基于神经网络的距离保护训练算法的研究

对神经网络式距离保护做了简要概述,并且为了使该新型保护更加完善,对其存在的训练算法问题做了深入的研究。对8种改进的BP(Back-Propagation)算法训练神经网络进行了比较,通过反复训练,得出8种算法在权值调整和误差收敛过程中所遇到的共同点和差别,并得出初始权值、激励函数和神经元个数等因素的选取对神经网络学习的影响。实验证明:LM算法和尺度共轭梯度反向传播算法训练网络收敛速度快,受权值影响小,但占用较大的内存;贝叶斯正则化算法有较好的泛化能力。     

基于神经网络的距离保护训练算法的研究

对神经网络式距离保护做了简要概述,并且为了使该新型保护更加完善,对其存在的训练算法问题做了深入的研究.对8种改进的BP(Back-Propagation)算法训练神经网络进行了比较,通过反复训练,得出8种算法在权值调整和误差收敛过程中所遇到的共同点和差别,并得出初始权值、激励函数和神经元个数等因素的选取对神经网络学习的影响.实验证明:LM算法和尺度共轭梯度反向传播算法训练网络收敛速度快,受权值影响小,但占用较大的内存;贝叶斯正则化算法有较好的泛化能力.     

Fault impedance estimation algorithm for digital distance relaying

Fault impedance is one of the major parameters that must be estimated accurately in digital distance relaying application. In this paper, a new algorithm is proposed based on symmetrical components theory. The proposed algorithm has computational advantage over previously suggested symmetrical components based algorithms. A procedure for applying shunt fault conditions to the sequence equations to estimate fault impedance of the protected transmission line is discussed. The Alternative Transient Program (ATP) that is available on personal computers was used in evaluating the proposed algorithm. ATP models a power system and simulates many fault conditions on a selected transmission line. Fault data obtained were used in calculating fault impedance using the proposed algorithm. Fault impedance estimates were inserted in relay characteristics to determine suitability of the proposed algorithm for first zone distance protection. Sample results of these studies which show stable fault distance estimates are presented and discussed in the paper     

Numerical distance relaying algorithm based on Mathematical Morphology and Least-Squares Curve Fitting method

A new numerical distance relaying algorithm based on Mathematical Morphology and a Least-Square Curve Fitting has been proposed. It makes use of morphological operators to detect and classify the faults and a Curve Fitting method to estimate the fault distance. To show the effectiveness of the proposed technique, computer simulations have been carried out on a test system, considering several fault types in different locations, loading angle and fault incidence angle. Due to simple mathematics operations used, the protection scheme proposed displays secure and effective high speed fault detection and tripping.     

A new distance relaying algorithm based on complex differential equation for symmetrical components

This paper presents a new digital impedance measuring technique for transmission lines that combines symmetrical components and the complex differential equation of an equivalent fault loop circuit. The phase voltages and currents at the relaying point are transformed into symmetrical components using Fourier filters of short window length. Depending on fault type, an appropriate fault loop circuit is formed, signals of which are the appropriate symmetrical components, while a parameter of which is the positive sequence impedance being a geometrical measure of the distance from the relaying point to a fault. The impedance, however, is measured very fast by on-line solving the complex differential equation originated for this fault loop circuit. Consequently, this approach combines frequency domain estimation of symmetrical components (accurate filtration) and time domain measurement of positive sequence impedance (high speed response).

The presented method suits well the protection of parallel lines against high-resistance faults occurring very close to the far end of a line. A new method is proposed for detecting high-resistance faults and deciding which line out of two parallel lines actually suffers a fault.

The included EMTP test results demonstrate the efficiency of the proposed relaying algorithm.     

First-zone distance relaying algorithm of parallel transmission lines for single-phase to ground faults

A novel zone-one distance relaying algorithm for single phase to ground faults on parallel lines is proposed. The proposed algorithm only requires sampled current and voltage values at one end of the protected line to calculate the fault impedance. The adjacent circuit zero-sequence current can be calculated from the protected circuit zero-sequence current and without cross-connection. The algorithm can overcome the issues of overreach and under-reach. The study in this paper shows that the new algorithm has higher reliability than that of conventional distance relays with and without cross-connected zero-sequence current compensation. Therefore, the algorithm optimizes the performance of zone-one distance relaying for parallel transmission lines. The results are verified by the simulations using PSCAD software.     

Multi-layer neural networks applied to distance relaying

This paper demonstrates the use of Artificial Neural Networks (ANNs) as pattern classifiers for a distance relay operation of transmission lines. Two different types of ANN architectures, concerning the input data, are taken into account. One approach utilises the first five post-fault samples as inputs. The other one employs the magnitudes of the three-phase voltage and current phasors (including the zero sequence) as inputs. A comparison of how well the schemes performed is carried out. An improvement concerning the use of ANNs for protection purposes is found.     

