基于模糊神经网络的故障诊断方法的应用

针对大型机组的状态监测与故障诊断问题,为了克服单一故障诊断方法的局限性,对现有的大型设备故障诊断方法作了分析之后,提出一种基于区间值模糊神经网络的诊断方法。该方法根据设备故障诊断的不同阶段,利用基于规则库、区间值模糊集理论、模糊神经网络和模糊模式识别等方法。该方法在某炼油厂重催化机组故障诊断中得到了具体应用。     

风电机组故障智能诊断技术及系统研究

风电机组的状态监测和故障诊断是保证机组长期稳定运行和安全发电的关键。基于风电机组的基本结构,介绍了机组的故障类型和机理,论述了实际应用中机组的状态监测和故障诊断技术;基于BP神经网络的原理和优点,深入讨论了如何应用人工神经网络构建风电机组智能诊断系统,并给出了可行的系统设计方案和软件实现流程图。     

基于支持向量机的燃气轮机故障诊断

分析燃气轮机的8种典型常见故障,建立了基于支持向量机的故障诊断模型,用实例计算证明其有效性。同时和神经网络方法对比后发现：在小样本情况下,支持向量机方法的计算结果比神经网络要好,推广能力更强,而且效率高于神经网络。本方法针对故障诊断样本少的特点,为建立智能化的燃气轮机状态监控和故障诊断提供了一种新的途径,具有广泛的实用价值。     

Application of artificial neural networks to the condition monitoring and diagnosis of a combined heat and power plant

The objective of this study has been to create an online system for condition monitoring and diagnosis of a combined heat and power plant in Sweden. The system in question consisted of artificial neural network models, representing each main component of the combined heat and power plant, connected to a graphical user interface. The artificial neural network models were integrated on a power generation information manager server in the computer system of the combined heat and power plant, and the graphical user interface was made available on workstations connected to this server.     

基于RBF神经网络的核动力装置故障诊断方法研究

核动力装置是一个高度复杂并具有高度安全性要求的结构体系,其故障检测方法一般采用传统的阈值方法。为克服阈值方法的不足,提出了基于RBF(radial basis function)神经网络的核动力装置故障诊断方法。该方法选择对核动力装置安全具有重要影响的运行参数作为神经网络的输入,并利用核动力装置正常运行模式及典型故障模式的监测数据作为训练样本,网络训练采用正交最小二乘算法(orthogonal least square,OLS)。为了验证所提方法的可行性,利用核动力装置运行监测数据进行检验。结果表明,RBF神经网络成功地诊断出了故障,具有良好的诊断效果。     

汽轮发电机组远程智能故障诊断系统

分析研究了汽轮发电机组振动智能故障诊断技术,将人工神经网络技术与面向对象技术相结合,建立了振动频谱、轴心轨迹、升降速特性和负荷特性等4个征兆神经网络,同时构建了具有不完全征兆输入的汽轮发电机组振动智能故障诊断神经网络系统。以机组振动频谱征兆为例,研究了频谱征兆的自动提取方法．给出了基于频谱征兆的不完全征兆综舍故障诊断实例。在此基础上,采用B／S模式和Java技术,开发了汽轮发电机组远程智能故障诊断系统,介绍了系统的结构组成、功能模块以及服务器和客户端程序设计和实现方法。     

Impact of New Technology on the Korean Electricity Industry

This letter demonstrates the use of modal logic for knowledge representation for condition monitoring of gas turbine start-up sequences. The potentially large amounts of data and the complex real-time processes behind on-line fault detection indicate the need for software entities that can reason and react to changing environmental conditions. These are known as intelligent software agents. As a consequence, data interpretation is achieved by converting the data into appropriate information and combining individual agents' knowledge, resulting in an automatic fault diagnosis.     

