Transformer Health Monitoring Using Dissolved Gas Analysis

Abstract

As integral components of any power plant, transformers sup-ply the generated electricity to the grid. However, the trans-former’s cellulose-based paper insulation and the mineral oilin which it is immersed break down over time under stan-dard operating conditions—or more rapidly due to potentialfaults within the system. This technical brief exhibits a col-lection of diagnostic and prognostic techniques that utilitiescan adopted in lieu of labor-intense periodic preventive main-tenance routines. Furthermore, prognostic models have beenincorporated using the latest version of the Institute of Elec-trical and Electronics Engineers (IEEE) standard (IEEE StdC57.104TM-2019) for dissolved gas analysis (DGA), thusexpanding it to include estimation of the time to maintenance.Overall, four different methodologies are explained, each ofwhich aid in determining a transformer’s state of health. Thesemethodologies include the Chendong model, the IEEE C57.91-2011 thermal life consumption model, a diagnostic model forDGA, and a prognostic model for DGA that uses an autore-gressive integrated moving average (ARIMA) model. An ad-ditional improvement for estimating missing system parame-ters from monitoring data (i.e., a tool for parameter estimationutilizing Powell’s method) is presented, enabling the IEEEthermal life consumption model to benefit not only the col-laborating power plant, but also the power industry at large.

Determining the Remaining Functional Life of Power Transformers Using Multiple Methods of Diagnosing the Operating Condition Based on SVM Classification Algorithms

“…To determine and monitor transformer condition, many users rely solely on dissolved gas analysis [17], so a number of standards have been reviewed [18,19] and diagnostic methods using artificial intelligence-based programmes have been developed [20,21].…”