基于SA-WNN模型的水电机组故障诊断研究

针对水电机组振动故障征兆和故障类型的非线性特性及传统小波网络在故障诊断中的缺陷,设计了一种基于模拟退火算法的小波神经网络(SA-WNN)故障诊断模型。将SA-WNN诊断模型应用到水电机组四种典型故障,验证其可行性。实例结果表明,与传统小波网络相比,基于模拟退火算法优化的小波神经网络训练次数少,收敛精度高,为水电机组故障诊断提供了新途径。     

改进的QPSO算法在电网故障诊断系统中的应用

电网故障诊断系统通常基于建立的解析模型,通过分析保护和断路器的动作信息来推断可能的故障位置,从而识别保护与断路器的故障元件和误动作。本文根据保护动作原理,构建了一种改进的解析模型,并采用改进的量子粒子群算法对其目标函数进行优化求解。该模型不仅充分考虑到了保护和断路器的误动与拒动、断路器失灵保护等问题,且能辨识告警信息的误报和漏报。实验结果表明改进的算法不仅使故障诊断结果更精确,并能使故障情况很清晰的表示出来,有利于故障的及时恢复,同时使模型的运算速度和稳定性也进一步得到了提高。     

基于极化因子神经网络的火电厂制粉系统故障诊断技术

制粉系统是火电厂的主要设备,其安全稳定运行对发电企业的经济生产具有十分重要的意义。针对制粉系统的运行特性和故障分析,提出了基于极化因子神经网络的火电厂制粉系统故障诊断方法,该方法将故障征兆相应的过程变量作为输入,将制粉系统故障类型作为输出,通过训练神经网络建立其系统故障诊断模型,其中训练过程中采用极化因子来自动调整神经网络的收敛速度,从而在满足误差目标的前提下,防止其陷入局部极小。选取实际火电厂制粉系统3个典型故障及其相对应的9个故障征兆参数进行了实验。结果表明,该方法具有良好的收敛性,完全可以满足火电厂制粉系统现场故障诊断的要求。     

基于免疫遗传算法改进的BP神经网络在灭火系统电路板故障诊断中的应用

针对装甲车辆灭火系统电路板规模较大,功能日趋多样与完善的同时,其复杂程度也日益提高,故障层次越来越多,故障现象与故障原因的映射关系更加复杂,组合故障频发,传统的故障诊断方法已不能满足灭火系统电路板故障诊断的要求。设计了基于免疫遗传算法优化的BP神经网络对灭火系统电路板进行故障诊断,并在免疫和遗传过程中保留了部分训练最优解。实现了神经网络收敛速度的提高,使用Matlab编程优化算法并完成了电路板仿真故障的诊断。通过实验验证了该诊断模型的准确性和可靠性,为电气系统通用检测设备的神经网络诊断方法实现提供了理论支撑。     

基于多区域代理的分布式故障诊断方法

军用大型复杂装备组成涉及多个子系统或多个装备,故障诊断涉及上百个分散测试点数据采集和分离模块的诊断推理。传统装备采用集中测试和诊断方法,配套测试系统结构设计复杂、系统故障诊断算法效率低。本文基于D-矩阵故障诊断原理,提出基于多区域Agent的分布式故障诊断结构模型和区域Agent数据协同、区域Agent测试结果仲裁等问题的解决办法,并以某型舰船装备为例,验证了基于多区域代理的分布式故障诊断技术的有效性。     

模糊Petri网在车电系统总线故障诊断中的应用

针对车电系统总线故障现象和故障原因之间存在复杂模糊关系而无法实现快速故障诊断这一难题,提出采用模糊Petri网(fuzzy petri net,FPN)建立车电系统总线的故障诊断分析模型,并给出了相应的形式化推理算法;以某型车电系统总线为例,分析比较了各种故障原因的可信度;分析表明:所建模型有效地描述了车电系统总线故障现象和故障原因之间的模糊关系,能够实现故障的快速诊断,该模型可以作为车电系统总线快速故障诊断的理论支持工具。     

