Abstract
Frequency response analysis is a powerful tool for mechanical fault diagnostics in power transformers. However, interpretation schemes still today depend on expert analyses, mainly because of the complex structure of power transformers. One of the fundamental shortcomings of experimental investigations is that mechanical deformations cannot be managed on real transformers to obtain data for different scenarios because they are too destructive. To address this issue in a systematic way, the current research used a specially designed laboratory transformer model that allows mechanical defects to be introduced so its frequency response can be evaluated under different conditions. The key feature of this model is the non-destructive interchangeability of its winding sections, allowing reproducibility and repeatability of frequency response measurements. Numerical indices were compared over key performance indicators (linearity, sensitivity and monotonicity). The analysis indicated that comparative standard deviation offered promising results for evaluation of mechanical deformations on the laboratory winding model given its monotonic behaviour, sensitivity and linear increase with fault severity. Additionally, support vector machine learning, radial basis function neural network and the statistical k-nearest neighbour method were used for fault classification with different strategies and configurations. While limited data from different transformers are used in the available literature, the approach discussed here considers 371 measurements from the same transformer model. The test results are supportive and demonstrate great accuracy when machine learning is used for winding fault classification.
Highlights
Power transformers are essential assets of electrical power networks, and monitoring their operating condition is crucial for functional and economic reasons
Frequency response at a frequency range affected in fault mode: from 400 kHz to 700 kHz for (a) axial displacement, (b) radial deformation, (c) disc space variation and (d) shorted turns; and from 20 kHz to 50 kHz for (e) shorted turns
RECOGNITION PERFORMANCE AND DISCUSSION Three machine learning classifiers were investigated in an effort to obtain a more objective interpretation for fault diagnostics in a winding model: radial basis function (RBF), support vector machine (SVM) and k-nearest neighbour
Summary
Power transformers are essential assets of electrical power networks, and monitoring their operating condition is crucial for functional and economic reasons. FRA compares current and reference frequency response measurements of a power transformer. This paper explores different measurements taken on a laboratory transformer model to study FRA interpretation. Studies investigating FRA interpretation use numerical indices [10, 11], white-box modeling [12, 13] and artificial intelligence algorithms [14,15,16,17] to objectively assess frequency response traces obtained from real cases [8, 18], laboratory experiments [19] and simulation studies [20,21,22]. The frequency bands of interest and the best-performing numerical index were subsequently used as machine-learning input to achieve an objective interpretation of fault modes in FRA measurements. Since the faults were introduced on winding 1, the open-circuit measurement taken from winding 1 was used in this research to compare faulty and healthy states
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
