Power Distribution Fault Cause Identification With Imbalanced Data Using the Data Mining-Based Fuzzy Classification E-Algorithm

Power distribution systems have been significantly affected by many outage-causing events. Good fault cause identification can help expedite the restoration procedure and improve the system reliability. However, the data imbalance issue in many real-world data sets often degrades the fault cause identification performance. In this paper, the E-algorithm, which is extended from the fuzzy classification algorithm by Ishibuchi to alleviate the effect of imbalanced data constitution, is applied to Duke Energy outage data for distribution fault cause identification. Three major outage causes (tree, animal, and lightning) are used as prototypes. The performance of E-algorithm on real-world imbalanced data is compared with artificial neural network. The results show that the E-algorithm can greatly improve the performance when the data are imbalanced     

A classification approach for power distribution systems fault cause identification

Power distribution systems play an important role in modern society. When distribution system outages occur, fast and proper restorations are crucial to improve the quality of services and customer satisfaction. Proper usages of outage root cause identification tools are often essential for effective outage restorations. This paper reports on the investigation and results of two popular classification methods: logistic regression (LR) and artificial neural network (ANN) applied on power distribution fault cause identification. LR is seldom used in power distribution fault diagnosis, while ANN has been extensively used in power system reliability researches. This paper discusses the practical application problems, including data insufficiency, imbalanced data constitution, and threshold setting that are often faced in power distribution fault cause identification problems. Two major distribution fault types, tree and animal contact, are used to illustrate the characteristics and effectiveness of the investigated techniques.     

Application of artificial neural network methods for the lightning performance evaluation of Hellenic high voltage transmission lines

Feed-forward (FF) artificial neural networks (ANN) and radial basis function (RBF) ANN methods were addressed for evaluating the lightning performance of high voltage transmission lines. Several structures, learning algorithms and transfer functions were tested in order to produce a model with the best generalizing ability. Actual input and output data, collected from operating Hellenic high voltage transmission lines, as well as simulated output data were used in the training, validation and testing process. The aims of the paper are to describe in detail and compare the proposed FF and RBF ANN models, to state their advantages and disadvantages and to present results obtained by their application on operating Hellenic transmission lines of 150 kV and 400 kV. The ANN results are also compared with results obtained using conventional methods and real records of outage rate showing a quite satisfactory agreement. The proposed ANN methods can be used by electric power utilities as useful tools for the design of electric power systems, alternative to the conventional analytical methods.     

Electricity price short-term forecasting using artificial neuralnetworks

This paper presents the system marginal price (SMP) short-term forecasting implementation using the artificial neural networks (ANN) computing technique. The described approach uses the three-layered ANN paradigm with backpropagation. The retrospective SMP real-world data, acquired from the deregulated Victorian power system, was used for training and testing the ANN. The results presented in this paper confirm considerable value of the ANN based approach in forecasting the SMP     

基于RBF神经网络非线性预测模型的开关磁阻电机自适应PID控制

开关磁阻电机的非线性和变参数特性使得采用传统的PID控制很难取得较好的控制效果。人工神经网络在一定的条件下可以任意精度逼近任意非线性函数且具有较强的自学习、自适应、自组织能力。故将其与传统的PID控制相结合构成神经网络自适应PID控制策略，应用于非线性严重的开关磁阻电机，可实现对开关磁阻电机的高性能控制。同时，神经网络所具有的非线性变换特性和高度的并行运算能力使得其适合建立非线性预测模型进行参数预测。通过对被控系统参数的预测，可提高系统的动态响应性能。该文采用两个神经网络-BP神经网络和RBF神经网络来分别构成神经网络NNC和神经网络NNI。神经网络NNC进行自适应PID参数调节；神经网络NNI用来建立非线性预测模型进行参数预测。为进一步加快神经网络的学习收敛速度，该文采用变学习速率的神经网络学习算法，学习速率随收敛过程误差的大小而自适应地进行调整，这可大大加快神经网络学习训练的收敛速度，进一步提高系统动态响应速度。实验结果表明，系统的动态响应快，超调小，稳态精度高，鲁棒性强，有较强的抗扰动能力，具有较好的控制效果。     

A variable structure adaptive neural network static VAR controller

A variable structure adaptive neural network power system static VAR stabilizer is developed. The static VAR compensator (SVC) controlled by the above proposed controller is used for voltage regulation and enhancing power system stability. The artificial neural network (ANN) is trained off-line using the variable structure control system Benchmark data at different operating conditions and external disturbances. Moreover, the trained ANN parameters (weights and biases) are tuned and updated on-line using the synchronous machine speed deviation state as the ANN output error to increasingly improve the power system performance. A sample digital simulation result of the power system speed deviation state responses when reference voltage, speed deviation state and input power disturbances take place are obtained. The digital simulation results prove the effectiveness and robustness of the present adaptive neural network in terms of a high performance power system.     

