Transformer Incipient Fault Diagnosis Research Articles

Performance Assessment of IEEE/IEC Method and Duval Triangle technique for Transformer Incipient Fault Diagnosis

Power transformers are among the most important equipment in a power system. The assessment of the transformer’s condition which is connected to a system is needed to avoid disastrous failures and the subsequent power outages. Although transformers are highly dependable and efficient, but are always under the influence of thermal, electrical stresses which are caused due to the deterioration of transformer insulation. Internal faults in a transformer can be classified as incipient faults and internal short circuit faults. The former type of faults develops over an extended period of time and lead to the degradation of insulation. Incipient faults are generally the result of deterioration of the dielectric strength of transformer mineral oil due to hydrolysis, pyrolysis, and oxidation, which result in the formation of gases that are collected in the gap between the oil and tank and partially get dissolved in it. If incipient conditions are not corrected timely, they may finally lead to collapse of the system where such a transformer is installed. Dissolved Gas Analysis (DGA) methods are extensively accepted by utilities for detection of developing faults. In this work, the brief study of two of the prevalent DGA methods for identification of incipient faults has been carried out. The methods that have been studied are IEEE/IEC Ratio Method and Duval’s Triangle Method. The published DGA data where the actual fault is known is used for identification of the incipient faults and the results have been compared.

An integrated method of ANFIS and Dempster-Shafer theory for fault diagnosis of power transformer

Dissolved gas analysis (DGA) approach is extensively applied to detect incipient faults of power transformers. This paper presents a novel DGA method for power transformer incipient fault diagnosis based on integrated adaptive neuro fuzzy inference system (ANFIS) and Dempster-Shafer Theory (DST). Four out of seven common conventional methods which are studied and compared for better consistency and accuracy, are used to develop new ANFIS based fault diagnosis models. To promote fault diagnostic performance further and make fault decision process more reliable and reasonable, an improved DST is introduced to integrate outputs of each ANFIS based model, and to provide comprehensive and convincing fault diagnosis results. The fault diagnosis capability of the proposed method is validated by a reported fault dataset and 10-fold cross validation experiment. The performance of the proposed method is compared with conventional approaches and ANFIS based models which demonstrate that the proposed method is superior to other methods and is more effective and stable for power transformer fault diagnosis with high accuracy and consistency.

Transformer incipient fault diagnosis on the basis of energy-weighted DGA using an artificial neural network

In this paper, a transformer incipient fault diagnosis model has been developed with the help of an artificial neural network (ANN), taking into account the difference in the energy required to produce the different fault gases. The key fault gases are indicative of the fault type prevailing in the transformer. However, in conventional studies, the energy difference in fault gas formation is not considered while adopting the key gas method for fault diagnosis. In this work, a weighting factor has been used to take into account this relative difference in energy requirement for various fault gas formations. The fault gas concentrations have been suitably weighted by their respective weighting factors before being used in the incipient fault diagnosis process. A backpropagation ANN has been appropriately trained using the weighted fault gas concentration for transformer incipient fault identification. The model has been trained to identify fault types as enlisted in the transformer fault-interpreting standard IEC-599. The developed ANN model has been tested for its diagnostic capability using a reported fault database. The comparative diagnosis results presented here show clear improvement in the diagnosis of transformer internal faults using the energy-weighted ANN model over the unweighted ANN model.

Interpretation of DGA for transformer fault diagnosis with complementary SaE-ELM and arctangent transform

This paper presents a novel approach for power transformer incipient fault diagnosis through the analysis of dissolved gas in oil. The proposed approach is implemented for improving the diagnosis accuracy by dissolved gas analysis (DGA) of power transformer based on the combined use of a multi-classification algorithm self-adaptive evolutionary extreme learning machine (SaE-ELM) and a simple arctangent transform (AT). On the one hand, the SaE-ELM algorithm has the ability to approximate any nonlinear functions with its structure parameters, i.e. hidden node biases and output weights, optimized self-sufficiently. On the other hand, the AT can alter the data structure of the experiment data, which will enhance the generalization capability for SaE-ELM as well as other machine learning algorithms. Thus, the combination of SaEELM and AT can complement each other and improve the diagnosis accuracy from the aspect of both algorithm and data structure. The performances of the proposed approach are compared with that derived from ANN, SVM, and ELM methods, respectively. Experimental results with both published and power utility provided data indicate that the developed approach can significantly improve the accuracies for power transformer fault diagnosis.

Function analysis based rule extraction from artificial neural networks for transformer incipient fault diagnosis

Dissolved gas analysis (DGA) has been widely used for fault diagnosis in a transformer. Artificial neural networks (ANN) have high accuracy but are regarded as black boxes that are difficult to interpret. For many problems it is desired to extract knowledge from trained ANN so that the user can gain a better understanding of the solution arrived by the NN. This paper applies a pedagogical approach for rule extraction from function approximating ANN with application to incipient fault diagnosis using the concentrations of the dissolved gases within the transformer oil, as the inputs. The proposed method derives linear equations by approximation the hidden unit activation function and splitting the input space into subregion. For each subregion there is a linear equation. The experiments on real data indicate that the approach used can extract simple and useful rules. Transformer incipient fault diagnosis can be made that matches the actual fault present and at times the predictions better than those of the IEC/IEEE method. The rule sets generated have been successfully checked for accuracy of predictions by applying them to case studies.

A case‐based reasoning approach to power transformer fault diagnosis using dissolved gas analysis data

AbstractA synthetic diagnosis approach based on case‐based reasoning is presented to diagnose incipient fault of power transformer. First, the base case bank is established according to the characteristics of dissolved gas analysis (DGA) of transformer oil. Based on different artificial intelligence techniques, three kinds of case searching method are adopted to retrieve the set of base cases, which the symptom of every retrieved case is similar to that of suspected transformer to some extent. And then a synthetic estimation method is presented to achieve the optimal base case for all retrieved base cases. Since similar symptoms may be induced by the same kind of faults, the diagnosis conclusion of suspected transformer could be drawn by the similar degree comparison between the optimal case and the suspected transformer. The application results show that the method has higher reliability and is more practical for the transformer incipient fault diagnosis. Copyright © 2008 John Wiley & Sons, Ltd.

Extension neural network for power transformer incipient fault diagnosis

An extension neural network (ENN)-based diagnosis system for power transformer incipient fault detection is presented. The ENN proposed is a combination of extension theory and a neural network. Using an innovative extension distance instead of Euclidean distance (ED) to measure the similarity between tested data and the cluster centre, it can effect supervised learning and achieve shorter learning times than traditional neural networks. Moreover, the ENN has the advantage of height accuracy and error tolerance. Thus, the incipient faults of power transformers can be diagnosed quickly and accurately. To demonstrate the effectiveness of the proposed method, 40 sets of field DGA data from power transformers in Australia, China, and Taiwan have been tested. The test results confirm that the proposed method has given promising results.

Neural net and expert system diagnose transformer faults

Dissolved gas-in-oil analysis (DGA) is a common practice in transformer incipient fault diagnosis. The analysis techniques include the conventional key gas method, ratio methods, and artificial intelligence methods. Application of artificial intelligence (Al) techniques have shown very promising results. The methods include fuzzy logic, expert systems (EPS), evolutionary algorithms (EA), and artificial neural networks (ANN). A transformer incipient fault diagnosis system (ANNEPS) was developed over a period of 5 years at Virginia Tech, collaborating with Doble Engineering Company. The system can detect thermal faults (distinguishing overheating of oil from that of cellulose and between four overheating stages and overheating of oil), low-energy discharge (partial discharge), high-energy discharge (arcing), and cellulose degradation.