Moisture is one of the critical factors to determine the service life of transformers. The moisture inside the transformer oil-immersed insulation could be quantified with feature parameters. This paper proposes and develops a Genetic Algorithm Support Vector Machine (GA-SVM) model to carry out the moisture diagnosis. Present findings reveal that these feature parameters can be obtained by using frequency domain spectroscopy. Therefore, a novel model for predicting frequency domain spectroscopy curves is firstly reported based on a small number of samples, which could be utilized to obtain the feature parameters database to develop GA-SVM. Then, the moisture diagnosis in lab and field conditions is presented to verify its feasibility and accuracy. The novelty of this work is in an exploration of the reported model, as an intelligent based moisture diagnosis tool for power transformers.

The dielectric modulus Μ∗(ω) is used for studying the frequency domain response and activation energy (E a ) of transformer immersed cellulose insulation. Existing literatures show that the temperature is a crucial factor affecting the Μ∗(ω) and aging rate of transformer oil-paper insulation, while the E a can be regarded as an indicator to reflect the average aging rate of the transformer immersed cellulose insulation. Therefore, the discussion of the temperature-dependence on both Μ∗(ω) and E a is of great significance. This paper attempts to report an approach for understanding the temperature impact on both Μ∗(ω) and E a . The obtained knowledge can be used to establish two available models for temperature correction on Μ∗(ω) and activation energy prediction of transform immersed cellulose insulation, respectively. These findings are expected to promote the reliability of the condition prediction result of transformer immersed cellulose insulation by using Μ∗(ω) and E a technique.

Moisture accumulates with the growing aging progress of oil-paper insulation and further shortens the remaining life of the transformer. The frequency-domain spectroscopy (FDS) technique can be used to realize the moisture estimation. However, the moisture estimation results would be unreliable once the aging effect on FDS was ignored. Given this issue, an alternative model including the aging effect is thus proposed using FDS and intelligent algorithm. In this work, the feature parameters of FDS data are used to build the databases for characterizing the aging degree and moisture. Then, the moisture estimation models are developed using the weighted K-nearest neighbor (K-NN) algorithm. The accuracy and applicability of the proposed models are finally discussed in laboratory and field conditions. In that respect, the findings reveal that the reported model is available for moisture estimation of transformer oil-paper insulation under various aging degrees and test temperatures.

The results of frequency domain spectroscopy (FDS) will be affected by moisture which often leads to an unreliable condition prediction of oil-immersed cellulose insulation in transformers. In view of this, a solution is proposed in this study by adopting a fitting fingerprint database (FFD) technique, which can be utilized for condition prediction of aging and moisture content. In the current work, the relevant fingerprints that could characterize the insulation aging condition and moisture content are extracted from the FDS curves and the DC conductivity of the transformer oil. The FFD is then constructed by fitting fingerprints. The accuracy of the reported FFD technique is verified from tests on oil-immersed pressboard prepared in the lab and a transformer from the field. In this respect, the present contribution highlights FFD might be used as a powerful tool for condition prediction of oil-immersed cellulose insulation in transformers.