Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jan 3;14(1):376.
doi: 10.1038/s41598-023-50833-7.

Discernment of transformer oil stray gassing anomalies using machine learning classification techniques

M K Ngwenyama #  1 , M N Gitau #  2
Affiliations

Discernment of transformer oil stray gassing anomalies using machine learning classification techniques

M K Ngwenyama et al. Sci Rep. .

Abstract

This work examines the application of machine learning (ML) algorithms to evaluate dissolved gas analysis (DGA) data to quickly identify incipient faults in oil-immersed transformers (OITs). Transformers are pivotal equipment in the transmission and distribution of electrical power. The failure of a particular unit during service may interrupt a massive number of consumers and disrupt commercial activities in that area. Therefore, several monitoring techniques are proposed to ensure that the unit maintains an adequate level of functionality in addition to an extended useful lifespan. DGA is a technique commonly employed for monitoring the state of OITs. The understanding of DGA samples is conversely unsatisfactory from the perspective of evaluating incipient faults and relies mainly on the proficiency of test engineers. In the current work, a multi-classification model that is centered on ML algorithms is demonstrated to have a logical, precise, and perfect understanding of DGA. The proposed model is used to analyze 138 transformer oil (TO) samples that exhibited different stray gassing characteristics in various South African substations. The proposed model combines the design of four ML classifiers and enhances diagnosis accuracy and trust between the transformer manufacturer and power utility. Furthermore, case reports on transformer failure analysis using the proposed model, IEC 60599:2022, and Eskom (Specification-Ref: 240-75661431) standards are presented. In addition, a comparison analysis is conducted in this work against the conventional DGA approaches to validate the proposed model. The proposed model demonstrates the highest degree of accuracy of 87.7%, which was produced by Bagged Trees, followed by Fine KNN with 86.2%, and the third in rank is Quadratic SVM with 84.1%.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Example of DT.
Figure 2
Figure 2
Example of SVM.
Figure 3
Figure 3
Example of KNN.
Figure 4
Figure 4
Example of EC.
Figure 5
Figure 5
Extraction of transformer oil for DGA.
Figure 6
Figure 6
Dataset of potential faults.
Figure 7
Figure 7
Catastrophe statistics of distinct transformer parts reported by CIGRE.
Figure 8
Figure 8
The logarithmic nomograph.
Figure 9
Figure 9
Coordinates and zones of Duval triangle transformer fault diagnosis.
Figure 10
Figure 10
Research flowchart for MC model.
Figure 11
Figure 11
Function block diagram on the proposed model.
Figure 12
Figure 12
ML workflow.
Figure 13
Figure 13
TO evaluation phases.
Figure 14
Figure 14
Analyzed databank using DT classifier.
Figure 15
Figure 15
Analyzed databank using SVM classifier.
Figure 16
Figure 16
Analyzed databank using KNN classifier.
Figure 17
Figure 17
Analyzed databank using EC classifier.
Figure 18
Figure 18
Principal analysis component (PCA) principle.
See this image and copyright information in PMC

References

    1. Poonnoy N, Suwanasri C, Suwanasri T. Neural network approach to dissolved gas analysis for fault analysis in power transformers. In: Poonnoy N, Suwanasri C, Suwan T, editors. 2022 International Electrical Engineering Congress (iEECON) IEEE; 2022. pp. 1–4.
    1. Jia J, Tao F, Zhang G, Shao J, Zhang X, Wang B. Validity evaluation of transformer DGA online monitoring data in grid edge systems. IEEE Access. 2020;8:60759–60768. doi: 10.1109/ACCESS.2020.2982674. - DOI
    1. Wang L, Littler T, Liu X. Gaussian process multi-class classification for transformer fault diagnosis using dissolved gas analysis. IEEE Trans. Dielectr. Electr. Insul. 2021;28(5):1703–1712. doi: 10.1109/TDEI.2021.009470. - DOI
    1. Gouda OE, El-Hoshy SH, Ghoneim SS. Enhancing the diagnostic accuracy of DGA techniques based on IEC-TC10 and related databases. IEEE Access. 2021;9:118031–118041. doi: 10.1109/ACCESS.2021.3107332. - DOI
    1. Cui H, et al. Impact of load ramping on power transformer dissolved gas analysis. IEEE Access. 2019;7:170343–170351. doi: 10.1109/ACCESS.2019.2926435. - DOI