Publication

[1] D. Firouzimagham, P. Aminaie, Z. Shayan, M. Sabouri and M. H. Asemani, "Online Transformer Oil Analysis Based on Spectroscopy Technique and Machine Learning Classifier: Experimental Setup", 15th International Conference on Protection and Automation of Power Systems (IPAPS), Shiraz, Iran, 2020, pp. 30-36, DOI: 10.1109/IPAPS52181.2020.9375568. 

Link to IEEE

Abstract:

Power transformers are used throughout the interconnected power grid. These transformers significantly affect the reliability of the power grid. One of the most critical components of a transformer is insulating oil. Insulating oil is responsible for heat transfer and electrical insulation. Scheduled monitoring of transformer oil aging can improve the status of the transformers and make significant changes to increase the reliability of the power grid. The main reasons for oil aging are thermal and electrical pressures. These tensions cause chemical degradation of the oil. Therefore, by several types of tests, the relative aging of the oil can be detected. Current industrial methods are generally offline and costly. In this paper, a laboratory-based method for online transformer oil analysis based on the spectroscopy technique has been proposed and implemented. Furthermore, machine learning algorithms implemented on system results to distinguish between oils with different aging. According to the obtained results, the presented method is effective with high accuracy.