmonic Detection

Nowadays, harmonic distortion in power systems is attracting significant attention. Traditional technical tools for harmonic distortion analysis using either fast Fourier transform or discrete Fourier transform are, however, susceptible to the presence of noise in the distorted signals. Harmonic detection by using Fourier transformation also requires input data for more than one cycle of the current waveform and requires time for the analysis in the next coming cycle. In this paper, an alternative method using neural network algorithm has achieved satisfactory results for fast and precise harmonic detection in noisy environments by providing only 1/2 cycle sampled values of distorted waveforms to neural network. Sensitivity considerations are conducted to determine the key factors affecting the performance efficiency of the proposed model to reach the lowest errors of testing patterns     

神经网络余数制系统与余数制神经网络模型

余数制和神经网络各有其独特优点，将其有机结合这些优点得以充分发挥。将神经网络结构和方法引人余数制信号处理系统，构造出完成余数约化运算和余／十转换运算以及余数加法运算的新结构，开辟了高速实时信号处理的新途径．将余数制引入神经网络，即神经网络中的数据、权值均按余数制表示和运算，构造出一种新的感知机模型—余数制神经网络，由于余数制运算具有一种独特的非线性特点，使这种模型比常规神经网络具有更强的功能。     

基于神经网络方法的半导体生产工艺优化

以提高生产成品率为目标,利用神经网络的非线性和容错性,对半导体芯片生产过程进行了分析和优化,具体内容如下：（１）使用神经网络方法建立模型,确定生产线上工艺参数和成品率之间的映射关系,构造以工艺参数为输入,成品率为输出的多维函数曲面．（２）对上述多维函数曲面进行搜索,搜索成品率最高的最优点,以该最优点的工艺参数值为依据确定工艺参数的规范值．（３）对工艺参数规范进行优化,在实际生产工艺中反复实践,直至达到提高成品率的目的．生产实践证明,神经网络的分析结果是合理的．根据神经网络分析提出的优化建议,有效地提高了工     

基于神经网络方法的半导体生产工艺优化

以提高生产成品率为目标,利用神经网络的非线性和容错性,对半导体芯片生产过程进行了分析和优化,具体内容如下：(1)使用神经网络方法建立模型,确定生产线上工艺参数和成品率之间的映射关系,构造以工艺参数为输入,成品率为输出的多维函数曲面.(2)对上述多维函数曲面进行搜索,搜索成品率最高的最优点,以该最优点的工艺参数值为依据确定工艺参数的规范值.(3)对工艺参数规范进行优化,在实际生产工艺中反复实践,直至达到提高成品率的目的.生产实践证明,神经网络的分析结果是合理的.根据神经网络分析提出的优化建议,有效地提高了工序能力指数和产品成品率的一致性,具有实际应用价值.     

网络化非线性编辑系的构建

节目制作系统的数字化、网络化改造已成为各电视台的热门话题.本文针对泰州电视台建立非线性后期编辑网络的具体情况,对非线性视频网络的结构模式、关键技术、发展趋势及其特点优势作了深入分析,并探讨了网络化非线性编辑系统的选型和构建方案.     

Frequency Response Analysis of Current Controllers for Selective Harmonic Compensation in Active Power Filters

This paper compares four current control structures for selective harmonic compensation in active power filters. All controllers under scrutiny perform the harmonic compensation by using arrays of resonant controllers, one for the fundamental and one for each harmonic of interest, in order to achieve zero phase shift and unity gain in the closed-loop transfer function for selected harmonics. The complete current controller is the superposition of all individual harmonic controllers and may be implemented in various reference frames. The analysis is focused on the comparison of harmonic and total closed-loop transfer functions for each controller. Analytical similarities and differences between schemes in terms of frequency response characteristics are emphasized. It is concluded that three of them have identical harmonic behavior despite the fact that their implementation is significantly different. It emerges that the fourth one has superior behavior and robustness and can stably work at higher frequencies than the others. Theoretical findings and analysis are supported by comparative experimental results on a 7-kVA laboratory setup. The highest harmonic frequency that can be stably compensated with each control method has been determined, indicating significant differences in the control performance.      

基于神经网络技术的虚拟传感器温度补偿系统

介绍了一体化虚拟温度传感器补偿仪,运用多传感器数据融合技术与神经网络技术,与虚拟仪器技术相结合创建了虚拟压阻式传感器的温度补偿系统。实验结果表明,该方法有效地抑制干扰因素,获得高稳定性测量结果。     

基于小波神经网络的光纤陀螺系统级温度补偿

捷联惯组中光纤陀螺的输出精度受温度的影响较大,在实际应用中必须对其进行温度漂移补偿。对于光纤陀螺的零偏随温度变化呈较强的非线性特性,传统的多元线性回归法难以满足补偿精度要求,因而将小波神经网络用于建立光纤陀螺的温度补偿模型。通过对某型号捷联惯组中光纤陀螺的静漂数据进行仿真,实验结果表明,基于小波神经网络模型比多元线性回归模型的补偿效果更明显,有效提高了陀螺的精度。     

峰值电流控制开关电源的反馈补偿问题研究

针对电流控制模式降压型开关电源芯片,探讨了输入电压的不同以及工作温度的差异造成对输出带负载能力和峰值电流的影响。在电流反馈回路的斜坡补偿模块中,加入随输入电压线性变化的基准电流源,以补偿不同输入电压对采样与斜坡补偿峰值电压造成的差异。此外,对反馈环中的比例电阻采用不同的工艺制作,通过电阻的温度系数补偿由采样电阻随温度变化所造成的采样电压的变化,减小温度对电路的带负载能力和峰值电流的影响。改进后,在相同环境温度下,4．7V到30V输入时,输出最大负载电流差异由2A降为0．5A。电阻改进后,从27℃到150℃,输出最大负载电流几乎不变。     

