Diagnosis of DC Bias in Power Transformers Using Vibration Feature Extraction and a Pattern Recognition Method

Abstract

DC bias is a great threat to the safe operation of power transformers. This paper deals with a new vibration-based technique to diagnose DC bias in power transformers. With this technique, the DC bias status of power transformers can be automatically recognized. The vibration variation process of a 500 kV autotransformer is tested under the influence of DC bias in the monopole trail operation stage of a ±800 kV HVDC transmission system. Comparison of transformer vibration under normal and DC-biased conditions is conducted. Three features are proposed and are validated by sensitivity analysis. The principal component analysis method is employed for feature de-correlation and dimensionality reduction. The least square support vector machine algorithm is used and verified successful in DC bias recognition. A remote on-line monitoring device based on the proposed algorithm is designed and applied in field DC bias diagnosis of power transformers. The suggested diagnostic algorithm and monitoring device could be useful in targeted DC bias control and improving the safe operation level of power transformers.

Fractal dimension and data mining for detection of short-circuited turns in transformers from vibration signals

“…This limitation, depending on the available data, can compromise the results. As an alternative to the FT approaches, the wavelet theory (WT)-based analysis has been also presented [17][18][19][20]. Although the WT presents several advantages over the FT, special attention has to be given to the selection of both the decomposition level and the mother wavelet since the results depend on these two parameters.…”

“…In fact, these works use different mother wavelets, e.g. quadratic spline [17], biorthogonal [18], and Daubechies [19], even an optimization procedure for the selection of both the decomposition level and the mother wavelet for a specific application is presented in [20]. In order to improve the results of the wavelet packet transform, this technique is combined with the Hilbert-Huang transform [21], which is an adaptive technique based on the empirical mode decomposition (EMD) method.…”

State Identification of Transformer Under DC Bias Based on Wavelet Singular Entropy

“…In terms of DC bias identification, characteristic parameters such as odd to even harmonic ratio, spectrum complexity, and wavelet packet energy are proposed in [16]. And then the principal component analysis (PCA) and support vector machine (SVM) method are used to identify the DC bias of transformers.…”

Active Vibration Distribution through Restricted Topology and Single Node Control

“…Distribution of vibration over structural systems has been prominent in many engineering problems. In vehicles, vibration propagation is closely monitored for driving safety and passenger comfort [1]; in gas turbine and aerospace applications, vibration distribution properties are utilized for engine/aircraft health management with improved operational decision-making [2,3]; in power systems, transformer tank vibration is used to detect DC bias [4] and winding deformations [5]. Since vibration distribution reveals the properties of the underlying structures, it has aroused theoretical interests for feature detection and extraction.…”