A novel fuzzy neural network based distance relaying scheme

This paper presents a new approach to distance relaying using fuzzy neural network (FNM). The FNN can be viewed either as a fuzzy system, a neural network or fuzzy neural network. The structure is seen as a neural network for training and a fuzzy viewpoint is utilized to gain insight into the system and to simplify the model. The number of rules is determined by the data itself and therefore a smaller number of rules is produced. The network is trained with the backpropagation algorithm. A pruning strategy is applied to eliminate the redundant rules and fuzzification neurons, consequently a compact structure is achieved. The classification and location tasks are accomplished by using different FNN's. Once the fault type is identified by the FNN classifier the selected fault locating FNN estimates the location of the fault accurately. Normalized peaks of fundamental voltage and current waveforms are considered as inputs to all the networks and an additional input derived from the DC component is fed to fault locating networks. The peaks and DC component are extracted from sampled signals by the EKF. Test results show that the new approach provides robust and accurate classification/location of faults for a variety of power system operating conditions even with resistance in the fault path     

ANN based directional relaying scheme forprotection of Korba-Bhilai transmission lineof Chhattisgarh state

As it is crucial to protect the transmission line from inevitable faults consequences, intelligent scheme must be employed for immediate fault detection and classification. The application of Artificial Neural Network (ANN) to detect the fault, identify it’s section, and classify the fault on transmission lines with improved zone reach setting is presented in this article. The fundamental voltage and current magnitudes obtained through Discrete Fourier Transform (DFT) are specified as the inputs to the ANN. The relay is placed at section-2 which is the prime section to be protected. The ANN was trained and tested using diverse fault datasets; obtained from the simulation of different fault scenarios like different types of fault at varying fault inception angles, fault locations and fault resistances in a 400 kV, 216 km power transmission network of CSEB between Korba-Bhilai of Chhattisgarh state using MATLAB. The simulation outcomes illustrated that the entire shunt faults including forward and reverse fault, it’s section and phase can be accurately identified within a half cycle time. The advantage of this scheme is to provide a major protection up to 99.5% of total line length using single end data and furthermore backup protection to the forward and reverse line sections. This routine protection system is properly discriminatory, rapid, robust, enormously reliable and incredibly responsive to isolate targeted fault.     

An algorithm using a shape-based approach in Park's plane for transformer differential relaying on the basis of time-dependent symmetrical components

Discrimination between inrush transients and internal faults is an issue of most concern in differential relaying when protecting power and distribution transformers. Based on an analysis of the symmetrical components obtained during inrush and during internal fault conditions, a linkage between their instantaneous evolution and the shapes of plots in Park's plane is presented in this paper. The use of Park transformation allows to avoid conventional spectrum analysis, what results in a quite simplified protective technique. By introducing a vector, which is defined as the sum of the vectors corresponding to measurements in both sides of the transformer, a categorization of shapes of plots is done here. Thus, a shape-based rule is presented for discriminating between inrush and fault in this paper. In addition, an algorithm is presented for fast classification of shapes. The proposed algorithm is based on the periodicity generated by the modulus of the defined Park's vector. The approach presented in this paper has been tested in a laboratory transformer, showing a robust, accurate and fast performance.     

ANN based directional relaying scheme for protection of Korba-Bhilai transmission line of Chhattisgarh state

As it is crucial to protect the transmission line from inevitable faults consequences, intelligent scheme must be employed for immediate fault detection and classification. The application of Artificial Neural Network (ANN) to detect the fault, identify it’s section, and classify the fault on transmission lines with improved zone reach setting is presented in this article. The fundamental voltage and current magnitudes obtained through Discrete Fourier Transform (DFT) are specified as the inputs to the ANN. The relay is placed at section-2 which is the prime section to be protected. The ANN was trained and tested using diverse fault datasets; obtained from the simulation of different fault scenarios like different types of fault at varying fault inception angles, fault locations and fault resistances in a 400 kV, 216 km power transmission network of CSEB between Korba-Bhilai of Chhattisgarh state using MATLAB. The simulation outcomes illustrated that the entire shunt faults including forward and reverse fault, it s section and phase can be accurately identified within a half cycle time. The advantage of this scheme is to provide a major protection up to 99.5% of total line length using single end data and furthermore backup protection to the forward and reverse line sections. This routine protection system is properly discriminatory, rapid, robust, enormously reliable and incredibly responsive to isolate targeted fault.     

