EUVIMEDEUVIMED entdecken
Crossref

Intelligent identification algorithm and key point detection of abnormal vibration of transmission tower based on machine learning

Huawei Hong, Kaibin Wu, Mengmeng Yue, An Dai

International Journal of Emerging Electric Power Systems · 18.08.2023 · 24 (4) · 423-432

DOI: 10.1515/ijeeps-2023-0002 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Emerging Electric Power Systems, online erschienen am 17.04.2023. Verfasst von Huawei Hong und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 15 Literaturangaben. Gefördert von: Science and Technology Project of State Grid Corporation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In some special geological areas, the inclination and displacement of transmission line towers are relatively common, which should be analyzed from various factors. Transmission towers are the support structure for overhead transmission lines and play a pivotal role in the safe operation of the power grid. Transmission lines are widely distributed. Transmission poles and towers are generally built in areas with poor geological conditions such as goaf, river bed and slope. Under severe weather conditions, the force on the tower may be affected to a certain extent, causing the tower to tilt, deform, or even collapse, and thus causing a wide range of power system failures, which have a great impact on people’s production and life. Based on this objective problem, this paper has mainly studied the intelligent recognition methods and key technologies based on machine learning. In the experimental study of support vector machine (SVM) model based on machine learning, the average training time of genetic algorithm support vector regression (GA-SVR) was the longest, reaching 1.462 s. The average training duration of double chain quantum genetic algorithm-least squares support vector regression (DCQGA-LSSVR) was the shortest, with 0.156 s. The average pose error of double chain quantum genetic algorithm-support vector regression (DCQGA-SVR) was the smallest, only 0.136, while the average attitude error of genetic algorithm-least squares support vector regression (GA-LSSVR) was the highest, reaching 0.45. Therefore, it is of the great significance to analyze abnormal vibration of the transmission towers based on machine learning method.

Förderung

  • Science and Technology Project of State Grid Corporation

Zitieren

APA

Hong, H., Wu, K., Yue, M., & Dai, A. (2023). Intelligent identification algorithm and key point detection of abnormal vibration of transmission tower based on machine learning. International Journal of Emerging Electric Power Systems, 24(4), 423-432. https://doi.org/10.1515/ijeeps-2023-0002

Vancouver

Hong H, Wu K, Yue M, Dai A. Intelligent identification algorithm and key point detection of abnormal vibration of transmission tower based on machine learning. International Journal of Emerging Electric Power Systems. 2023;24(4):423-432. doi:10.1515/ijeeps-2023-0002

BibTeX
@article{Hong2023,
  author = {Hong, Huawei and Wu, Kaibin and Yue, Mengmeng and Dai, An},
  title = {Intelligent identification algorithm and key point detection of abnormal vibration of transmission tower based on machine learning},
  journal = {International Journal of Emerging Electric Power Systems},
  year = {2023},
  volume = {24},
  number = {4},
  pages = {423--432},
  doi = {10.1515/ijeeps-2023-0002}
}
Kostenlos starten →