An artificial neural network approach to transformer faultdiagnosis

This paper presents an artificial neural network (ANN) approach to the diagnosis and detection of faults in oil-filled power transformers based on dissolved gas-in-oil analysis. A two-step ANN method is used to detect faults with or without cellulose involved. Good diagnosis accuracy is obtained with the proposed approach     

An adaptive neural network approach to one-week ahead loadforecasting

A neural network approach is proposed for one-week ahead load forecasting. This approach uses a linear adaptive neuron or adaptive linear combiner called Adaline. An energy spectrum is used to analyze the periodic components in a load sequence. The load sequence mainly consists of three components: base load component, and low and high frequency load components. Each load component has a unique frequency range. A load decomposition is made for the load sequence using digital filters with different passband frequencies. After load decomposition, each load component can be forecasted by an Adaline. Each Adaline has an input sequence, an output sequence, and a desired response-signal sequence. It also has a set of adjustable parameters called the weight vector. In load forecasting, the weight vector is designed to make the output sequence, the forecasted load, follow the actual load sequence; it also has a minimized least mean square error. This approach is useful in forecasting unit scheduling commitments. Mean absolute percentage errors of less than 3.4% are presented from five months of utility data, thus demonstrating the high degree of accuracy that can be obtained without dependence on weather forecasts     

An artificial-intelligence approach to ECG analysis

The issue we address in this article is how to reduce the computational burden by using an algorithm based on a linear-approximation distance-thresholding compression technique combined with the backpropagation neural network method. We also address how to improve the training speed. The experimental results found with the MIT-BIH database show that the new algorithm is faster in convergence and more accurate in feature recognition than existing methods     

An electrical network based on half-wave resonance systems

This paper contains an analysis of peculiarities of electricity transmission in a half-wave resonance single-wire transmission line. A principle of implementing distributed electrical networks based on a resonance system is proposed.     

An automated approach to beat-by-beat QT-interval analysis

The present work attempts to resolve some of the problems encountered in QT interval analysis and to describe a new algorithm that uses wavelets to analyze the QT interval on a beat-by-beat basis. The QT interval is further segmented into its contributing factors to find the variability in the repolarization phase. The technique and the algorithm have been tested on control and disease data from the standard MIT ECG library to prove the reproducibility and accuracy of the system. The technique has been implemented on a PC DSP add-on card to do the analysis on a beat-by-beat basis     

A rule based comprehensive approach for reconfiguration of electrical distribution network

This paper proposes a rule based comprehensive approach to study distribution network reconfiguration (DNRC). The DNRC model with line power constraints is set up, in which the objective is to minimize the system power loss. In order to get the precise branch current and system power loss, a power summation based radiation distribution network load flow (PSRDNLF) method is applied in the study. The rules that are used to select the optimal reconfiguration of distribution network are formed based on the system operation experiences. The proposed rule based comprehensive approach is implemented in distribution network in Guiyang South Power Supply Bureau. For the purpose of illustrating the proposed approach, two distribution network systems are tested and analyzed in the paper.     

A time-domain approach to transmission network equivalents viaProny analysis for electromagnetic transients analysis

This paper presents a method of obtaining transmission network equivalents from the network's response to a pulse excitation signal. The proposed method is based on modal decomposition representation for the large-scale interconnected system. In this framework we use Prony analysis to identify the network function of the system and to decompose the large system into a parallel combination of simple first-order systems. As a result the network function of the transmission network can be identified easily, and a Thevenin-type of discrete-time filter model can be generated. It can reproduce the driving-point impedance characteristic of the network. Furthermore, the proposed model can be implemented into the EMTP in a direct manner. The simulation results with the full system representation and the developed equivalent system showed a good agreement     

基于多层前向神经网络的基波检测方法

基波检测是系统控制和电能质量调节装置的一项很重要的任务,检测方法的精确性和实时性是系统可靠控制和有效调节的基础和关键.提出了一种基于多层前向人工神经网络实现基波检测的方法,检测网络采用误差反向传播的神经网络,结合电力系统中畸变波形的特点生成训练样本,并对神经网络的结构和参数进行了优化研究.该方法可以快速而准确地检测出畸变电网中的基波信号,仿真与实验均表明其具有优良的检测效果和跟踪速度,而且具有一定的泛化和外推能力,对于未经训练的含有更高次谐波的样本同样具有良好的检测能力.     

利用网络监听技术获取SDH网管信息

电力通信网中存在很多基于TMN体系的不同网络管理系统，有必要建立一种综合网管系统来收集不同专业网管的告警信息，进一步给予处理，完成复杂的管理任务，满足电力通信网的要求。网络监听是获得告敬信息的最便捷的方法。论文描述了利用网络监听技术获取网管信息的方法，说明了信息转换系统的设计与实现，此系统具有的信息处理功能，能很好地满足综合SDH故障管理系统的要求。     

An energy approach to analysis of interarea oscillations in powersystems

In this paper, an energy approach to analysis of interarea oscillations (IAO) in power systems has been developed. IAO is characterized as oscillatory behavior, following a disturbance, of the rotor motion for two or more generator groups such that there is a periodic interchange of energy between them. By comparing the phase of the coefficient of the dominant energy mode in the kinetic energy for each generator, we identify the groups for which there are periodic interchanges of energy. The location of these groups in the system provides insight regarding transmission lines over which the energy interchange is taking place. Numerical results are obtained using a test system similar in structure and characteristics to that of the WSCC system in North America. Time domain simulation indicates installation of thyristor controlled series capacitors in key transmission lines identified using the results of the energy analysis provides an effective control for damping IAO     

Harmonic modeling,analysis, mitigation of Kuwait EHV electrical network

The issue of power system quality has been of great concern in the last decade. The problem associated with high harmonic contents in the power system not only results in poor quality of supply but also the operation of the system will get affected. Thus, the quality of a power supply system can be assured with the implementation of effective harmonic analysis and compensation. This paper presents a harmonic analysis of the Kuwait EHV network. Maximum loading conditions for the network are considered. Big industrial loads are located and simulated as they are considered the main source of harmonics in this network. The network is modeled using ETAP PowerStation software for both fundamental and harmonic load flow studies. A complete fundamental and harmonic load flow analysis is performed. Standard harmonic limits are adopted to propose the suitable shunt filters in order to reduce the total harmonic distortion. Results before and after using filters are presented and evaluated.     

