Measuring Color Index of Transformer Oil-Enabling Single-Wavelength Spectroscopy with Artificial Neural Network-Fuzzy Logic Model

• Main Authors: Hasnul Hadi M.H., Ker P.J., Lee H.J., Leong Y.S., Thiviyanathan V.A., Hannan M.A., Jamaludin M.Z., Mahdi M.A.
• Other Authors: 57295067100
• Format: Article
• Published: Institute of Electrical and Electronics Engineers Inc. 2025
• Subjects: Computer circuits; Electric transformer testing; Errors; Fuzzy inference; Fuzzy neural networks; Insulating oil; Machine learning; Mean square error; Oil filled transformers; Olive oil; Regression analysis; Color index; Fuzzy logic modeling; Fuzzy-Logic; Hybrid artificial neural network; Machine-learning; Oil; Oil insulations; Optical path lengths; Single wavelength; Transformer; Color

Conventionally, the color index of transformer oil is determined by a color comparator based on the American Society for Testing and Materials (ASTM) D 1500 standard. The equipment requires humans to operate, which leads to human error and limited number of samples tested per day. This work proposes...