电流互感器饱和影响测距精度的一种解决方法

电流互感器(TA)饱和会给基于工频电气量的输电线路故障测距精度带来很大的误差。文中利用MATLAB程序，设计了一个前向BP网络，利用BP网络来对TA饱和电流进行矫正补偿，然后再进行故障测距。EMTP仿真的结果表明，对TA饱和电流进行补偿矫正后，明显地改进了故障测距的精度。     

Integrated fuzzy filter for distribution outage information

In many distribution management systems, customer trouble calls have been used as the main data source for low-level outage handling. Increased distribution supervisory control and data acquisition (SCADA) and recent developments in automated meter reading (AMR) systems are providing more metering information about the distribution system below the feeder breaker. However, the distribution system is so complex that no single data source can provide consistently errorless outage information for fast and accurate outage location determination. In this paper, an outage data processing algorithm is introduced, which provides more accurate outage information for the distribution outage management system by combining data from trouble call, AMR and distribution SCADA. Fuzzy logic is used in this algorithm to model the uncertainty of the outage information and to reconcile conflicting data. The filtered outage data include a reduced amount of accurate information for use in the outage location and system restoration algorithm.     

基于深度人工神经网络和GIS数据的最优停电模型研究

为了有效利用地理信息技术支撑复杂大电网的信息化建设,针对停电事故对电力系统运行和日常生活带来的诸多影响,提出基于深度人工神经网络和GIS数据的最优停电模型。结合电力系统运行的特殊性,把最优参数设置和增量反馈结合用来优化受限玻尔兹曼机算法。通过仿真分析了算法的性能。仿真结果表明,采用深度神经网络的最优停电模型可以提高计算效率和精度。     

基于Copula熵的神经网络径流预报模型预报因子选择

采用神经网络进行水文预报的关键问题之一是预报因子(输入变量)的选择,目前国内尚缺有效、系统的理论方法,国外主要是采用偏互信息(Patial mutual information,PMI)法。本文针对偏互信息计算方法的缺陷,引入Copula熵的概念,推导Copula熵与互信息的关系,提出采用Copula熵计算PMI;并借助模拟试验检验了所提方法的合理性;最后,将该方法应用到三峡水库的水文预报中,并与现行方法进行了比较分析。结果表明,本文所提方法不仅具有理论基础,而且结果合理可信。     

人工神经网络的混合电力补偿控制器设计

针对电力系统谐波补偿控制问题,基于人工神经网络技术,提出了电力补偿控制器设计方法,并给出了人工神经网络的结构、网络训练和测试的具体方法。实现了电力系统中谐波电流的自动检测,并根据谐波电流的具体情况实现补偿元件的自动切换以达到对谐波电流的补偿。仿真结果证明,利用神经网络技术实现对混合电力补偿器的控制是提高其动态性能的有效途径。     

青藏铁路变电站接地网设计规则的提取

为了获得建立青藏铁路变电站接地网设计专家系统所需的模糊规则,提出神经网络和遗传算法相结合的方法自动生成模糊规则.首先建立了用于青藏线接地网接地电阻求解的遗传优化神经网络,从而可以快速得到所需的大量样本数据,然后利用遗传算法优化计算得到了用于青藏线接地网设计的模糊规则.通过仿真对比计算表明,采用此方法得到的模糊规则可以为接地网设计专家系统的建立打下了基础.     

面向不平衡数据的配电网故障停电预测方法

配电网故障停电事件会严重影响正常的社会经济生活。因此,迫切需要有效的配电网故障停电预测方法。采用人工智能方法分析配电网故障停电数据,发现存在配电网故障停电次数较少和引发配电网故障停电的原因分布不均等数据不平衡情况。为了及时、准确地预测配电网故障停电情况,从数据集质量和防止过拟合两方面入手改进故障停电预测模型。首先,设计了基于聚类的对抗神经网络来增强数据集质量。其次,构造了基于随机代价敏感卷积神经网络(RandomCost-CNN)的故障停电预测模型。RandomCost-CNN预测算法中采用有放回随机抽样思想设计了损失函数的随机选择策略,用以解决常规代价敏感过度拟合少数类(故障停电类)而使得大量多数类(正常类)被误报的问题,既保证少数类具有较好召回率与精确度,同时又提高了模型的泛化性能。实验证明所提方法能有效预测配电网故障停电事件发生概率,在配电网运维管理中能够发挥较好的预警作用。     

A new artificial neural network based method for islanding detection of distributed generators

This paper presents an artificial neural network (ANN) based method for islanding detection of distributed synchronous generators. The proposed method takes advantage of ANN as pattern classifiers. It is capable of identifying the islanding condition based on samples of the voltage waveform measured at the distributed generator terminals only, which is an important advantage over other ANN-based anti-islanding methods. Moreover, the proposed method is robust against false operation. In order to create a training data set for the ANN, a data selection procedure has been proposed, so that the ANN could be trained more effectively, which has contributed positively to the good performance of the method. The concept of the time-performance region has been introduced to assess the method performance, as well as the non-detection zones. A detailed discussion about the data sampling rate to feed the proposed method has also been conducted, so that the computational burden can be faced as an important factor to assess its performance.     

