Review on Artificial Intelligence in Substation Operation and Maintenance Management

被引：0
作者：
Wang L. [1 ]
Zhou Z. [1 ]
Lin L. [2 ]
Han J. [1 ]
机构：
[1] State Grid Zhejiang Electric Power Co., Ltd., Research Institute, Hangzhou
[2] Global Energy Interconnection Research Institute Co., Ltd., Beijing
来源：
Gaodianya Jishu/High Voltage Engineering | 2020年 / 46卷 / 01期
关键词：
Artificial intelligence; Condition monitoring; Intelligent perception; Operation and maintenance management; Substation; Video monitoring;
D O I：
10.13336/j.1003-6520.hve.20191227001
中图分类号：
学科分类号：
摘要：
The operation and maintenance management of substation is one of the typical application scenarios of artificial intelligence in energy and power system. The artificial intelligence technology, mainly represented by expert system, traditional machine learning, and deep learning, is significant in promoting the development of substation intelligence. Firstly, we summarized the development status and characteristics, challenges, development trends and hot spots of artificial intelligence technology. Then, in combination with the advanced functional requirements of two major information systems in the substation, namely, the remote monitoring system based on sensors and the remote viewing system based on cameras, we analyzed the progress of artificial intelligence technology in typical scenarios such as assessment and diagnosis of major electrical equipment status, intelligent perception of substation security environment, and detection and discrimination of personnel behavior. Meanwhile, we pointed out the problems existing in the current application of artificial intelligence technology in the above-mentioned typical scenarios of substations. Finally, we put forward several suggestions on the key breakthrough areas in the future application of artificial intelligence technology to vital equipment state awareness and 3D panoramic visualization of substations. © 2020, High Voltage Engineering Editorial Department of CEPRI. All right reserved.
引用
收藏
页码：1 / 13
页数：12
相关论文
共 110 条
[61]  
Zhang Z., Yue H., Wang B., Et al., Pattern recognition of partial discharge ultrasonic signal based on similar matrix BSS and deep learning CNN, Power System Technology, 43, 6, pp. 1900-1906, (2019)
[62]  
Wang T., He Y., Li B., Et al., Transformer fault diagnosis using self-powered RFID sensor and deep learning approach, IEEE Sensors Journal, 18, 15, pp. 6399-6411, (2018)
[63]  
Liu H., Wang Y., Liang X., Et al., Prediction method of the dissolved gas volume fraction in transformer oil based on multi factors, High Voltage Engineering, 44, 4, pp. 1114-1121, (2018)
[64]  
Dai J., Song H., Yang Y., Et al., Concentration prediction of dissolved gases in transformer oil based on deep belief networks, Power System Technology, 41, 8, pp. 2737-2742, (2017)
[65]  
Li K., Qi X., Wei B., Et al., Prediction of transformer top oil temperature based on kernel extreme learning machine error prediction and correction, High Voltage Engineering, 43, 12, pp. 4045-4053, (2017)
[66]  
Li K., Xu Y., Wei B., Et al., Prediction model for top oil temperature of transformer based on hybrid kernel extreme learning machine trained and optimized by particle swarm optimization, High Voltage Engineering, 44, 8, pp. 2501-2508, (2018)
[67]  
Li Z., Zhang W., Sun N., Et al., Calculation of vibration fundamental frequency amplitude of transformer surface based on generalized regression neural network, High Voltage Engineering, 43, 7, pp. 2287-2293, (2017)
[68]  
Dai J., Song H., Sheng G., Et al., Prediction method for power transformer running state based on LSTM network, High Voltage Engineering, 44, 4, pp. 1099-1106, (2018)
[69]  
Wang Y., Lu F., Li H., Modified method on dielectric loss factor of capacitive equipment based on support vector machine and genetic algorithm, Proceedings of the CSEE, 29, 4, pp. 123-128, (2009)
[70]  
Wang X., Zhu Y., Wang Y., Et al., Online identification method of power capacitor dielectric loss angle based on deep learning, Transactions of China Electrotechnical Society, 32, 15, pp. 145-152, (2017)
234567891011