基于大数据分析的eHorus智慧云智能诊断系统在光伏电站巡检中的应用

随着全球光伏发电规模的日益扩大,光伏电站中光伏设备的状态监控、故障诊断与故障定位变得日益重要。基于此,介绍了一款可用于光伏电站中光伏设备的智能诊断系统——eHorus智慧云智能诊断系统,通过在云端构建光伏电站的光伏设备运行状态大数据中心,采集并存储包括光伏阵列在内的光伏电站全站光伏设备的实时运行状态数据,建立科学有效的大数据分析模型,实时对光伏电站全站光伏设备的运行情况进行线上智能巡检,以便及时发现低效设备或故障设备。对于诊断出异常的设备,智能诊断系统自动向光伏电站运维工程师推送报警信息并生成故障缺陷单,光伏电站运维工程师接到报警信息后快速到达故障设备现场,及时进行设备消缺,提高光伏电站全站光伏设备的运行水平。     

火电厂真空系统的在线监测与故障诊断专家系统

为保证火电厂真空系统的安全经济优化运行，实现故障诊断和操作指导，开发了该真空系统在线监测与故障诊断专家系统。介绍了该系统的基本结构、主要功能和应用实例。系统中采用了多种故障诊断相结合的方法，如基于规则的专家系统和基于神经网络的故障诊断方法。     

汽轮机组回热系统故障诊断知识的模糊处理及诊断研究

在建立火电机组回热系统常见故障的故障集和征兆集基础上,利用模糊数学知识和相关理论,针对回热系统故障征兆参数的不同变化方向和程度,采用不同的变化等级和阈值,建立了回热系统典型故障样本模式知识库及实时故障模式集。同时利用基于MATLAB环境下的径向基函数网络,建立了回热系统故障诊断模型。并利用电站仿真机模似典型故障进行了神经网络模型的验证。实践表明,这种方法可有效地进行回热加热器故障样本模式的模糊量化处理,极大地改善了神经网络训练的收敛性。有利于回热系统的故障诊断。     

人工神经网络在混合智能故障诊断技术中的应用研究

故障诊断的关键是寻找一种使诊断结果更为有效的方法。人工神经网络作为一种新兴的故障诊断方法，越来越受到人们的关注。然而，对于复杂的系统，单一的传统神经网络很难给出理想的结果。本文重点对神经网络与其它诊断方式融合的混合智能技术，即神经网络与专家系统、模糊控制、小波分析和遗传算法的结合以及集成神经网络等在故障诊断中的应用进行了综述。这些方法已应用到实践中，并取得了一定的成果。     

基于BP网络的故障诊断方法及其在电站中的应用

电站机组可能会发生各种故障，有些故障没有明显征兆。为能诊断这类故障，需要新的方法。提出了根据当前技术条件下可以测量到的参数，而不一定是故障特征参数，进行故障诊断的思路。介绍了BP人工神经网络的结构和学习方法，提出了基于BP网络的模式识别能力，建立电站性能监测与诊断系统的新思路和方法。利用该方法，对电站设备性能下降故障的程度进行了成功诊断。图2表2参3     

基于知识与模糊神经网络的故障诊断技术

论述了建立规则型模糊神经网络的理论和方法,针对大型旋转机械提出了一种采用多层规则库结构及智能推理机的故障诊断技术,该技术以Ｒｕｌｅ型模糊联想记忆器作为诊断系统的分类和综合算法,把基于知识的符号处理方法与模糊神经网络有机结合在一起,讨论了模糊神经网络输入和输出模糊化的问题,为电厂汽轮发电机组故障诊断专家系统提供了新的思路。     

网络化汽轮机组远程监测及故障诊断系统的研究

针对火电机组状态监测和故障诊断方面存在的不足，提出了建立省级故障诊断中心，并研究开发了网络化汽轮机组远程监测及故障诊断系统，已应用于生产实际，在汽轮发电机组运行和维修中发挥了重要作用。介绍了该系统的体系结构、软件结构、网络技术及特点，并给出应用实例说明其实用性和有效性。图7参1     

基于小波神经网络的旋转机械故障诊断

研究了小波变换与人工神经网络结合起来应用于旋转机械故障诊断的问题。通过选择合适的参数，对故障信号功率谱进行小波分解，简化了故障特征向量的提取。建立了基于小波变换和BP网络的混合诊断模型，成功地实现了对故障的智能诊断。     

Deep learning methods and applications for electrical power systems: A comprehensive review

