Transmission line voltage classes identification based on particle swarm optimization algorithm and PCNN

ABSTRACT

For the current problems of the high voltage device of autonomous safety, warning is required manual input of the voltage classes. A method of dividing the insulator image based on the simplified model of PCNN is proposed to extract the number of insulator sheds of a string to independently identify the voltage of high voltage transmission line. Because the image segmentation effect of PCNN model is closely related to its many parameter tuning, however, the PSO algorithm is used to select the optimal PCNN parameter to realize the binary segmentation of the Insulator image in this paper, and then the transform angle of the image region is corrected so that the Insulator horizontal array, and then according to the shape of the Insulator binary image characteristics to extract the number of Insulator Sheds in order to achieve the transmission line voltage classes of self-identification. The experimental results show that the method can identify and extract the number of Insulator Sheds, and has strong practicability.

KEYWORDS:

• Voltage classes identification
• insulator image
• angle correction
• shape features

Funding

This work was financially supported by Electric Power Research Foundation funded project (2017KF28).