R. Behkam; A. Moradzadeh; H. Karami; M.S. Nadery; B. Mohammadi ivatloo; G.B. Gharehpetian; S. Tenbohlen
Abstract
The Frequency Response Analysis (FRA) technique has advantages in identifying faults related to power transformers, but it suffers from the interpretation of frequency responses. This paper presents an approach based on statistical indices and Artificial Neural Network (ANN) methods to interpret frequency ...
Read More
The Frequency Response Analysis (FRA) technique has advantages in identifying faults related to power transformers, but it suffers from the interpretation of frequency responses. This paper presents an approach based on statistical indices and Artificial Neural Network (ANN) methods to interpret frequency responses. The proposed procedure divides frequency responses into four frequency regions based on frequency resonances and anti-resonances. Then, Lin’s Concordance Coefficient (LCC) index is used as one of the most appropriate numerical indices to extract features of the four frequency regions. Finally, the Multilayer Perceptron (MLP) neural network is trained by the extracted features to identify and differentiate the types of winding faults. Besides, other intelligent algorithms such as Support Vector Machine (SVM), Extreme Learning Machine (ELM), Probabilistic Neural Network (PNN), and Radial Basis Function (RBF) neural network have been employed to compare the classification results. The proposed techniques have been practically implemented. The Axial Displacement (AD) and Disk Space Variation (DSV) faults are applied as two common mechanical faults in different locations and intensities on the 20kV windings of a 1.6MVA distribution power transformer and their corresponding frequency responses are calculated. Frequency responses calculated from the AD and DSV faults constitute the MLP input data set. The network is trained with part of the input data, and the rest of the data is allocated to validate and test the network. The results show that the suggested method has more proper performance than others using the phase component of the frequency responses in interpreting frequency responses and separation and identifying various mechanical fault types of transformer windings.
Transformers
V. Behjat; A. Shams; V. Tamjidi
Abstract
Electromagnetic forces in power transformer windings are produced by interaction between the leakage fluxes and current passing them. Since the leakage flux distribution along the windings height is in two axial and radial directions, so the electromagnetic forces have two components, radial and axial. ...
Read More
Electromagnetic forces in power transformer windings are produced by interaction between the leakage fluxes and current passing them. Since the leakage flux distribution along the windings height is in two axial and radial directions, so the electromagnetic forces have two components, radial and axial. There is a risk that a large electromagnetic force due to the short circuit or inrush currents, can cause the windings to be deform, rupture, and/or displace, if the transformer and winding holders structure is not designed or assembled properly. Also, these mechanical changes can damage insulation between two or more adjacent turns of a winding and so, produce the local inter-turn fault. Occurrence of any fault in windings will change the electromagnetic force distribution in transformers and will cause developing secondary faults. Hence, this contribution is aimed at characterizing the electromagnetic forces behavior in power transformers and determines the changes of force values after occurring winding mechanical and inter-turn. The study keeps at disposal a two-winding, three phase, 8 MVA power transformer, on their windings faults are imposed and investigated through the FEM analysis. The accuracy of the created FEM model is firstly validated using analytical methods for transformer healthy condition, and then the winding shorted turn fault along with the mechanical faults are considered using 3D FEM model. The extracted characteristic signatures attained to different type of winding faults is expected to be useful at the design stage of power transformers.