Prediction of Power Transformer Fault Based on Auto Regression Model

2011 ◽  
Vol 317-319 ◽  
pp. 2230-2233
Author(s):  
Rui Rui Zheng ◽  
Bao Chun Wu ◽  
Ji Yin Zhao
Keyword(s):  
Regression Model ◽  
Power Transformer ◽  
Information Criterion ◽  
Fault Prediction ◽  
Transformer Oil ◽  
Ar Model ◽  
Prediction Algorithm ◽  
Gray Model ◽  
Transformer Fault ◽  
Auto Regression

Dissolved gases analysis is the essence to diagnose and forecast power transformer fault. This paper utilized an Auto Regression model to predict contents of gases dissolved in power transformer oil, and adopted Akaike's Information Criterion to determine model order. Then, the prediction results of AR model are compared with results of Gray model. Finally, gray artificial immune algorithm diagnosed power transformer fault types through gases contents predicted by Auto Regression model. Experiments demonstrates that Auto Regression model has a higher accuracy than Gray Model, and the fault prediction results of the proposed algorithm are in accord with the results using real gases contents, thus , the power transformer fault prediction algorithm present in the paper is effective and reliable.

Research on Power Transformer Fault Forecast

2011 ◽  
Vol 204-210 ◽  
pp. 1553-1558
Author(s):  
Rui Rui Zheng ◽  
Ji Yin Zhao ◽  
Min Li ◽  
Bao Chun Wu
Keyword(s):  
Time Series ◽  
Fault Location ◽  
Power Transformer ◽  
Forecast Model ◽  
Ratio Method ◽  
Gray Model ◽  
Artificial Immune ◽  
Diagnosis Method ◽  
Type Data ◽  
Transformer Fault

To forecast power transformer fault, this paper proposed a integrated algorithm. Research found that discrete time series of power transformer dissolved gases concentration have 2 main types: the s type and the monotone increasing type. The gray verhulst model was chosen for forecasting the s type series, while the gray model predicted the monotone increasing type data. The two models combined a new integrated forecast model. The fault diagnosis method combines the improved three-ratio method and gray artificial immune algorithm, so it can diagnoses both single and multi power transformer faults, and give the fault location. Experiments show that the power transformer fault forecast algorithm is effective and reliable.

Parallelization Analysis of Dissolved Gases in Transformer Oil Based on Random Forest Algorithm

2014 ◽  
Vol 519-520 ◽  
pp. 98-101
Author(s):  
De Wen Wang ◽  
Zhi Wei Sun
Keyword(s):  
Fault Diagnosis ◽  
Random Forest ◽  
Power Transformer ◽  
Gas Analysis ◽  
Transformer Oil ◽  
Dissolved Gases ◽  
Random Forest Algorithm ◽  
Dissolved Gas ◽  
Important Method ◽  
Transformer Fault

Dissolved gas analysis (DGA) in oil is an important method for transformer fault diagnosis. This paper use random forest parallelization algorithm to analysis the dissolved gases in transformer oil. This method can achieve a fast parallel fault diagnosis for power equipment. Experimental results of the diagnosis of parallelization of random forest algorithm with DGA samples show that this algorithm not only can improve the accuracy of fault diagnosis, and more appropriate for dealing with huge amounts of data, but also can meet the smart grid requirements for fast fault diagnosis for power transformer. And this result also verifies the feasibility and effectiveness of the algorithm.

scholarly journals Coercively Adjusted Auto Regression Model for Forecasting in Epilepsy EEG

2013 ◽  
Vol 2013 ◽  
pp. 1-12 ◽  
Author(s):  
Sun-Hee Kim ◽  
Christos Faloutsos ◽  
Hyung-Jeong Yang
Keyword(s):  
Time Series ◽  
Fractal Dimension ◽  
Regression Model ◽  
Random Coefficients ◽  
Experimental Results ◽  
Ar Model ◽  
Forecasting Method ◽  
Eeg Data ◽  
Future Value ◽  
Auto Regression

Recently, data with complex characteristics such as epilepsy electroencephalography (EEG) time series has emerged. Epilepsy EEG data has special characteristics including nonlinearity, nonnormality, and nonperiodicity. Therefore, it is important to find a suitable forecasting method that covers these special characteristics. In this paper, we propose a coercively adjusted autoregression (CA-AR) method that forecasts future values from a multivariable epilepsy EEG time series. We use the technique of random coefficients, which forcefully adjusts the coefficients with−1and 1. The fractal dimension is used to determine the order of the CA-AR model. We applied the CA-AR method reflecting special characteristics of data to forecast the future value of epilepsy EEG data. Experimental results show that when compared to previous methods, the proposed method can forecast faster and accurately.

