• Home
  • Search
  • Dynamic Prediction of Conductor Tension under Coupled Icing–Wind Loads
  • https://doi.org/10.1109/ei268505.2025.11425321Copy DOI Icon

Dynamic Prediction of Conductor Tension under Coupled Icing–Wind Loads

  • Dec 5, 2025
  • Yue Li +5 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

As a critical component of power system, distribution conductors are susceptible to fatigue damage under complex meteorological conditions involving combined wind and ice effects. Such damage can lead to strand breakage, thereby compromising the reliability and safety of distribution networks. To address the strong nonlinearity and temporal variability of conductor tension under the coupled influence of icing and fluctuating wind loads, this study develops a hybrid prediction framework that integrates CNN, CBAM and BiLSTM network. Research results indicate that the proposed CNN–CBAM– BiLSTM model significantly outperforms the conventional LSTM, BiLSTM, CNN–LSTM, and CNN–BiLSTM models in both prediction accuracy and stability, achieving RMSE and MAE values of 41.62 and 30.92, respectively. These results highlight the model’s superior ability in spatiotemporal feature extraction and adaptive feature fusion, effectively capturing the nonlinear and time-varying behavior of conductor tension under coupled wind– ice loading. This study provides a valuable reference for accurate conductor tension prediction and operational safety evaluation of distribution lines under the coupled influence of icing and fluctuating wind loads.

Similar Papers
  • Research Article

A Deep Recurrent Learning Framework for Multi-Class Microgrid Fault Classification Using LSTM and Bi-LSTM Models

  • Mar 23, 2026
  • Eng
  • Rakesh Sahu +4
  • PDF
  • Research Article
  • Citations50

Short-term prediction of wind power based on BiLSTM–CNN–WGAN-GP

  • Jan 17, 2022
  • Soft Computing
  • Ling Huang +3
  • Research Article
  • Citations6

Artificial Intelligence And Big Data Analytics For Supply Chain Management

  • Sep 23, 2024
  • International Research Journal of Modernization in Engineering Technology and Science
  • Research Article
  • Citations15

Impacts of LULC changes on runoff from rivers through a coupled SWAT and BiLSTM model: A case study in Zhanghe River Basin, China

  • Dec 01, 2024
  • Ecological Informatics
  • Jiawen Liu +4
  • Research Article
  • Citations4

Enhancing Stock Price Prediction Method Based on CNN-LSTM hybrid model

  • Dec 12, 2023
  • Highlights in Business, Economics and Management
  • Yuqi Ding
  • Research Article
  • Citations148

Image Captioning with Deep Bidirectional LSTMs and Multi-Task Learning

  • Apr 25, 2018
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Cheng Wang +2
  • Research Article
  • Citations3

BDBRC: A Chinese military entity recognition model combining context contribution and residual dilatation convolutional networks

  • Oct 20, 2023
  • Journal of King Saud University - Computer and Information Sciences
  • Jintao Wang +3
  • Research Article
  • Citations2

Crop Classification with Attention Based BI-LSTM and Temporal Convolution Neural Network Combination for Remote Sensing Breizhcrop Time Series Data

  • Apr 30, 2024
  • Yüzüncü Yıl Üniversitesi Fen Bilimleri Enstitüsü Dergisi
  • Amer Bandar +1
  • Research Article
  • Citations7

FP-STE: A Novel Node Failure Prediction Method Based on Spatio-Temporal Feature Extraction in Data Centers

  • Jan 01, 2020
  • Computer Modeling in Engineering & Sciences
  • Yang Yang +4
  • Research Article

Dynamic Response Analysis of Large-Diameter Monopile Foundation Under Ice Load

  • Mar 06, 2025
  • Sustainability
  • Shuxing Liu +3
  • Research Article
  • Citations1

Deep learning-based automatic modulation recognition: Combination of CNN and LSTM neural network

  • Apr 16, 2025
  • Advances in Engineering Innovation
  • Yun Jiang
  • Research Article
  • Citations49

Short-term PV power prediction based on meteorological similarity days and SSA-BiLSTM

  • Feb 23, 2024
  • Systems and Soft Computing
  • Yikang Li +4
  • PDF
  • Research Article
  • Citations9

Quantitative Detection of Defects in Multi-Layer Lightweight Composite Structures Using THz-TDS Based on a U-Net-BiLSTM Network.

  • Feb 09, 2024
  • Materials
  • Dandan Zhang +7
  • PDF
  • Research Article
  • Citations7

Automatic Recognition of Communication Signal Modulation Based on the Multiple‐Parallel Complex Convolutional Neural Network

  • Jan 01, 2021
  • Wireless Communications and Mobile Computing
  • Zhen Huang +4
  • Research Article
  • Citations18

A Deep 1-D CNN and Bidirectional LSTM Ensemble Model With Arbitration Mechanism for LDDoS Attack Detection

  • Dec 01, 2022
  • IEEE Transactions on Emerging Topics in Computational Intelligence
  • Zengguang Liu +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.