Accurate interpretation of dissolved gas analysis (DGA) measurements for power transformers is essential to ensure overall power system reliability. Various DGA interpretation techniques have been proposed in the literature, including the Doernenburg Ratio Method (DRM), Roger Ratio Method (RRM), IEC Ratio Method (IRM), Duval Triangle Method (DTM), and Duval Pentagon Method (DPM). While these techniques are well documented and widely used by industry, they may lead to different conclusions for the same oil sample. Additionally, the ratio-based methods may result in an out-of-code condition if any of the used gases fall outside the specified limits. Incorrect interpretation of DGA measurements can lead to mismanagement and may lead to catastrophic consequences for operating power transformers. This paper presents a new interpretation technique for DGA aimed at improving its accuracy and consistency. The proposed multi-method approach employs s scoring index and random forest machine learning principles to integrate existing interpretation methods into one comprehensive technique. The robustness of the proposed method is assessed using DGA data collected from several transformers under various health conditions. Results indicate that the proposed multi-method, based on the scoring index and random forest; offers greater accuracy and consistency than individual conventional interpretation methods alone. Furthermore, the multi-method based on random forest demonstrated higher accuracy than employing the scoring index only.

Power transformer is a critical and expensive asset in electric transmission and distribution networks. It is essential to monitor the health condition of all power transformer fleet in such networks to avoid unwanted outages. The health index (HI) is a quick and efficient way to assess the condition of power transformers based on multi-criteria. While Power transformer HI method has been well presented in the literature, not much attention was given to handle the uncertainty and reliability of this method due to unavailability of used data. Therefore, this paper aims to tackle this issue through employing Artificial Intelligence (AI)-based techniques to reveal the health condition of power transformers with high accuracy and at the same time handling data uncertainty. The proposed HI approach assesses the power transformer insulation system based on oil quality, dissolved gas analysis (DGA), and paper condition. In this regard, collected data from 504, 150-kV transformers are used to establish the proposed AI-models. Seven AI algorithms including k-Nearest Neighbor (kNN), Support Vector Machine (SVM), Random Forest (RF), Naïve Bayes (NB), Artificial Neural Network (ANN), Adaptive Boosting (AdaBoost), and Decision Tree are investigated. A performance comparison of the proposed AI-based HI models is carried out using the scoring-weighting-based HI method as the reference. Results show that RF model provides the best performance in predicting power transformer HI with an accuracy of 97.3%.

This article presents an algorithm for modelling an Adaptive Neuro Fuzzy Inference System (ANFIS) for power transformer paper conditions in order to estimate the transformer’s expected life. The dielectric characteristics, dissolved gasses, and furfural of 108 running transformers were collected, which were divided into 76 training datasets and another 32 testing datasets. The degree of polymerization (DP) of the transformer paper was predicted using the ANFIS model based on using the dielectric characteristics and dissolved gases as input. These inputs were analyzed, and the best combination was selected, whereas CO + CO₂, acidity, interfacial tension, and color were correlated with the paper’s deterioration condition and were chosen as the input variables. The best combination of input variables and membership function was selected to build the optimal ANFIS model, which was then compared and evaluated. The proposed ANFIS model has 89.07% training accuracy and 85.75% testing accuracy and was applied to a transformer paper insulation assessment and an estimation of the expected life of four Indonesian transformers for which furfural data is unavailable. This proposed algorithm can be used as a furfural alternative for the general assessment of transformer paper conditions and the estimation of expected life and provides a helpful assistance for experts in transformer condition assessment.

In determining the severity of power transformer faults, several approaches have been previously proposed; however, most published studies do not accommodate gas level, gas rate, and Dissolved Gas Analysis (DGA) interpretation in a single approach. To increase the reliability of the faults’ severity assessment of power transformers, a novel approach in the form of fuzzy logic has been proposed as a new solution to determine faults’ severity using the combination of gas level, gas rate, and DGA interpretation from the Duval Pentagon Method (DPM). A four-level typical concentration and rate were established based on the local population. To simplify the assessment of hundreds of power transformer data, a Support Vector Machine (SVM)-based DPM with high agreements to the graphical DPM has been developed. The proposed approach has been implemented to 448 power transformers and further implementation was done to evaluate faults’ severity of power transformers from historical DGA data. This new approach yields in high agreement with the previous methods, but with better sensitivity due to the incorporation of gas level, gas rate, and DGA interpretation results in one approach.

Health index has been widely accepted as a powerful tool for monitoring the condition of power transformer insulation system based on various diagnostic parameters. While this approach has been extensively discussed in the literature, not much attention was given to provide effective solutions to the uncertainty in the used data. According to CIGRE 761, data quality issues may arise due to measurement accuracy as well as incompleteness and unavailability of the required data. Therefore, this article presents the implementation and evaluation of a certainty level model for transformer insulation system health index to deal with data uncertainty. The impact of data unavailability on the health index results is also investigated. Certainty level of the health index is determined by the criticality level of available data, and is reported along with the health index result. A method to handle unavailable data by predicting the oil interfacial tension (IFT) using Random Forest approach is also presented. The proposed certainty level model is designed to accommodate the predicted value of missed data into the health index model while considering its prediction accuracy. The robustness of the developed model is validated through its application in assessing the health condition of six in-service power transformers. The results indicate that by including the proposed certainty level and the prediction approach to eliminate the issue of uncertain and missed diagnostic data, an asset management decision can be taken on operating power transformer fleets with high level of confidence.