Chromatographic Peaks of Dissolved Gases in Transformer Oil Identification by Random Forest

2021 ◽  
pp. 60-67
Author(s):  
Hao-Min Chen ◽  
Cheng-Kuo Chang ◽  
Jeng-Shyang Pan ◽  
Jie Shan ◽  
Zhi-Jun Li
Keyword(s):  
Random Forest ◽  
Transformer Oil ◽  
Dissolved Gases ◽  
Chromatographic Peaks

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.

On the effect of the periodicity of diagnostic measurements on improving the reliability of high-voltage transformers

2019 ◽  
Vol 12 (1) ◽  
pp. 18-21
Author(s):  
V. A. Tikhonov
Keyword(s):  
Service Life ◽  
High Voltage ◽  
Chromatographic Analysis ◽  
Aluminum Industry ◽  
Early Stage ◽  
Diagnostic Methods ◽  
Transformer Oil ◽  
Operating Voltage ◽  
Dissolved Gases ◽  
The Aluminum Industry

The influence of the periodicity of diagnostic measurements on the operational state of high-voltage transformers is considered. Examples of defects of switching devices of converter transformers and methods for their detection are given. The rationale for the importance of recognition of defects at an early stage of their occurrence is given. The influence of the multiplicity of overvoltages on the service life of converter transformers in the aluminum industry is investigated. Based on the analysis of the service life of converter transformers of one of the powerful aluminum plants, where 83% of converter transformers have exhausted their standard service life, it is shown that in 40% of cases it would be possible to avoid their failures, with timely detection and elimination of emerging defects. Examples of defects of OLR (on-load regulators) of converter transformers and methods for their detection are given. The importance of recognition of defects at an early stage of their occurrence is substantiated. A method for chromatographic analysis of dissolved gases in transformer oil has been developed for the qualitative determination of defects and ways to eliminate them. Examples of diagnostics of converter transformers at operating voltage and working load are given, providing the best quality operational characteristics of converter transformers. The periodicity of diagnostic measurements and the reduction of defects and failures has been substantiated. The question of diagnosing the state of the converter transformer TDNP-40000/10 at an enterprise of the aluminum industry is investigated. Currently, diagnostic methods are being developed based on chromatographic analysis of dissolved gases in transformer oil. The presented method of evaluating the operating parameters of transformers allows for the safe operation of high-voltage transformers and enables to increase the reliability of the power supply scheme of aluminum industry plants.

scholarly journals Transformer Oil Quality Assessment Using Random Forest with Feature Engineering

Energies ◽  
2021 ◽  
Vol 14 (7) ◽  
pp. 1809
Author(s):  
Mohammed El Amine Senoussaoui ◽  
Mostefa Brahami ◽  
Issouf Fofana
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Oil Quality ◽  
Principal Component ◽  
Condition Assessment ◽  
Classification Performance ◽  
Transformer Oil ◽  
Classification Model ◽  
Insulation Degradation ◽  
Transformer Oils

Machine learning is widely used as a panacea in many engineering applications including the condition assessment of power transformers. Most statistics attribute the main cause of transformer failure to insulation degradation. Thus, a new, simple, and effective machine-learning approach was proposed to monitor the condition of transformer oils based on some aging indicators. The proposed approach was used to compare the performance of two machine-learning classifiers: J48 decision tree and random forest. The service-aged transformer oils were classified into four groups: the oils that can be maintained in service, the oils that should be reconditioned or filtered, the oils that should be reclaimed, and the oils that must be discarded. From the two algorithms, random forest exhibited a better performance and high accuracy with only a small amount of data. Good performance was achieved through not only the application of the proposed algorithm but also the approach of data preprocessing. Before feeding the classification model, the available data were transformed using the simple k-means method. Subsequently, the obtained data were filtered through correlation-based feature selection (CFsSubset). The resulting features were again retransformed by conducting the principal component analysis and were passed through the CFsSubset filter. The transformation and filtration of the data improved the classification performance of the adopted algorithms, especially random forest. Another advantage of the proposed method is the decrease in the number of the datasets required for the condition assessment of transformer oils, which is valuable for transformer condition monitoring.

