Autors: Ivanov G., Mateev, V. M., Marinova, I. I. Title: A Cascaded Neural Network Framework for Estimating Degree of Polymerization of Insulated Paper and DGA Analysis in Power Transformers Keywords: 2-Furaldehyde, Degree of polymerization, DGA, fault diagnosis, insulation aging, neural networks, power transformers, predictive maintenanceAbstract: This paper presents a cascaded artificial neural network (ANN) framework designed to improve the estimation of insulation paper evaluation by estimation of degree of polymerization (DP) based on Furaldehyde (2-FAL) concentration data and diagnosing transformer faults through Dissolved Gas Analysis (DGA). The framework contains three specialized ANNs: a model for DP estimation from 2-FAL measurements data, a fault classifier based on DGA results, and a validator correlating predicted DP. A data set of 80 power transformers was used to train and test created ANNs. Integrating 2-FAL and DGA data within a cascaded ANNs architecture framework provides a foundation for developing predictive, data-driven maintenance strategies for improved transformer reliability. References - Thango, B. A., & Bokoro, P. N. (2022). Prediction of the degree of polymerization in transformer cellulose insulation using the feedforward backpropagation artificial neural network. Energies, 15(12), 4209.
- Ghoneim, S. S. (2021). The degree of polymerization in a prediction model of insulating paper and the remaining life of power transformers. Energies, 14(3), 670.
- Sapi, Zsombor, and Richard Butler. "Properties of cryogenic and low temperature composite materials-a review." Cryogenics 111 (2020): 103190.
- Ghunem, R. A., El-Hag, A. H., & Assaleh, K. (2010, June). Prediction of furan content in transformer oil using artificial neural networks (ANN). In 2010 IEEE International Symposium on Electrical Insulation (pp. 1-4). IEEE.
- Material data catalogue Isovolta AG, Isovolta AG, Austria. (http://https://www.isovolta.com/)
- Zakaria, F., Johari, D., & Musirin, I. (2012, November). Artificial neural network (ANN) application in dissolved gas analysis (DGA) methods for the detection of incipient faults in oil-filled power transformer. In 2012 IEEE International Conference on Control System, Computing and Engineering (pp. 328-332). IEEE.
- Dwiputranto, T. H., Setiawan, N. A., & Adji, T. B. (2021, September). DGA-based early transformer fault detection using GA-optimized ANN. In 2021 International Conference on Technology and Policy in Energy and Electric Power (ICT-PEP) (pp. 342-347). IEEE.
- Power, K. E. (2020). Analysis of Power Transformator Conditions Using DGA Method Using Artificial Neural Network in Krakatau Electrical Power Company. Management Research, 7(6), 77
Issue
| 2025 19th International Conference on Electrical Machines, Drives and Power Systems, ELMA 2025 - Proceedings, pp. 1-5, 2025, Bulgaria, https://doi.org/10.1109/ELMA65795.2025.11083400 |
Copyright IEEE |