State Key Laboratory of Electrical Insulation and Power Equipment, Xi'an Jiaotong University, Xi'an 710049, Shaanxi Province, China.
Rev Sci Instrum. 2023 Feb 1;94(2):024704. doi: 10.1063/5.0104722.
Several deep learning partial discharge (PD) diagnostic approaches have been developed in recent years to guarantee the security and stability of gas-insulated switchgear (GIS). The centralized training method requires multiple clients to jointly obtain as much data as possible to train the model to achieve excellent performance, which is impractical due to conflicts of interest and privacy protection. Furthermore, because of differences in the distribution of client data and the presence of a small sample, achieving high-precision and robust diagnosis for each client is an urgent problem. To that end, a novel personalized federated meta-learning (FML) is proposed in this paper to address the aforementioned issues. It develops reliable and personalized PD diagnosis models by collaborating with multiple clients and solves the problem of small sample diagnosis through scenario training under the premise of protecting data privacy. The experimental results show that the FML proposed can diagnose GIS PD with high precision and robustness for each client while maintaining privacy. The diagnostic accuracy of the FML proposed in this paper, especially for on-site unbalanced small sample clients, is 93.07%, which is significantly higher than that for other methods. It serves as a model for the collaborative development of an effective GIS PD diagnostic model.
近年来，为了保证气体绝缘开关设备（GIS）的安全稳定，已经开发了几种深度学习局部放电（PD）诊断方法。集中式训练方法需要多个客户端共同尽可能多地获取数据来训练模型以达到优异的性能，但由于利益冲突和隐私保护的原因，这在实践中是不切实际的。此外，由于客户端数据分布的差异和小样本的存在，为每个客户端实现高精度和鲁棒的诊断是一个紧迫的问题。为此，本文提出了一种新颖的个性化联邦元学习（FML）方法来解决上述问题。它通过与多个客户端合作开发可靠和个性化的 PD 诊断模型，并在保护数据隐私的前提下通过场景训练解决小样本诊断问题。实验结果表明，所提出的 FML 可以在保护隐私的同时，为每个客户端的 GIS PD 诊断提供高精度和鲁棒性。本文提出的 FML 的诊断精度，特别是对于现场不平衡的小样本客户端，高达 93.07%，明显高于其他方法。它为开发有效的 GIS PD 诊断模型的协作提供了一个模型。
