Transformer failure diagnosis using fuzzy association rule mining combined with case‐based reasoning

Abstract

In the field of transformer failure diagnosis, the potential correlation between different characteristic parameters and failures is difficult to detect using traditional methods. Further, the quantities of inspection data have not been fully utilized. To improve the accuracy of transformer diagnosis, this study establishes a diagnosis model based on fuzzy association rules combined with case-based reasoning (CBR) to evaluate the failure types, fault locations, and cause of breakdown in power transformers. First, the inspection data of transformers are collected from several substations over 10 years. Then, the preprocessed data are randomly separated into training and testing sets. For the training set, fuzzy association rules are built for multiple parameters to narrow the search scope of base case preliminarily. Next, CBR is applied to determine the most similar cases. The failure information of the target transformer can be obtained in detail along with the most similar base case. Finally, the accuracy of the model is validated shown in case studies using the testing data set. The result demonstrates that the diagnosis model provides a higher accuracy than the classic IEC 60599 three-ratio method used in the current industry, which means that this diagnosis model has better performance on diagnosis accuracy.

A Practical Approach for Predicting Power in a Small-Scale Off-Grid Photovoltaic System using Machine Learning Algorithms

“…Method Inference [28] Transformer failure diagnosis using fuzzy association rule mining combined with case based reasoning -Hybrid CBR algorithm is employed to discover the past cases which are the most identical to the present case. The exactness of the model is confirmed using past 10 years data.…”

“…Predicted wattage with only temperature Predicted wattage % Accuracy using proposed LR method % Accuracy using CBR (28) Comparison chart showing % accuracy using CBR and LR 95.00 96.00 97.00 98.00 99.00 100.00 101.00 4 shows the specifications of Arduino Uno. The ratings of the PV panel used are given in Table 5, and Table 6 lists the essential cloud services used.…”

“…The software and hardware style for constructing a wireless datalogger for a thermal authentication system to measure and operate in a stated temperature range and also agreeing with International and European protocols for validation of pharmaceutical, biotechnology, and the medical device is described in [27], where the temperature ranges from -60 °C to 150 °C with total system measurement accuracy of 0.1 °C. CBR algorithm is employed to discover the past cases which are the most identical to the present case in [28]. The exactness of the model is confirmed using past 10 years data.…”

A Hybrid Method for the Fault Diagnosis of Onboard Traction Transformers

“…The traditional fault diagnosis of traction transformers is similar to that of power transformers, which are mainly diagnosed by the DGA method [6]. Examples include the Duval triangle method, the three-ratio method, Rogers' method, and others [7,8]. Although these methods are early research methods in the field of transformer fault diagnosis, they still have many shortcomings, which are that the coding is incomplete, the boundary is too absolute, and the coding is beyond the boundary.…”

Gaussian Process Multi-Class Classification for Transformer Fault Diagnosis Using Dissolved Gas Analysis

“…In [4], the adaptive network-based fuzzy inference system (ANFIS) aggregated with the Dempster-Shafer theory (DT) has been presented to improve fault diagnosis capabilities, based on DGA which helps eliminate the existence of incorrect or unresolved diagnoses. A joint model of fuzzy association rules and case-based reasoning (CBR) was implemented for transformer diagnosis by connecting fault type with characteristic parameters to enhance diagnostic capability [5]. The performance of rulebased fuzzy logic approaches relies on the empirical and cumulative knowledge of human experts, thus, some prevalent AI models extract relative state information from training data directly rather than manual collection, such as artificial neural network (ANN) and support vector machines (SVMs).…”