基于ELMAN神经网络的同步电机动态参数在线辨识

为提高同步电机参数在线辨识的速度和可靠性，减少辨识计算量，提出了一种基于神经网络的电机参数动态跟踪辨识方法。针对同步电机暂态、次暂态参数的非线性和动态特性，在多层前向BP网络中引入特殊关联层，形成有“记忆”能力的Elman神经网络，因而可以映射系统的非线性和动态特性。在网络训练算法中，提出一种自适应修正步长和矩量因子的算法，显著提高了训练的收敛速度。训练样本集以同步电机在各种典型运行模式下的检测数据经卡尔曼滤波、状态空间有限元等基于模型的辨识算法离线计算得到。文中还给出了由工控机、智能数据采集卡和传感器锁相环控制接口电路构成的在线辨识硬件电路设计。数字仿真和动模实验机组辨识算例证明，这种Elman神经网络模型能够实现同步电机动态参数的在线跟踪辨识。     

基于GE Smallworld GIS的停电分析系统研究

本文提出了基于GE Smallworld GIS的停电分析系统,它是建立和维护从变电站至用户馈线连通性模型的工具.该系统可对配电网有关信息进行地理聚焦定位,可在GIS视图中进行停电范围分析和模拟停电分析,是配电网操作人员的一个决策支持工具.在综合环境中它可与企业的其它信息系统相互作用,是配网综合停电管理系统成功设计和实施的关键.研究的结果表明,该系统有很好实用价值,在停电管理方面的性能非常好.     

Observer-Based Speed Estimation Method for Sensorless Vector Control Using Artificial Neural Network

This paper presents a novel approach to sensorless vector control of induction motor drives. The method is based on an adaptive flux observer in the rotorspeed reference frame in which an artificial neural network (ANN) is employed to modify the estimated rotor flux to improve the performance of speed estimation. The adopted ANN is a feed-forward neural network identified off-line. It uses the backpropagation learning process to update their weights. The data for training are obtained from a computer simulation and experimental data file of a vector control system. Then, the estimated rotor flux is used in the speed estimation that will feedback to the vector control system. The proposed method has the advantages of better accuracy at low speed range and speed following under heavy loads. Experimental results show the effectiveness of the proposed method.     

基于多分辨率SVM回归估计的短期负荷预测

针对短期负荷预测支持向量机（SVM）方法的局部逼近能力和泛化能力进行研究,将多分辨率支持向量机（M—SVM）用于短期负荷预测中节点负荷预测曲线的回归估计。该理论在保持曲线总体逼近能力的同时提高了局部区域的逼近能力。文中根据短期负荷预测的具体特点,设计了负荷预测数学模型,采用96条回归曲线进行日负荷的曲线预测,并在该模型的基础上采用实际数据进行验证,分析了这种回归模型的泛化能力。实验结果表明M-SVM模型在预测精度和预测速度方面具有优良的特性。     

基于人工神经网络的风电功率预测

风电场输出功率预测对接入大量风电的电力系统运行有重要意义。对风速和风电场输出功率预测的方法进行了分类。根据风电场输出功率的影响因素,建立了风电功率预测的神经网络模型。分析了实测功率数据、不同高度的大气数据对预测结果的影响。建立了基于神经网络的误差带预测模型,实现了误差带预测。研究结果表明,神经网络的结构和输入样本对预测结果有一定的影响;实测功率数据作为输入可以提高提前量为30 min的预测精度,而对提前量为1 h的预测精度会降低;把不同高度的数据都作为神经网络的输入比只采用轮毂高度数据的预测精度高;设计的神经网络能够对误差带进行预测。     

基于神经网络的说话人识别算法的研究与实验

人工神经网络通过学习可以实现对输入向量的分类,也就是说,对于经过训练的神经网络,每输入一个矢量,人工神经网络输出一个该矢量所属类别的标号,神经网络的这种分类作用可以运用到说话人识别中.本文在介绍人工神经网络实现对输入向量分类原理的基础上,通过MATLAB实现了基于神经网络学习向量量化方法(LVQ)的说话人识别实验,取得了较为满意的结果.