Abstract
Dissolved gas analysis (DGA) is one of the most important methods to analyze fault in power transformers. In general, DGA is applied in monitoring systems based upon an autoregressive model; the current value of a time series is regressed on past values of the same series, as well as present and past values of some exogenous variables. The main difficulty is to decide the order of the autoregressive model; this means determining the number of past values to be used. This study proposes a wavelet-like transform to optimize the order of the variables in a nonlinear autoregressive neural network to predict the in oil dissolved gas concentration (DGC) from sensor data. Daubechies wavelets of different lengths are used to create representations with different time delays of ten DGC, which are then subjected to a procedure based on principal components analysis (PCA) and Pearson’s correlation to find out the order of an autoregressive model. The representations with optimal time delays for each DGC are applied as input in a multi-layer perceptron (MLP) network with backpropagation algorithm to predict the gas at the present and future times. This approach produces better results than choosing the same time delay for all inputs, as usual. The forecasts reached an average mean absolute percentage error (MAPE) of 5.763%, 1.525%, 1.831%, 2.869%, and 5.069% for C2H2, C2H6, C2H4, CH4, and H2, respectively.
Highlights
The transformer is one of the most important devices in the electricity distribution process, and reliable power distribution depends largely on the failure-free operation of this equipment.The failure of the transformer during operation can bring a significant loss of revenue to the utility, possible environmental damage, explosion and fire risks, and expensive costs of repair or replacement [1,2]
Development of an approach based on a wavelet-like transform that determines the optimal delay for each external variable and for the output variable in an autoregressive prediction model; A prediction model with high precision as it focuses on the trend of the input signals from the noise-free approximations calculated by the wavelet transform; Expansion of knowledge of the temporal relationship between gases underlying degradation process of the insulating oil and solid insulating material; Reduction of the number of input variables in the autoregression model when using the approximations resulting from transformations with wavelets of different lengths, which already consider the time delay determined for each variable
This work presented an approach based on the wavelet transform to determine the ideal time delay for each gas concentration and use it as a regression model in an multi-layer perceptron (MLP) network
Summary
The transformer is one of the most important devices in the electricity distribution process, and reliable power distribution depends largely on the failure-free operation of this equipment.The failure of the transformer during operation can bring a significant loss of revenue to the utility, possible environmental damage, explosion and fire risks, and expensive costs of repair or replacement [1,2]. The transformer is one of the most important devices in the electricity distribution process, and reliable power distribution depends largely on the failure-free operation of this equipment. The analysis of the condition and maintenance of the transformer are extremely important to ensure stable reliability of electricity [1,3,4,5]. On condition of internal transformer failure occurring, the emergence speed of these gases is accelerated [6]. One of the most important tools for power transformer condition monitoring and internal fault diagnosis is the transformer oil gas chromatography test, known as dissolved gas analysis (DGA) [7,8,9,10]
Sign-in/Register to view highlights & summary 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.