基于RBF网络的断路器电流自适应保护研究

针对传统断路器电流保护方法存在受系统运行方式影响、整定困难、智能化低等问题,本文提出了基于RBF的断路器电流自适应保护算法,并给出了算法的模型。该算法融合了RBF神经网络的故障检测和电流自适应保护。首先通过RBF网络检测负载线路的电流故障,然后用电流自适应算法进行保护。在对神经网络进行训练时,利用PSO算法对RBF神经网络的参数进行优化以此来提高网络的泛化能力和学习能力;然后采用优化后的PSO-RBF神经网络对电流故障进行诊断。实验表明,该算法较大地提高了断路器智能化管理水平。     

基于LM-BP神经网络的气阀故障诊断方法

提出一种基于LM（Levenberg-Marquardt）算法优化的 BP (Back Propagation)神经网络的多级往复式压缩机压缩机气阀故障诊断方法。以6M25-185/314氢氮气压缩机的 6级压差和6级温差作为网络的输入向量,建立可对往复式压缩机一至六级气阀故障进行在线监测及故障诊断的LM-BP神经网络模型。以100组故障数据作为网络训练样本,30组数据作为网络检测样本进行故障诊断,结果表明,LM-BP神经网络相比于变梯度BP神经网络和RBF神经网络诊断更快速稳定且准确率达到96%以上。利用Matlab软件平台建立的LM-BP 神经网络故障诊断模型,模型简单便于在工程实际中应用。     

基于GA-BP的移动通信设备故障诊断

针对通信设备故障发生随机性强,影响因素多,对应的故障诊断有高度非线性和不确定性的特点,采用BP神经网络算法,优化的GA-BP神经网络算法和POS-BP神经网络算法分别搭建基站设备故障诊断模型,提取设备故障历史数据进行MATLAB仿真,准确预测设备故障类型,帮助提高代维公司调度管理的智能化水平,提高基站设备运维的执行效率。仿真结果表明：本文的BP,GA-BP和POS-BP神经网络算法都能够实现设备故障类别的预测,且GA-BP神经网络算法相比BP和POS-BP神经网络算法对通信设备故障诊断有更好的适应性。     

基于小波和神经网络的风机故障诊断系统设计

本文在LabVIEW平台下,设计了一种基于小波和神经网络的风机故障在线诊断系统。以风机产生的噪声为诊断依据,用噪声信号的功率谱重心、A声级、小波分解后相关频段的能量构成故障诊断的特征向量,以BP网络作为故障的智能分类器,建立起智能诊断系统。实验结果表明,采用小波和神经网络相融合的诊断与识别技术,是提取风机故障特征,进行状态识别的一种有效方法。所设计系统有较强的学习能力和容错能力。诊断结果比较可靠、准确。     

射频指标自动测试及故障诊断系统研究

自动测试与故障诊断的联合研究已经在电子设备实际工作中得到较为广泛的应用。文章针对通信设备研发阶段射频指标测试效率低下以及测试故障定位难度较大等问题,开发了基于虚拟仪器技术的自动测试系统以及适用于射频指标自动测试问题定位的智能故障诊断系统。故障诊系统采用基于专家系统的知识库及推理机制,解释机制采用预制文本法进行设计。实际运行结果表明该系统能够高效准确地完成射频指标自动测试,并对测试过程中出现的问题进行较为准确的定位。     

基于多信号流模型的电子设备故障诊断方法

为了提高产品的可靠性,并且在电子设备发生故障时迅速地确定故障源,保障设备的正常运行,基于多信号流模型的诊断建模方法,在多信号流基础上引入了以故障重要先验知识为主的多信号流故障诊断策略,通过引入故障模式的故障概率改进了多信号流诊断技术。该方法已应用于BEPCⅡ磁铁电源接口控制设备故障诊断系统,使用TEAMS测试工具箱建模实现了快速准确的故障诊断和定位,提高了磁铁电源控制设备的故障诊断检测率和隔离率,并且可以方便地扩展到其他设备和系统上。     

