面向无人机巡检场景基于 QRGBDT 的架空输电线路弧垂区间预测
Power Line Sag Interval Prediction Basedon QRGBDT for UAV InspectionScenario
DOI: 10.12677/AIRR.2023.122016, PDF, 下载: 191  浏览: 461  国家科技经费支持
作者: 武云发, 林文帅, 段 恒, 谢家豪：广东工业大学自动化学院，广东 广州
关键词: 无人机巡检；架空输电线路；弧垂区间预测；分位数极限梯度提升树；Drone Inspection； Overhead Transmission Lines； Sag Interval Prediction； QRGBDT
摘要: 随着无人机电力巡检技术的发展，无人机巡检逐渐替代了人工巡检，成为输电线路监测和维护中不可或缺的工具。弧垂作为输电线路安全运行的关键指标，准确的弧垂区间预测对于确保线路安全运行和及时维护具有重大意义。针对新型无人机巡检场景，本研究提出了一种基于分位数极限梯度提升树（QRGBDT）的架空输电线路弧垂区间预测方法。通过将分位数回归模型与极限梯度提升树模型相结合，构建了一个既能有效处理异常值、捕捉数据分布多样性，又具有高度拟合能力和优异泛化性能的弧垂区间预测模型。通过实际应用案例以及与 QRCNN 和 QRRNN 模型的对比，证实了本方法的有效性和优越性。
Abstract: With the development of drone power inspection technology, drone inspection has gradually replaced manual inspection, becoming an indispensable tool in the monitoring and maintenance of transmission lines. As a key indicator of the safe operation of transmission lines, accurate sag interval prediction is of great significance for ensuring the safe operation of lines and timely maintenance. In view of the new drone inspection scenario, this study proposes an overhead transmission line sag interval prediction method based on Quantile Regression Extreme Gradient Boosting Decision Tree (QRGBDT). By combining the quantile regression model with the extreme gradient boosting decision tree model, a sag interval prediction model is constructed that can effectively handle outliers, capture the diversity of data distribution, and has high fitting ability and excellent generalization performance. Through actual application cases and comparison with QRCNN and QRRNN models, the effectiveness and superiority of this method are confirmed.
文章引用：武云发, 林文帅, 段恒, 谢家豪. 面向无人机巡检场景基于 QRGBDT 的架空输电线路弧垂区间预测[J]. 人工智能与机器人研究, 2023, 12(2): 126-142. https://doi.org/10.12677/AIRR.2023.122016

参考文献

[1] da Silva, M.F., Honório, L.M., Marcato, A.L.M., Vidal, V.F. and Santos, M.F. (2020) Unmanned Aerial Vehicle for Transmission Line Inspection Using an Extended Kalman Filter with Colored Electromagnetic Interference. ISA Transactions, 100, 322-333.
https://doi.org/10.1016/j.isatra.2019.11.007
[2] 彭向阳, 易琳, 钱金菊, 王柯, 郑晓光, 韩正伟, 陈国强. 大型无人直升机电力线路巡检系统实用 化 [J]. 高电压技术, 2020, 46(2): 384-396.
[3] Zhang, Y., Yuan, X.X., Li, W.Z. and Chen, S.Y. (2017) Automatic Power Line Inspection Using UAV Images. Remote Sensing, 9, Article 824.
https://doi.org/10.3390/rs9080824
[4] 常龙, 游华武. 无人机激光雷达技术在高压输电线路三维设计中的应用 [J]. 电声技术, 2021, 45(10): 80-82.
[5] 隋宇, 宁平凡, 牛萍娟, 王辰羽, 赵地, 张伟龙, 韩抒真, 梁立君, 薛高建, 崔颜军. 面向架空输电 线路的挂载无人机电力巡检技术研究综述 [J]. 电网技术, 2021, 45(9): 3636-3648.
[6] 全国架空线路标准化技术委员会线路运行分技术委员会. DL/T 741-2019. 架空输电线路运行 规程 [S]. 北京: 中国电力出版社, 2019: 1-36.
[7] IEEE (2013) IEEE Standard for Calculating the Current-Temperature Relationship of Bare Overhead Conductors. IEEE Std 738-2012, IEEE, New York, 1-58.
[8] 孟遂民, 孔伟. 架空输电线路设计 [M]. 第 2 版. 北京: 中国电力出版社, 2015.
[9] Xu, Y.J., Huang, C., Chen, X., Mili, L., Tong, C.H., Korkali, M. and Min, L. (2019) Response Surface-Based Bayesian Inference for Power System Dynamic Parameter Estimation. IEEE Transactions on Smart Grid, 10, 5899-5909.
https://doi.org/10.1109/TSG.2019.2892464
[10] Ye, G., Xiang, Y., Nijhuis, M., Cuk, V. and Cobben, J.F.G. (2017) Bayesian-Inference-Based Voltage Dip State Estimation. IEEE Transactions on Instrumentation and Measurement, 66, 2977-2987.
https://doi.org/10.1109/TIM.2017.2734138
[11] Wang, Y., Zhou, Z., Botterud, A. and Zhang, K.F. (2017) Optimal Wind Power Uncertainty Intervals for Electricity Market Operation. IEEE Transactions on Sustainable Energy, 9, 199- 210.
https://doi.org/10.1109/TSTE.2017.2723907
[12] Yue, C.-D., Chiu, Y.-S., Tu, C.-C. and Lin, T.-H. (2020) Evaluation of an Offshore Wind Farm by Using Data from the Weather Station, Floating LiDAR, MAST, and MERRA. Energies, 13, Article 185.
https://doi.org/10.3390/en13010185
[13] Wang, S.J., Zeng, J.Y. and Liu, X.P. (2019) Examining the Multiple Impacts of Technological Progress on CO2 Emissions in China: A Panel Quantile Regression Approach. Renewable and Sustainable Energy Reviews, 103, 140-150.
https://doi.org/10.1016/j.rser.2018.12.046
[14] Zheng, H.T., Yuan, J.B. and Chen, L. (2017) Short-Term Load Forecasting Using EMD-LSTM Neural Networks with a Xgboost Algorithm for Feature Importance Evaluation. Energies, 10, Article 1168.
https://doi.org/10.3390/en10081168
[15] Jia, X.W., Willard, J., Karpatne, A., Read, J.S., Zwart, J.A., Steinbach, M. and Kumar, V. (2021) Physics-Guided Machine Learning for Scientific Discovery: An Application in Simulating Lake Temperature Profiles. ACM/IMS Transactions on Data Science, 2, Article No. 20.
https://doi.org/10.1145/3447814
[16] Chen, T.Q., He, T., Benesty, M., Khotilovich, V., Tang, Y., Cho, H., Chen, K.L., et al. (2015) XGBoost: Extreme Gradient Boosting.
https://cran.r-project.org/web/packages/xgboost/vignettes/xgboost.pdf

为你推荐