Applied Mathematics and Nonlinear Sciences
Journal license

Journal

Applied Mathematics and Nonlinear Sciences


Volume
& Issue

Volume 9, Issue 1


Published
on

November 18, 2024


Pages


DOI

Article

Research on intelligent identification algorithm for preventing external damage behavior of power cable based on machine learning

Check for updates


Authors

Qian Li Affiliation:
Shijiazhuang Power Supply Branch, State Grid Hebei Electric Power Co., LTD., Shijiazhuang, Hebei, 050000, China.
, Kang Guo Affiliation:
Shijiazhuang Power Supply Branch, State Grid Hebei Electric Power Co., LTD., Shijiazhuang, Hebei, 050000, China.
, Siying Wang Affiliation:
Shijiazhuang Power Supply Branch, State Grid Hebei Electric Power Co., LTD., Shijiazhuang, Hebei, 050000, China.
, Jun Zhang Affiliation:
Shijiazhuang Power Supply Branch, State Grid Hebei Electric Power Co., LTD., Shijiazhuang, Hebei, 050000, China.
and Zexin Zhang Affiliation:
Shijiazhuang Power Supply Branch, State Grid Hebei Electric Power Co., LTD., Shijiazhuang, Hebei, 050000, China.


Abstract

As the key carrier of power distribution line power transmission and the supporting artery of urban functioning, power cables are widely used in electric power engineering construction. The number of users is increasing, and the distribution of locations is becoming more complex. However, if a power cable failure occurs, if not eliminated in time, it will threaten the safety of the power grid, seriously affecting the production of enterprises and the lives of residents. The article first on the power cable vibration signal recognition algorithm design, extraction of power cable external damage fault signal characteristics, proposed based on PSO-SVM power cable external damage fault waveform recognition algorithm, and the design of power cable anti-external damage intelligent early warning system, to achieve a certain period according to the trend of signal changes in the vibration event to discriminate. Research results show that under the same computer operating conditions, the average running time of the algorithm proposed in this paper is only 3.43. Compared to the other two algorithms, the algorithm has the highest recognition accuracy, the fastest convergence speed, and the optimal comprehensive performance. In the external damage signal recognition and warning test, the recognition rate of the excavator passing through defense zone one and two at a distance of 3 meters is 100%, which is greater than 80%, in line with the expected effect.


Keywords

External damage, Intelligent analysis, Support vector machine, Anti-external damage monitoring and warning system, Signal recognition, 65Y20


Citation

Li, Q., Guo, K., Wang, S., Zhang, J., & Zhang, Z. (2024). Research on intelligent identification algorithm for preventing external damage behavior of power cable based on machine learning. Applied Mathematics and Nonlinear Sciences, 9(1). https://doi.org/10.2478/amns-2024-3331

Published by: Engineering Journals

Engineering Journals Logo