混沌状态下永磁同步发电机的故障诊断——LMI法研究

本文以永磁同步风力发电机为研究对象, 在两相同步旋转坐标系下建立了永磁同步发电机的数学模型. 应用时间尺度和线性仿射变换建立了系统混沌模型, 验证了系统在某些参数和工作条件下会出现混沌运动. 随后在考虑系统不确定性的情况下设计了故障观测器, 在系统发生故障时, 通过所设计的故障观测器能对混沌状态下永磁同步发电机的故障做出准确估计. 仿真结果表明基于线性矩阵不等式方法的故障观测器能够对系统故障做出快速准确的诊断. 关键词： 永磁同步发电机 混沌 非线性不确定系统 故障诊断     

基于信息融合的模拟电路故障的特征提取与融合方法

在模拟电路故障诊断中,故障特征的提取是一个非常重要的环节,其提取结果的好坏将直接影响最终的诊断正确率。对现有文献研究发现,每种特征提取方法单独使用时都有一定的局限性,为了能够更加充分的提取模拟电路故障特征,提出了小波包分析与主元分析并行应用的方法,并将两种方法提取的特征向量依据不同规则进行了三种类型的融合,方便对比实验。为获取最优小波特征,提出了特征偏离度,并以此为标准选择最优小波基。最后,通过设计一种改进的神经网络分类器模型,将融合后的三种特征向量送入其中进行仿真验证,得出最终诊断结果。结果表明,该方法能够有效克服单一特征提取方法提取不充分的缺点,提高故障诊断的正确率,并且融合因子 适中时诊断正确率最高。     

基于气象因素的集中供热系统热负荷预测研究

为了解决直升机旋翼伺服作动器维修保障过程中训练资源有限,拆装难度高,故障率较高且难以确定故障点等难题,在直升机虚拟维修训练系统(VMTS, Virtual Maintenance Training System)的基础上,提出了应用虚拟仪器检测,确定故障点的直升机故障诊断可视化设计方法。分析了故障诊断过程中仪器、工具、环境等对故障诊断的影响,实现了动态的建立仿真模型和数据处理。通过虚拟仪器和推理机的功能配合,解决了直升机维护中复杂多变的故障诊断难题,形成一个逻辑推理能力强的故障诊断系统。最后以直升机旋翼伺服作动器故障诊断为例,验证该方法的可行性。     

基于案例和规则融合的民用客机故障诊断系统设计

目前很多工程应用中的飞机故障诊断方法,只考虑单一的基于案例或基于规则的诊断方法,故障诊断的效率有待提高。本文针对民用客机地面运营支持系统的特点和要求,将案例和规则融合的推理机制引入到飞机故障诊断系统的设计中。该方法采用规则推理为前导、案例推理后置补充的结合方式,最大化地利用飞机故障隔离手册知识和从维修记录中提取的案例知识,从而提高首次故障隔离效率、降低无效排故时间。以民用客机某系统的典型故障为例,阐述了该推理机制在故障诊断中的应用。通过历史飞行数据试验,验证了提出的基于案例与规则融合诊断方法的有效性,以此为基础设计的故障诊断方案可为航空公司构建更完善的专家系统提供参考。     

A generalized scheme for analysis of multifarious commercially used mufflers

Commercial automotive mufflers are often too complex to be broken into a cascade of one-dimensional elements with predetermined transfer matrices. The one-dimensional (1-D) scheme presented in this paper is based on an algorithm that uses user-friendly visual volume elements along with the theory of transfer matrix based muffler analysis. This work attempts to exploit the speed of the one-dimensional analysis with the flexibility, generality and user-friendliness of three-dimensional analysis using geometric modeling. A code based on the developed algorithm has been employed to demonstrate the generality of the proposed method in analyzing commercial mufflers by considering three very diverse classes of mufflers with different kinds of combinations of reactive, perforated and absorptive elements. Though the examples used in the paper are not very complex for they are meant to be just representative cases of certain classes of mufflers, yet the algorithm can handle a large domain of commercial mufflers of high degree of complexity. Results from the present algorithm have been validated through comparisons with both the analytical (plane wave based) and the more general, three-dimensional FEM based results. The forte of the proposed method is its power to construct the system matrix consistent with the boundary conditions from the geometrical model to evaluate the four-pole parameters of the entire muffler and thence its transmission loss, etc. Thus, the algorithm can be used in conjunction with the transfer matrix based muffler programs to analyze the entire exhaust system of an automobile.     