Oil health index calculation and incipient fault diagnosis in power transformers using fuzzy logic

2022 ◽  
Vol 64 (1) ◽  
pp. 28-37
Author(s):  
T Manoj ◽  
C Ranga
Keyword(s):  
Fuzzy Logic ◽  
Logic Model ◽  
Transformer Oil ◽  
Power Transformers ◽  
Dissolved Gases ◽  
Health Index ◽  
Fuzzy Logic Model ◽  
Proposed Model ◽  
Incipient Faults ◽  
Incipient Fault

In this paper, a new fuzzy logic (FL) model is proposed for assessing the health status of power transformers. In addition, the detection of incipient faults is achieved where two or more faults exist simultaneously. The process is carried out by integrating a fuzzy logic model with the conventional International Electric Committee (IEC) ratio codes method. As transformer oil insulation deteriorates, excess percentages of dissolved gases such as hydrogen, methane, ethane, acetylene and ethylene are induced within the trasnformer. The status of oil health is generally assessed using these gas concentrations. Therefore, in the proposed model, 31 fuzzy rules are designed based on the severity levels of these gases in order to determine the health index (HI) of the oil. Similarly, any incipient faults along with their severity are also detected using the proposed fuzzy logic model with 22 expert rules. To validate the proposed fuzzy logic model, the data for dissolved gases in 50 working transformers operated by the Himachal Pradesh State Electricity Board (HPSEB), India, are collected. Over the years, calculations for the health index have been performed using conventional dissolved gas analysis (DGA) interpretation methods. The shortcomings of these methods, such as non-reliability and inaccuracy, are successfully overcome using the proposed model. The detection of incipient faults is normally performed using key gas, Rogers ratios, the Duval triangle, Dornenburg ratios, modified Rogers ratios and the IEC ratio codes methods. The shortcomings of these conventional ratio code methods in identifying incipient faults in some typical cases, ie multiple incipient fault cases, are overcome by the proposed fuzzy logic model.

Application of Polycrystalline SnO2 Sensor Chromatographic System to Detect Dissolved Gases in Transformer Oil

2018 ◽  
Vol 267 ◽  
pp. 636-646 ◽  
Author(s):  
Jingmin Fan ◽  
Feng Wang ◽  
Qiuqin Sun ◽  
Huisheng Ye ◽  
Qinji Jiang
Keyword(s):  
Transformer Oil ◽  
Dissolved Gases ◽  
Chromatographic System

Automatic Field Monitoring of Dissolved Gases in Transformer Oil

1981 ◽  
Vol PAS-100 (4) ◽  
pp. 1538-1544 ◽  
Author(s):  
M. Yamada ◽  
Y. Nomura ◽  
Y. Katayama ◽  
T. Ishii ◽  
O. Imamura ◽  
...  
Keyword(s):  
Field Monitoring ◽  
Transformer Oil ◽  
Dissolved Gases

scholarly journals Interpreting dissolved gases in transformer oil: A new method based on the analysis of labelled fault data

2021 ◽  
Author(s):  
Arnaud Nanfak ◽  
Samuel Eke ◽  
Charles Hubert Kom ◽  
Ruben Mouangue ◽  
Issouf Fofana
Keyword(s):  
Transformer Oil ◽  
New Method ◽  
Dissolved Gases

Gas sensing mechanism of dissolved gases in transformer oil on Ag–MoS2 monolayer: A DFT study

2020 ◽  
Vol 118 ◽  
pp. 113947 ◽  
Author(s):  
Jingxuan Wang ◽  
Qu Zhou ◽  
Lingna Xu ◽  
Xin Gao ◽  
Wen Zeng
Keyword(s):  
Gas Sensing ◽  
Transformer Oil ◽  
Dft Study ◽  
Dissolved Gases ◽  
Sensing Mechanism ◽  
Mos2 Monolayer
Sign in / Sign up

Export Citation Format

Share Document