浅谈提高继电保护辅助装置可靠性的措施

继电保护辅助装置在电力系统继电保护中起着极为重要的作用 ,因此其动作可靠性很受关注。影响继电保护辅助装置动作可靠性的原因主要有辅助装置中使用的中间继电器线圈断线、触点接触不良或烧损等。结合辅助装置有关回路的设计要求 ,提出一些提高辅助装置可靠性的措施。     

Application of a distance relaying scheme to compensate fault location errors due to fault resistance

This paper proposes a distance relaying scheme based on the current phase jump behavior during fault conditions to improve the apparent impedance estimated by the distance relay. For a nonpilot protection scheme, the measured impedance is affected by error due to the combined effects of fault resistance and prefault load. An experimental relation between the current phase jump introduced with fault inception and the X/R ratio seen by the distance protection is deduced. The phase jump correction factor obtained is an exponential function of the X/R ratio of the line. This factor is applied to the apparent impedance measured by the relay and it allows mitigating the adverse effect of prefault power. The relaying scheme improves significantly the accuracy in estimation of the resistive fault location. The application of this scheme does not require communication links from the remote end of line and is applicable to all types of fault.     

浅谈提高继电保护辅助装置可靠性的措施

继电保护辅助装置在电力系统继电保护中起着极为重要的作用,因此其动作可靠性很受关注.影响继电保护辅助装置动作可靠性的原因主要有辅助装置中使用的中间继电器线圈断线、触点接触不良或烧损等.结合辅助装置有关回路的设计要求,提出一些提高辅助装置可靠性的措施.     

基于准同步算法的谐波分析方法

介绍了一种采用准同步算法的谐波分析量方法，在不需要采样严格同步的条件下实现高精度的测量。仿真结果表明该方法的可行性及优越性。     

An algorithm to estimate mean traffic speed using uncalibratedcameras

We present a novel approach to estimate traffic speed using a sequence of images from an uncalibrated camera. We assert that exact calibration is not necessary to estimate speed. Instead, we use: 1) geometric relationships inherently available in the image, 2) some common-sense assumptions that reduce the problem to a one-dimensional geometry, 3) frame differencing to isolate moving edges and track vehicles between frames, and 4) parameters from the distribution of vehicle lengths to estimate speed     

An efficient algorithm to calculate intrinsic thermoelectric parameters based on Landauer approach

The Landauer approach provides a conceptually simple way to calculate the intrinsic thermoelectric (TE) parameters of materials from the ballistic to the diffusive transport regime. The approach relies on the calculation of the number of propagating modes and the mean free path for each mode. The modes are calculated from the energy dispersion (E(k)) of the materials, which require heavy computation and are often restricted to energy relations on sparse momentum (k) grids. Here an efficient method to calculate the distribution of modes (DOM) from a given E(k) relationship is presented. The two main features of this algorithm are: (i) its ability to work on sparse dispersion data, and (ii) creation of an energy grid for the DOM that is almost independent of the dispersion data therefore allowing for efficient and fast calculation of TE parameters. The effect of K-grid sparsity on the compute time for DOM and on the sensitivity of the calculated TE results are provided. The algorithm calculates the TE parameters within 5% accuracy when the K-grid sparsity is increased up to 60% for all the dimensions (3D, 2D and 1D). The time taken for the DOM calculation is strongly influenced by the transverse K density (K perpendicular to transport direction) but is almost independent of the transport K density (along the transport direction). The DOM and TE results from the algorithm are bench-marked with, (i) analytical calculations for parabolic bands, and (ii) realistic electronic and phonon results for Bi₂Te₃.     

An efficient ordering algorithm to improve sparse vector methods

The authors present a novel node-ordering algorithm to enhance sparse vector methods in power system analysis. The proposed technique locally minimizes the number of nonzero elements of the inverse of the table of factors. It uses the cardinality of the set of nodes which precede each node in the path graph as a tie-break criterion in the minimum degree elimination process. Test results are included showing that the method performs better than previously published methods     

Transmission line distance relaying using a variable window short-time Fourier transform

This paper presents a new approach for transmission line protection using a variable window short-time Fourier transform known as S-transform. The S-transform (ST) is a time–frequency spectral localization method, similar to short-time Fourier transform (STFT), but with a Gaussian window whose width scales inversely, and whose height scales linearly with the frequency. The change in spectral energy of the ST of the current and voltage signals provide the information regarding fault detection. After the fault detection, the impedance to the fault point is calculated using the estimated phasors of the faulted current and voltage signals which provide accurate results even with noisy conditions. Also, the fault location is calculated using polynomial curve fitting technique with a devised index obtained from the ratio of spectral energy of the voltage and current signals, respectively.     

基于Matlab的计算机距离保护微分方程算法仿真与研究

运用Matlab完成电力系统计算机距离保护的仿真,应用了两种基于线路模型的解微分方程的阻抗算法,分析了其应用于不同参数线路时的适应性,并通过分析在考虑存在干扰和误差时的阻抗计算结果,对两种算法的稳定性进行了研究.还对这两种算法的工程应用提出了有益的建议.