基于RBF神经网络的强流LIA故障诊断与性能评价技术

 用于流体动力学诊断的强流LIA是庞大而复杂的系统，其性能预测和评估是十分困难的。针对强流LIA大量的单次快脉冲非平稳信号，提出基于小波包分析与RBF神经网络技术相结合实现故障智能诊断和性能评价的方法。该方法以强流LIA高维信号的小波包结点能量提取的特征向量来表征信号平顶、脉宽以及暂态特性。在此基础上，建立了“神龙一号”加速器腔电压及注入器出口束流故障诊断与性能评价原型系统，该系统不仅可进行故障诊断和性能评价，还可探测到加速器运行参数的变化趋势，为加速器的精细维护提供预测信息。     

Random neural network based novel decision making framework for optimized and autonomous power control in LTE uplink system

This paper presents a novel decision making framework for cognitive radio networks. The traditional continuous process of sensing, analysis, reasoning, and adaptation in a cognitive cycle has been divided into two levels. In the first level, the process of sensing and adaptation runs over the radio transmission hardware during run-time. In the second level, the process of analysis and reasoning runs in the background in offline mode. This arrangement offloads the convergence time and complexity problem of reasoning process during run-time. For implementation of the first level, a random neural network (RNN) based controller trained on an open loop case based database on the cloud has been designed. For the second level, a genetic algorithm (GA) based reasoning and an RNN based learning has been developed. The proposed framework is used to address the uplink power control problem of long-term evolution (LTE) system. The performance of RNN is compared with artificial neural network (ANN) and state-of-the-art fractional power control (FPC) scheme in terms of essential cognitive engine (CE) design requirements, capacity, and coverage optimization (CCO). The simulation results have shown that RNN based CE can achieve comparable results with faster adaptation, even subject to severe environment changes without the need of retraining.     

Chance-constrained resource allocation for cognitive wireless-powered backscatter communication networks

With the rapid development of the Internet of Things (IoT) and the increasing number of wireless nodes, the problems of scare spectrum and energy supply of nodes have become main issues. To achieve green IoT techniques and resolve the challenge of wireless power supply, wireless-powered backscatter communication as a promising transmission paradigm has been concerned by many scholars. In wireless-powered backscatter communication networks, the passive backscatter nodes can harvest the ambient radio frequency signals for the devices’ wireless charging and also reflect some information signals to the information receiver in a low-power-consumption way. To balance the relationship between the amount of energy harvesting and the amount of information rate, resource allocation is a key technique in wireless-powered backscatter communication networks. However, most of the current resource allocation algorithms assume available perfect channel state information and limited spectrum resource, it is impractical for actual backscatter systems due to the impact of channel delays, the nonlinearity of hardware circuits and quantization errors that may increase the possibility of outage probability. To this end, we investigate a robust resource allocation problem to improve system robustness and spectrum efficiency in a cognitive wireless-powered backscatter communication network, where secondary transmitters can work at the backscattering transmission mode and the harvest-then-transmit mode by a time division multiple access manner. The total throughput of the secondary users is maximized by jointly optimizing the transmission time, the transmit power, and the reflection coefficients of secondary transmitters under the constraints on the throughput outage probability of the users. To tackle the non-convex problem, we design a robust resource allocation algorithm to obtain the optimal solution by using the proper variable substitution method and Lagrange dual theory. Simulation results verify the effectiveness of the proposed algorithm in terms of lower outage probabilities.