An efficient algebraic approach to observability analysis in state estimation

An efficient and compact algebraic approach to state estimation observability is proposed. It is based on transferring rows to columns and vice versa in the Jacobian measurement matrix. The proposed methodology provides a unified approach to observability checking, critical measurement identification, determination of observable islands, and selection of pseudo-measurements to restore observability. Additionally, the observability information obtained from a given set of measurements can provide directly the observability obtained from any subset of measurements of the given set. Several examples are used to illustrate the capabilities of the proposed methodology, and results from a large case study are presented to demonstrate the appropriate computational behavior of the proposed algorithms. Finally, some conclusions are drawn.     

Neural network approach to the solution of linear complementarity problems

The paper presents the application of nonlinear neural optimization networks to solve the linear complementarity problem. Two different approaches are presented and investigated: one leading to linear and the second to quadratic optimization programming. The numerical results of illustrative examples are given and discussed.     

On the minimum hybrid rank of a graph relative to a partition of its edges and its application to electrical network analysis

We consider the following problem in this paper: given a partition of the set of edges of a graph such that the subgraphs on the blocks of the partition are connected, what is the minimum number of node fission (splitting a node into two) and node fusion (coalescing two nodes) operations that will destroy all circuits containing edges from more than one block of the partition? This problem can be seen to be a generalization of the problem of determining the minimum hybrid rank of a graph. We may therefore regard this minimum number as the minimum hybrid rank of the graph relative to a specified partition of the edge set of the graph. We give an efficient algorithm for the construction of a minimum length sequence of such operations. Our solution can be applied to the problem of analysing networks after first decomposing them into subnetworks-the equations of the network can be displayed in a bordered block diagonal form where the blocks along the diagonal correspond to the subnetworks and the thickness of the border corresponds to the minimum hybrid rank relative to the partition of the sets of edges of the network into the sets of edges of the subnetworks.     

An analytical approach for DG allocation in primary distribution network

This paper proposes an analytical expression to calculate the optimal size and an effective methodology to identify the corresponding optimum location for DG placement for minimizing the total power losses in primary distribution systems. The analytical expression and the methodology are based on the exact loss formula. The effect of size and location of DG with respect to loss in the network is also examined in detail. The proposed methodology was tested and validated in three distribution test systems with varying size and complexity. Results obtained from the proposed methodology are compared with that of the exhaustive load flows and loss sensitivity method. Results show that the loss sensitivity factor based approach may not lead to the best placement for loss reduction.     

An approach to the analysis of large perturbations in hydro-electric plants with Kaplan turbines

The paper presents a mathematical model of a hydro generating unit with a Kaplan turbine and the corresponding turbine governor, suitable for analysing large perturbations in the power frequency loop. An original method is proposed for representing the turbine characteristics, which considerably decreases the simulation computation time, as compared to the interpolation method. The simulation results are compared with measurements made on-site at the hydro-electric power plant Djerdap I. The model is further used to analyse the operation of the turbine governor and the influence its variable parameters have on the quality of response during large disturbances.     

Multi-objective-optimization-based approach to improve the electrical efficiency for organic solar cells

In this paper, new electrical scheme modeling and optimization approaches are proposed to improve the conversion efficiency of the organic solar cells. The electrical parameters such as shunt resistance, series resistance, saturation current, ideality factors, photo-current density and open-circuit voltage of the device have been ascertained using the Trust-Region Method (TR) for the double exponential solar cell model. The developed double exponential solar cell model is used to formulate the objective functions, which are the pre-requisite of genetic algorithm computation, to improve the conversion efficiency. The problem is then presented as a multi-objective optimization one where the electrical parameters are considered simultaneously. Therefore, the developed approach is used to search of the optimal electrical parameters to obtain better conversion efficiency of the organic solar cells. The proposed approach may provide a theoretical basis and physical insights for organic solar cells design.     

Computerized interactive model approach to electrical distribution system planning

The results are described of a research effort to apply the latest technology to the problem of energy distribution-system planning. The interactive computerized model used promises to be a valuable means of analysing and planning for future distribution systems.     

一种用于次同步谐振研究的电力系统外网等值方法

针对结构复杂的串补输电系统的外网采用何种方法等值及等值后系统保留多大规模这一问题,基于现有的对次同步谐振模式在电网中的传递特性的认识,提出了一种适用于次同步谐振研究的电力系统外网等值方法.根据短路等效阻抗及等值前系统平衡运行状态,确定外网等值参数,并结合次同步谐振研究结果的参数敏感性对等值参数进行适当处理.以系统频率阻抗作为评价指标确定外网合适的等值规模.该方法简单方便,易于实现,适用于结构复杂的串补输电系统的次同步谐振评估分析.通过南方电网的应用算例验证得出,采用该方法进行外网多点等值时等值参数的简化处理及等值规模的判定方法对次同步谐振研究结果的影响很小,从而说明了该方法的有效性.