Transformer Fault Diagnosis with the Duval Triangle and Heuristic Techniques

2014 ◽  
Vol 535 ◽  
pp. 157-161
Author(s):  
Jeeng Min Ling ◽  
Ming Jong Lin ◽  
Chao Tang Yu
Keyword(s):  
Fault Diagnosis ◽  
Power Transformer ◽  
Gas Analysis ◽  
Transformer Oil ◽  
Dissolved Gas ◽  
Power Company ◽  
Triangle Method ◽  
Diagnosis Method ◽  
Combustible Gases ◽  
Transformer Fault

Dissolved gas analysis (DGA) is an effective tool for detecting incipient faults in power transformers. The ANSI/IEEE C57.104 standards, the most popular guides for the interpretation of gases generated in oil-immersed transformers, and the IEC-Duval triangle method are integrated to develop the proposed power transformer fault diagnosis method. The key dissolved gases, including H2, CH4, C2H2, C2H4, C2H6, and total combustible gases (TCG), suggested by ASTM D3612s instruction for DGA is investigated. The tested data of the transformer oil were taken from the substations of Taiwan Power Company. Diagnosis results with the text form called IEC-Duval triangle method show the validation and accuracy to detect the incipient fault in the power transformer.

Multi-Level Fault Diagnosis of Power Transformer Based on Fusion Technology

2013 ◽  
Vol 860-863 ◽  
pp. 1925-1928
Author(s):  
Zhi Bin Li ◽  
Qi Ben Li
Keyword(s):  
Fault Diagnosis ◽  
Power Transformer ◽  
Complex Structure ◽  
Transformer Oil ◽  
Fusion Technology ◽  
Fault Type ◽  
Neural Network Algorithm ◽  
Multi Level ◽  
Transformer Fault ◽  
Source Of Information

Traditional transformer fault diagnosis based on single source of information has significant limitation in identification of transformer fault type because of power transformers complex structure and changeable operating environment. So fusion technology is introduced into the fault diagnosis of power transformer. This method divides the progress of transformer fault diagnosis into two fusion levels. The first level is to ascertain whether it is overheated or discharged by content of gases dissolved in transformer oil. The second level is to ascertain the location or cause of the fault by electric data. The intelligence algorithms which are used in these two levels are both the improved BP neural network algorithm. Finally, the effectiveness is validated by the result of practical fault diagnosis examples.

Detection of Power Transformer Fault Conditions using Optical Characteristics of Transformer Oil

2018 ◽  
Author(s):  
Nur Afini Fauzi ◽  
Vimal Angela Thiviyanathan ◽  
Yang Sing Leong ◽  
Pin Jern Ker ◽  
M. Z. Jamaludin ◽  
...  
Keyword(s):  
Power Transformer ◽  
Transformer Oil ◽  
Optical Characteristics ◽  
Transformer Fault

scholarly journals Transformer Incipient fault prediction using Support Vector Machine (SVM)

2021 ◽  
Vol 23 (05) ◽  
pp. 737-744
Author(s):  
A. Kumar ◽  
◽  
Vidya H. A. ◽  
Keyword(s):  
Support Vector Machine ◽  
Prediction Accuracy ◽  
Power Transformer ◽  
Gas Analysis ◽  
Fault Prediction ◽  
Transformer Oil ◽  
Support Vector ◽  
Dissolved Gas ◽  
Industry Sector ◽  
Incipient Fault

The power transformer is an important link in the power system. Utilities will face a huge loss if a fault occurs transformer. The outage can cause loss to the industry sector. Transformer incipient fault can be predicted using Dissolved Gas Analysis (DGA) based on gas ratios. The current work is an effort to use SVM to predict transformer incipient fault more precisely. DGA data of various transformer oil samples were collected and analyzed to select the best SVM kernel function and kernel factor to be used and to observe the prediction accuracy.

Prediction Research of Transformer Fault Based on Regular Extreme Learning Machine

2014 ◽  
Vol 1049-1050 ◽  
pp. 1205-1209
Author(s):  
Xue Zhen Chen ◽  
Yong Li Zhu ◽  
Fei Pei
Keyword(s):  
Prediction Model ◽  
Extreme Learning Machine ◽  
Fault Prediction ◽  
Transformer Oil ◽  
Risk Minimization ◽  
Prediction Ability ◽  
Generalization Performance ◽  
Minimization Principle ◽  
Learning Machine ◽  
Transformer Fault

To predict the concentration of dissolved gas in transformer oil, and then realize the transformer latent fault prediction, can effectively prevent unnecessary loss caused by the transformer faults .In order to improve the transformer fault prediction ability,this paper proposes a new transformer fault prediction model--Regular Extreme Learning Machine (RELM) prediction model。RELM algorithm introduce structure risk minimization principle on the basis of traditional ELM, using the balance factor to weigh the empirical risk and the risk of structure size, further enhance the generalization performance of ELM. Verified by examples, the proposed prediction model based on the RELM in this paper achieve better generalization performance and prediction accuracy in the forecast of gases concentration dissolved in transformer oil.

Sign in / Sign up

Export Citation Format

Share Document