A 3D Space Violation Detection Method of Substations Based on the Deep Neural Network
Guoheng Ruan, Yerong Zhong, Jiaming Jiang · 2021
At present, smart grid construction has entered a new stage of the comprehensive and rapid development. In the field of sub stations, according to the requirements of the development plan formulated by the China Southern Power Grid Company Limited, the application of smart substations is imperative when the operation mode of traditional substations cannot meet the current development needs. Aiming at the problem of low efficiencies in the detection of violations and great harms to substations, this paper proposes a substation violation detection method based on a deep neural network from three-dimensional space. Based on the characteristic information of different violations, the characteristic expression of violations is established. Furthermore, an intelligent detection scheme for violations is established, in which the deep neural network is utilized to train samples. Effectivities and accuracies of the proposed intelligent detection scheme are verified by simulation experiments, and the results show that the algorithm can achieve good violation detection precisions.