Insulation cellulose paper is a basic measure for a power transformer’s remaining useful life, and its advantageous low cost, electrical, and mechanical properties have made it an extensive insulation system when impregnated in a dielectric liquid. Cellulose paper deteriorates as a result of ageing due to some chemical reactions like pyrolysis (heat), hydrolysis (moisture), and oxidation (oxygen) that affects its degree of polymerization. The condition analysis of cellulose paper has been a major concern since the collection of paper samples from an operational power transformer is almost impossible. However, some chemicals generated during cellulose paper deterioration, which were dissolved in dielectric liquid, have been used alternatively for this purpose as they show a direct correlation with the paper’s degree of polymerization. Furthermore, online and non-destructive measurement of the degree of polymerization by optical sensors has been proposed recently but is yet to be available in the market and is yet generally acceptable. In mitigating the magnitude of paper deterioration, some ageing assessments have been proposed. Furthermore, researchers have successfully enhanced the insulating performance of oil-impregnated insulation paper by the addition of various types of nanoparticles. This study reviews the ageing assessment of oil-paper composite insulation and the effect of nanoparticles on tensile strength and electrical properties of oil-impregnated paper insulation. It includes not only significant tutorial elements but also some analyses, which open the door for further research on the topic.

In the era of Industry 4.0, digital transformation has spurred the swift advancement of technologies, including intelligent predictive maintenance scheduling, prognostics and health management. The accurate prediction of remaining useful life plays a crucial role in these technologies as it extends power equipment’s safe operational duration and decreases the maintenance costs associated with unforeseen shutdowns. Also, the increased accessibility of data for monitoring system conditions has paved the way for the more immense adoption of machine learning models in prognostics and health management for power transformers. At the moment, with the ever-increasing demand for electricity, there is a corresponding increase in the degradation processes of power transformers. Transformers insulation system and more importantly, the paper insulation happens to be the principal part where the degradation is prominent. Therefore, an accurate prediction of the insulating paper condition through its degree of polymerization is required to guarantee the reliability of power transformers. In this regard, the predictions, reliability, and health monitoring of this power equipment can be actualized by modeling the degradation of transformer insulation paper through several machine learning frameworks. In this view, this review paper has been drafted not only to serve as a guide for researchers interested in the fields of transformer insulation system fault prognosis but also to offer insights into potential research directions as existing literature in modeling and evaluating transformer paper insulation is presented.

The ageing of cellulose paper-based transformer insulation is a critical factor influencing the reliability and lifespan of power transformers, as insulating paper is not easily replaced or repaired. Therefore, this review explores the degradation mechanisms of insulating paper, emphasising the roles of dissolved gases, chemical markers, and macromolecular characterisation in assessing paper deterioration. Likewise, the impact of moisture and thermal stress on the breakdown of cellulose fibres are discussed, especially acid hydrolysis, which serves as the main degradation mechanism in cellulose insulating paper. Advanced diagnostic techniques for insulation condition monitoring, such as molecular simulations, glass transition temperature analysis, and DP estimation models, are highlighted. Furthermore, special attention is given to natural esters as alternative insulating liquids, demonstrating their ability to slow cellulose ageing through moisture absorption, hydrogen bonding stabilisation, and transesterification reactions. This paper also evaluates key chemical markers, including 2FAL and methanol, for estimating paper degradation. A comprehensive understanding of these mechanisms and diagnostic approaches can enhance predictive maintenance strategies and improve transformer longevity.

Dissolved gas analysis remains the most widely utilized non-intrusive diagnostic method for detecting incipient faults in insulating liquid-immersed transformers. Despite their prevalence, conventional ratio-based methods often suffer from ambiguity and limited potential for automation applicrations. To address these limitations, this study proposes a unified multiclass classification model that integrates traditional gas ratio features with supervised machine learning algorithms to enhance fault diagnosis accuracy. The performance of six machine learning classifiers was systematically evaluated using training and testing data generated through four widely recognized gas ratio schemes. Grid search optimization was employed to fine-tune the hyperparameters of each model, while model evaluation was conducted using 10-fold cross-validation and six performance metrics. Across all the diagnostic approaches, ensemble models, namely random forest, XGBoost, and LightGBM, consistently outperformed non-ensemble models. Notably, random forest and LightGBM classifiers demonstrated the most robust and superior performance across all schemes, achieving accuracy, precision, recall, and F1 scores between 0.99 and 1, along with Matthew correlation coefficient values exceeding 0.98 in all cases. This robustness suggests that ensemble models are effective at capturing complex decision boundaries and relationships among gas ratio features. Furthermore, beyond numerical classification, the integration of physicochemical and dielectric properties in this study revealed degradation signatures that strongly correlate with thermal fault indicators. Particularly, the CIGRÉ-based classification using a random forest classifier demonstrated high sensitivity in detecting thermally stressed units, corroborating trends observed in chemical deterioration parameters such as interfacial tension and CO₂/CO ratios. Access to over 80 years of operational data provides a rare and invaluable perspective on the long-term performance and degradation of power equipment. This extended dataset enables a more accurate assessment of ageing trends, enhances the reliability of predictive maintenance models, and supports informed decision-making for asset management in legacy power systems.