基于迁移联邦学习的输电线路缺陷检测
作者:
基金项目:

辽宁省高等学校基本科研项目(LIKMZ20220699, JYTMS20230804)


Transmission Line Defect Detection Based on Transfer Federated Learning
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [20]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    有效检测输电线路的破损和异物对电路智能巡检至关重要. 然而, 由于存在着数据孤岛问题, 难以收集不同电力公司的数据来训练统一的检测模型. 因此, 结合迁移联邦学习和目标检测算法提出了一种基于迁移联邦学习的电路缺陷检测方法. 具体地, 首先选用一个强大的检测模型作为基础检测模型, 并冻结模型初始权重. 然后通过权重矩阵的低秩分解以及插入适配器层的方式进行对不同客户端的数据进行适应学习, 从而大幅降低可训练模型参数的目的. 其次, 提出一种权重自适应筛选方法, 以精确确定模型权重层的低秩分解和适配器层的插入位置, 通过简单的适应学习, 即可对不同电力公司中的数据分布进行有效适应. 最后, 在接近真实环境的电力数据集上进行的实验验证表明, 在保证客户数据安全性和隐私性的前提下, 能够很好地适应不同分布的检测场景.

    Abstract:

    Effective detection of damage and foreign matter on transmission lines is very important for intelligent circuit inspection. However, it is difficult to collect data from different power companies to train a unified detection model due to the data island problem. Therefore, this study proposes a circuit defect detection method based on federated transfer learning by combining federated transfer learning and object detection algorithms. Specifically, a high-performance detection model is selected as the basic detection model, whose initial weight is frozen. The model adaptively learns from the data of different clients by using the low-rank decomposition of the weight matrix and inserting an adapter layer, so as to greatly reduce the number of the trainable parameters. An adaptive weight screening method is also proposed to accurately determine the low-rank decomposition of the weight layer and the insertion position of the adapter layer of the model. Through simple adaptive learning, the model can effectively adapt to the data distributions from different power companies. Experimental verification on a power dataset that closely resembles real-world conditions shows that the proposed model can adapt to different distributed detection scenarios under the premise of ensuring the security and privacy of customer data.

    参考文献
    [1] Xiao YZ, Tian ZQ, Yu JC, et al. A review of object detection based on deep learning. Multimedia Tools and Applications, 2020, 79(33): 23729–23791.
    [2] 尹宏鹏, 陈波, 柴毅, 等. 基于视觉的目标检测与跟踪综述. 自动化学报, 2016, 42(10): 1466–1489.
    [3] 张林华, 方正云, 李仕林, 等. 双重对抗无监督域自适应绝缘子检测算法. 重庆大学学报, 2021, 44(03): 122–131.
    [4] Zu GX, Wu GL, Zhang C, et al. Detection of common foreign objects on power grid lines based on Faster R-CNN algorithm and data augmentation method. Journal of Physics: Conference Series, 2021, 1746(1): 012039.
    [5] Zhou FN, Yang S, Fujita H, et al. Deep learning fault diagnosis method based on global optimization GAN for unbalanced data. Knowledge-based Systems, 2020, 187: 104837.
    [6] Liu JH, Guo F, Gao H, et al. Defect detection of injection molding products on small datasets using transfer learning. Journal of Manufacturing Processes, 2021, 70: 400–413.
    [7] Konečný J, McMahan HB, Yu FX, et al. Federated learning: Strategies for improving communication efficiency. arXiv:1610.05492, 2016.
    [8] Li DL, Wang JP. FedMD: Heterogenous federated learning via model distillation. arXiv:1910.03581, 2019.
    [9] Otoum S, Guizani N, Mouftah H. On the feasibility of split learning, transfer learning and federated learning for preserving security in ITS systems. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(7): 7462–7470.
    [10] 沈茂东, 裴健, 付新阳, 等. 一种新的输电线路异物检测网络结构——TLFOD Net. 计算机与现代化, 2019, (2): 118–122.
    [11] Guo SQ, Bai QL, Zhou XX. Foreign object detection of transmission lines based on faster R-CNN. In: Kim KJ, Kim HY, eds. Information Science and Applications. Singapore: Springer, 2020. 269–275.
    [12] McMahan B, Moore E, Ramage D, et al. Communication-efficient learning of deep networks from decentralized data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics. Fort Lauderdale: PMLR, 2017. 1273–1282.
    [13] Yang Q, Liu Y, Chen TJ, et al. Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology, 2019, 10(2): 12.
    [14] Liu Y, Kang Y, Xing CP, et al. A secure federated transfer learning framework. IEEE Intelligent Systems, 2020, 35(4): 70–82.
    [15] Karimireddy SP, Kale S, Mohri M, et al. Scaffold: Stochastic controlled averaging for federated learning. Proceedings of the 37th International Conference on Machine Learning. PMLR, 2020. 5132–5143.
    [16] Lee G, Jeong M, Shin Y, et al. Preservation of the global knowledge by not-true distillation in federated learning. Proceedings of the 36th Conference on Neural Information Processing Systems. New Orleans, 2022. 1–14.
    [17] Huang PP, Wang G, Qin SY. Boosting for transfer learning from multiple data sources. Pattern Recognition Letters, 2012, 33(5): 568–579.
    [18] Wang JD, Feng WJ, Chen YQ, et al. Visual domain adaptation with manifold embedded distribution alignment. Proceedings of the 26th ACM International Conference on Multimedia. Seoul: ACM, 2018. 402–410.
    [19] Chen YQ, Qin X, Wang JD, et al. FedHealth: A federated transfer learning framework for wearable healthcare. IEEE Intelligent Systems, 2020, 35(4): 83–93.
    [20] Carion N, Massa F, Synnaeve G, et al. End-to-end object detection with Transformers. Proceedings of the 16th European Conference on Computer Vision. Glasgow: Springer, 2020. 213–229.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

曲海成,周圣杰.基于迁移联邦学习的输电线路缺陷检测.计算机系统应用,2024,33(10):198-204

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2024-03-04
  • 最后修改日期:2024-05-06
  • 在线发布日期: 2024-09-02
文章二维码
您是第11198011位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号