基于遗传算法的RBF神经网络在涡流传感器非线性补偿中应用

为了解决涡流传感器的非线性问题,应用遗传算法(GA)训练径向基函数(RBF)神经网络(NN)实现其非线性补偿.介绍非线性补偿的原理和网络训练方法.从实测数据出发,建立了涡流传感器的非线性补偿模型.该方法能同时优化网络结构和参数,具有全局寻优能力,补偿精度高、鲁棒性好、网络训练速度快、能实现在线软补偿.实验结果表明,所采用的涡流传感器非线性补偿方法是有效的和可行的.补偿后,最大非线性误差在0.5%范围内,具有良好的线性.     

Implementation of Artificial Neural Network-Based Tracking Controller for High-Performance Stepper Motor Drives

Two distinct multilayer perception neural networks (NNs) are implemented via laboratory experiment to simultaneously identify and adaptively control the trajectory tracking of a hybrid step motor assumed to operate in a high-performance drives environment. That is, a neural network identifier (NNI) which captures the nonlinear dynamics of the stepper motor drive system (SMDS) over any arbitrary time interval in its range of operation, and a neural network controller (NNC) to provide the necessary control actions as to achieve trajectory tracking of the rotor speed. The exact form of the control law is unknown, and must be estimated by the NNC. Consequently, the NNC is constructed as a nonlinear unknown function depending on the current state of the drive system supplies by the NNI and the reference trajectory we wish the outputs to follow. The two NNs are online trained using dynamic back-propagation algorithm. The composite structure is used as a speed controller for the SMDS. Performance of the composite controller is evaluated through a laboratory experiment. Experimental results show the effectiveness of this approach, and demonstrate the usefulness of the proposed controller in high-performance drives     

基于SDH网的数据广播系统的安装调试

本文详实介绍了江西广电数字数据广播系统的组成、设备配置、功能、原理与调试。     

基于网络的入侵检测系统的实现机制

介绍现有基于网络的入侵检测系统的实现机制,分析此机制的优势和存在问题,并对新一代入侵检测系统提出建议。     

基于负载电流前馈的风电系统网侧变流器控制

对于具有并网变流器的风电系统,本文提出了一种基于负载电流前馈的网侧变流器矢量控制方法。与传统方法相比,该方法可提高风电系统在最大风能捕获过程中的暂态稳定性和抑制电网电压波动对直流母线电压所造成的影响。本文以双馈发电机型风电系统为例进行了理论分析和仿真实验,结果验证了所提方法的正确性和有效性。     

An Adaline Neural Network-Based Multi-User Detector Improved by Particle Swarm Optimization in CDMA Systems

The detector applied to each single user based on adaline neural network (ANN) is presented in this paper, which is equivalent to the joint one applied to all users in eliminating the multiple access interference in CDMA systems. Then, particle swarm optimization (PSO) algorithm combined with least mean square scheme is employed in the training procedure of the ANN, which can effectively remove the shortcoming of the poor dynamic adaptive behavior of conventional neural network, i.e. during the convergence procedure of the weights in conventional neural network, the training samples are usually required to be trained iteratively. However, in the improved detector, each training sample can be trained repeatedly, so that the converging speed is getting much faster. Simulation results show that, in the ANN based multi-user detector improved by PSO, the dynamic adaptive behavior has been remarkably improved.     

数据中心配电系统新型无功补偿解决方案

当前,高频UPS在数据中心的大规模应用带来了供电系统初期功率因数超前的问题,而常规电容无功补偿技术已无法解决该问题。通过对现有主流品牌UPS及典型数据中心和通信机房供电系统的测试情况进行分析,提出了采用SVG动态无功补偿技术解决数据中心供电系统的功率因数超前问题的解决方案。实验验证和现场测试结果显示,该方案解决了数据中心供电系统运行初期的功率因数超前和后期的谐波问题,进一步优化了供电质量,适用于新建数据中心采用。     

基于RBF神经网络的虚拟仪器测试系统动态补偿方法

测试系统存在着动态测试误差,为了准确地复现出被测量的原始信号,提出了基于RBF神经网络的虚拟仪器测试系统动态补偿方法.该方法不依赖于测试系统的数学模型,而是根据测试系统的输入和响应数据,利用神经网络的强非线性逼近能力获得补偿系统的模型参数,通过LabVIEW构造出测试系统的动态补偿系统.实验结果表明,将RBF神经网络和虚拟仪器相结合,对测试系统进行动态补偿具有良好的效果.     

配电网电能质量监控系统研究

电能质量(PQ)因为不同的PQ信号产生了多种分析技术,使得整合多种电能质量监控难度较大。为了解决这个问题,利用prony的PQ分析建立电能质量监控系统,可便捷地分析和检测各类PQ干扰,如基频偏差、谐波、相间谐波、电压波动以及PQ事件。目前,该监控系统已在南方电网中实施应用。     

中国公用会议电视网构架及系统组成

随着我国国民经济的飞速发展，会议电视日渐成为人们的迫切需要。本文较为详细地阐述了我国会议电视系统的总体结构和系统，便更妇地促进我国会议电视的应用和发展。