Oil-immersed power transformer is the most important piece of equipment in the transmission system, and the stable operation of this equipment is of great significance to the normal work of the power system. At present, deep learning has been widely used in transformer condition evaluation and fault detection. About the shortage of deep learning algorithm models, this paper proposes a transformer digital twin model construction and fault diagnosis and condition evaluation analysis based on gray clustering algorithm (GCA) and conventional neural network (CNN). The data are first collected and filtered by combining the operation data, condition information amount and faulty features of power transformers, and then the condition features and fault features are combined to evaluate and detect the condition and faults of power transformers using GCA-CNN respectively. The whitening weight function is determined by expert scoring, the state evaluation matrix is established, the evaluation coefficients are obtained to calculate the evaluation weights, and the transformer state is obtained according to the clustering coefficients; 2000 pieces of raw data are input into the model to obtain the output fault types. Finally, the results are derived and compared with the real results. This paper uses real data from a power plant in Yunnan, and according to the results, the model established in this paper has higher accuracy and better evaluation and detection effects.

Ziyi Wang, Haoran Xu. GCA-CNN based transformer digital twin model construction and fault diagnosis and condition evaluation analysis. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 6: 100-107. https://doi.org/10.25236/AJCIS.2023.060616.

[1] Xian Richang, Fan Huifang, Li Fei, et al. Fault diagnosis of power transformers based on improved GSA-SVM model [J]. Intelligent Power, 2022, 50(6):50-56.

[2] Fan Lu, Lu Yuncai, Tao Fengbo, et al. Application of artificial intelligence in partial discharge detection (II): pattern recognition and state assessment [J]. Insulation Materials, 2021, 54(7):10-24.

[3] Chen Qipeng. Research on the key technology for monitoring the state of automated production line manufacturing process oriented to digital twin [D]. Guizhou: Guizhou University, 2021.

[4] K.Y. Tan. Condition assessment and life prediction of power transformers [D]. Hunan: Hunan University, 2018.

[5] Fu Yang, Qiao Fei. A comprehensive analysis method of power transformer condition based on intelligent technology [J]. Journal of Shanghai Electric Power Institute, 2004, 20(3):1-6.

[6] Wu H, Shen G Q, Lin X, et al. A transformer-based deep learning model for recognizing communication-oriented entities from patents of ICT in construction[J]. Automation in Construction, 2021, 125(May 2021):103608.

[7] Luo Weiming. Research on power transformer condition assessment and fault diagnosis method [D]. Guangdong: Guangdong University of Technology, 2019.

[8] Deng Y, Wang XH. Research on transformer condition evaluation method based on CHSMM [J]. Journal of Electric Power, 2021, 36(1):7-16.

[9] Xie P. Research on health management system of oil-immersed power transformers based on data and model [D]. Guangdong: South China University of Technology, 2020.

[10] Liu C. F., Luo R. C., Jiang Q. Q., et al. Transformer group health state assessment based on gray clustering and fuzzy comprehensive evaluation [C]. // Proceedings of the Twenty-seventh Annual Academic Conference of Chinese Higher Education Institutions on Power Systems and Their Automation. 2011: 1-5.

[11] Wang Xingxun, Wang Yuexiang, Ni Kangting, et al. Deep learning based on transformer load capacity assessment and application [J]. Electrical Engineering Technology, 2022(15):42-45, 55.

[12] Xuejiao Gong, Ruijin Zhu, Bo Tang. Short-term peak load prediction based on Bayesian optimization XGBoost [J]. Power Engineering Technology, 2020, 39(6): 76-81.