Over the past decades, electric power systems (EPSs) have undergone an evolution from an ordinary bulk structure to intelligent flexible systems by way of advanced electronics and control technologies. Moreover, EPS has become a more complex, unstable and nonlinear structure with the integration of distributed energy resources in comparison with traditional power grids. Unlike classical approaches, physical methods, statistical approaches and computer calculation techniques are commonly used to solve EPS problems. Artificial intelligent (AI) techniques have especially been used recently in many fields. Deep neural networks have become increasingly attractive as an AI approach due to their robustness and flexibility in handling nonlinear complex relationships on large scale data sets. Major deep learning concepts addressing some problems in EPS have been reviewed in the present study by a comprehensive literature survey. The practices of deep learning and its combinations are well organized with up-to-date references in various fields such as load forecasting, wind and solar power forecasting, power quality disturbances detection and classifications, fault detection power system equipment, energy security, energy management and energy optimization. Furthermore, the difficulties encountered in implementation and the future trends of this method in EPS are discussed subject to the findings of current studies. It concludes that deep learning has a huge application potential on EPS, due to smart technologies integration that will increase considerably in the future.     

Small-batch-size convolutional neural network based fault diagnosis system for nuclear energy production safety with big-data environment

In nuclear energy production, with the continuous innovations and challenges in the big data and the industry 4.0 era, to guarantee the operation safety without the fault and failure will become more complex and intelligent. In this paper, a novel optimized convolutional neural network with small-batch-size processing (SCNN) was proposed and assembled in the nuclear fault diagnosis system. Eleven kinds of normal and fault conditions that include the whole 316 simulator sensor features were used to evaluate the performance of the proposed diagnosis system. The application of batch normalization with SCNN significantly optimized the model validation accuracy and loss under 100 epochs compared with normal operation and adding drop-out operation in same condition. Besides, outstanding diagnosis accuracy was highlighted by the comparison of traditional binary and multiple classification methods. This proposed diagnosis system has achieved more precise diagnosis accuracy and will provide the useful guidance to operators, assisting them to make accurate and rapid decision to ensure nuclear energy production safety.     

Fault detection in PV systems

A practical fault detection approach for PV systems intended for online implementation is developed. The fault detection model here is built using artificial neural network. initially the photovoltaic system is simulated using MATLAB software and output power is collected for various combinations of irradiance and temperature. Data is first collected for normal operating condition and then four types of faults are simulated and data are collected for faulty conditions. Four faults are considered here and they are: Line to Line faults with a small voltage difference, Line to line faults with a large voltage difference, degradation fault and open-circuit fault. This data is then used to train the neural network and to develop the fault detection model. The fault detection model takes irradiance, temperature and power as the input and accurately gives the type of fault in the PV system as the output. This system is a generalized one as any PV module datasheet can be used to simulate the Photovoltaic system and also this fault detection system can be implemented online with the use of data acquisition system.     

基于功率预测的风力机健康状态监测

随着风力发电的广泛应用,对风力机健康状态进行准确监测的重要性日益凸显,为此提出了一种基于风力机功率预测的健康状态监测方法,即结合多项式模型和自回归模型特点,考虑风速与风力机输出功率之间的相关性和滞后性,利用改进非线性自回归模型对某风场风力机输出功率进行预测,并将预测结果与传统灰色模型、BP神经网络模型预测结果进行对比,计算与实测数据之间的误差。最后,选取功率预测系数中变化较为稳定的系数项作为观测系数,通过标准残差法确定异常观测系数反推风力机健康状态。分析结果表明,改进非线性自回归模型预测值与实测数据较为接近,趋势较为吻合。相比于传统灰色模型、BP神经网络模型,改进非线性自回归模型预测误差较小,精度较高。可见通过分析功率预测系数变化能够及时发现风力机健康状态变化,为故障发现提供参考。     

A heuristic method of variable selection based on principal component analysis and factor analysis for monitoring in a 300 kW MCFC power plant

In a commercialized 300 kW molten carbonate fuel cell (MCFC) power plant, a univariate alarm system that has only upper and lower limits is usually employed to identify abnormal conditions in the system. Even though univariate alarms have already been adopted for system monitoring, this simple monitoring system is limited for using in an extended monitoring system for fault diagnosis. Therefore, based on principal component analysis (PCA), a recursive variable grouping method for a multivariate monitoring system in a commercialized MCFC power plant is presented in this paper. In terms of development, since a principal component analysis model that contains all system variables cannot isolate a system fault, heuristic recursive variable selection method using factor analysis is presented here. To verify the performance of the fault detection, real plant operations data are used. Furthermore, comparison between type 1 and type 2 errors for four different variable groups demonstrates that the developed heuristic method works well when system faults occur. These monitoring techniques can reduce the number of false alarms occurring on site at MCFC power plant.