Power System Fault Diagnosis Based on Wavelet Transform and Neural Networks

2014 ◽  
Vol 705 ◽  
pp. 255-258 ◽  
Author(s):  
Jun Liu ◽  
Lin Li ◽  
Qing Tao Long
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Wavelet Transform ◽  
Power System ◽  
Electric Power ◽  
Electric Power System ◽  
Singularity Detection ◽  
Fault Recognition ◽  
The Neural Network ◽  
Simulation Results

Using the principle of wavelet transform in the aspect of signal singularity detection analyzes and detects the electric power system fault signal. Then we extract signal feature near the fault moment and sent the feature vectors into the neural network. The simulation results fully prove the effectiveness and superiority of combining wavelet transform and neural network in electric power system fault recognition.

Use of Wavelet Transform and Generalized Regression Neural Network (GRNN) to the Characterization of Short-Duration Voltage Variation in Electric Power System.

2009 ◽  
Vol 7 (2) ◽  
pp. 217-222 ◽  
Author(s):  
Raimundo Nonato das Merces Machado ◽  
Ubiratan Holanda Bezerra ◽  
Evaldo Goncalves Pelaes ◽  
Roberto Celio Limao de Oliveira ◽  
Maria Emilia de Lima Tostes
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Power System ◽  
Electric Power ◽  
Short Duration ◽  
Electric Power System ◽  
Generalized Regression Neural Network ◽  
Voltage Variation ◽  
Generalized Regression

The Design of a Wavelet-Based Neural Network Adaptive Filter

2013 ◽  
Vol 860-863 ◽  
pp. 2791-2795
Author(s):  
Qian Xiao ◽  
Yu Shan Jiang ◽  
Ru Zheng Cui
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Real Time ◽  
Adaptive Filter ◽  
Adaptive Algorithm ◽  
Distributed Storage ◽  
Hopfield Neural Network ◽  
Lms Algorithm ◽  
The Neural Network ◽  
Simulation Results

Aiming at the large calculation workload of adaptive algorithm in adaptive filter based on wavelet transform, affecting the filtering speed, a wavelet-based neural network adaptive filter is constructed in this paper. Since the neural network has the ability of distributed storage and fast self-evolution, use Hopfield neural network to implement adaptive filter LMS algorithm in this filter so as to improve the speed of operation. The simulation results prove that, the new filter can achieve rapid real-time denoising.

scholarly journals STUDI ANALISIS UFR (UNDER FREQUENCY RELAY) PADA GARDU INDUK PESANGGARAN

2019 ◽  
Vol 6 (2) ◽  
pp. 45
Author(s):  
Bhrama Sakti K.P. ◽  
A.A. Gede Maharta Pemayun ◽  
I Gede Dyana Arjana
Keyword(s):  
Power Plant ◽  
Power System ◽  
Electric Power ◽  
Recovery Time ◽  
Electric Power System ◽  
Calculation Results ◽  
Working Principle ◽  
Simulation Results ◽  
System Frequency ◽  
Frequency State

The disruption of the electric power system due to overcurrent causes a trip to the 3rd generator of pesanggaran power plant . This causes a decrease in frequency due to the system losing its supply. Frequency interference can be detected automatically with UFR (Under Frequency Relay). The working principle of UFR is to compare the value of the system frequency and the value of the frequency setting. The comparison will determine how much load is released to balance the generator supply. This study analyzes UFR performance at Pesanggaran Substation by simulating a case of the generator being released so as to produce a decreased system frequency state. The method used is by comparing the ETAP simulation results and calculation results. The results of the comparison obtained the system recovery time when the conditions (gen1 tripped), (gen1 and gen2 tripped), and (gen1, gen2, and gen3 tripped), each is 1.171s; 4,531s; and 4,514s.

All-mode Validation of Calculations in the Analysis of Electric Power

2020 ◽  
Vol 11 (11) ◽  
pp. 28-37
Author(s):  
Aleksey A. SUVOROV ◽  
◽  
Alexander S. GUSEV ◽  
Mikhail V. ANDREEV ◽  
Alisher B. ASKAROV ◽  
...  
Keyword(s):  
Mathematical Model ◽  
Differential Equations ◽  
Power System ◽  
Electric Power ◽  
Field Data ◽  
Transient Stability ◽  
Experimental Studies ◽  
Electric Power System ◽  
Adequate Model ◽  
Simulation Results

The transient stability is the main condition for reliability and survivability operation of electric power system. The transient stability analysis is an extremely complex problem. It uses the results of numerical integration of differential equations that form a mathematical model of the power system. However, the mathematical model of a large-scale power system contains a rigid nonlinear system of extremely high-order differential equations. Such system cannot be solved analytically. The simplifications and limitations are used for improving the conditionality of the power system mathematical model in time-domain simulation. It decreases the reliability and accuracy of the simulation results. In this regard, it becomes necessary to validate them. The most reliable way of validation is to compare simulation results with field data. However, it is not always possible to receive the necessary amount of field data due to many power system states and a large amount of disturbances leading to instability. The paper proposes an alternative approach for validation: using an adequate model standard instead of field data. The prototype of Hybrid Real Time Power System Simulator having the necessary properties and capabilities has been used as the reference model. The appropriate sequence of actions has been developed for validation. The adequacy of proposed approach is illustrated by the fragments of the experimental studies

Electricity Peak Load Demand using De-noising Wavelet Transform integrated with Neural Network Methods

2016 ◽  
Vol 6 (1) ◽  
pp. 12
Author(s):  
Pituk Bunnoon
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Power Systems ◽  
Peak Load ◽  
Electric Power System ◽  
Load Demand ◽  
The Neural Network ◽  
Forecasting Method ◽  
Neural Network Algorithm ◽  
The One

One of most important elements in electric power system planning is load forecasts. So, in this paper proposes the load demand forecasts using de-noising wavelet transform (DNWT) integrated with neural network (NN) methods. This research, the case study uses peak load demand of Thailand (Electricity Generating Authority of Thailand: EGAT). The data of demand will be analyzed with many influencing variables for selecting and classifying factors. In the research, the de-noising wavelet transform uses for decomposing the peak load signal into 2 components these are detail and trend components. The forecasting method using the neural network algorithm is used. The work results are shown a good performance of the model proposed. The result may be taken to the one of decision in the power systems operation.

Sign in / Sign up

Export Citation Format

Share Document