Oil quality index model verification and validation using total acid number and interfacial tension experimental data

Transformers are indispensable components in any power network, facilitating the delivery of generated electricity to consumers at the most secure voltage level. The insulation system of oil-filled transformers is critical for the safe operation of power transformers, although it undergoes consistent degradation over time. Similar to blood in a human body, the insulating fluid serves as a condition monitoring medium. Most traditional oil aging detection methodologies operate offline; thus, they are most suitable for planned maintenance activities. These methods, however, have their drawbacks, including potential safety risks, contamination of samples, loss of productive hours, and the potential risk of overlooking early signs of aging that could occur beyond the maintenance cycle window. The Myers oil quality index (OQIN) number, derived from the quotient of interfacial tension (IFT) and total acid number (TAN) values, provides a tool for classifying transformer oil into seven distinct categories, expanding the potential for both offline and online oil applications. In this work, eighteen 750 mL samples of natural ester oil (NEO) are procured, aged, and analyzed using offline TAN and IFT techniques, and their respective values (IFT, TAN, and OQIN) are recorded. These experimental datasets are employed to verify and validate (V&V) an OQIN machine learning model. The model is further validated using existing mineral oil (MIN) datasets. The high-performance metrics, demonstrated in terms of accuracy, precision, sensitivity, specificity, and F-Score, confirm the effectiveness of the model for online transformer oil aging detection and classification. The bagged tree ensemble model shows the best performance for OQIN, NEO, and MIN, respectively, in terms of accuracy (100%, 83.30%, 100%), precision (100%, 90%, 100%), sensitivity (100%, 88%, 100%), specificity (100%, 96%, 100%), and F-Score (100%, 84.76%, 100%). This development proposes the potential for a shift from traditional offline scheduled maintenance aging detection methods to an online/Internet of Things (IoT)-based prescriptive aging detection, thereby enhancing the reliability of transformer performance in situ.