基于物理信息与数据驱动学习的电力系统鲁棒故障检测与分类
Robust Fault Detection and Classification in Power Systems via Physics-Informed and Data-Driven Learning
AI总结：
本文提出结合物理信息与数据驱动学习的智能框架，基于SMOTE平衡数据集训练PINN等模型，实现电力系统故障的鲁棒检测与分类，在噪声及训练数据占比波动下仍保持高准确率，可用于电网实时保护与广域监测控制。
AI中文摘要：
电力传输系统中的电气故障会严重影响电网稳定性、设备安全与运行可靠性。传统保护方案（尤其是距离继电器）依赖视在阻抗计算，在电流互感器（CT）/电压互感器（PT）饱和及高阻抗工况下，可能出现继电器超范围、欠范围或误动作问题。本文提出一种基于监督机器学习的智能故障检测与分类框架，该方法学习三相电压/电流模式与故障类型间的非线性关系，无需假设固定阻抗路径；采用推导得到的特征集表征6类故障，基于SMOTE平衡数据集开发人工神经网络、支持向量机、随机森林、XGBoost、长短期记忆网络（LSTM）及物理信息神经网络（PINN），在不同训练规模与高斯噪声水平下评估鲁棒性。PINN在干净数据集上达到最高故障检测准确率99.86%、多分类准确率99.79%，在2%-5%噪声及1%-60%训练数据占比下仍保持高准确率；该框架通过嵌入电力系统方程并提供毫秒级推理，衔接传统基于阻抗的保护与可扩展的数据驱动电网分析，适用于实时保护及广域监测与控制。
英文摘要：
Electrical faults in power transmission systems can severely affect grid stability, equipment safety, and operational reliability. Traditional protection schemes, particularly distance relays, depend on apparent impedance computation and may suffer from relay overreach, underreach, or maloperation due to CT/PT saturation and high-impedance conditions. This paper proposes an intelligent fault detection and classification framework based on supervised machine learning. The approach learns nonlinear relationships between three-phase voltage/current patterns and fault types without assuming fixed impedance paths. A derived feature set is used to represent six fault categories. Artificial Neural Networks, Support Vector Machines, Random Forests, XGBoost, Long Short-Term Memory networks, and Physics-Informed Neural Networks (PINNs) are developed using SMOTE-balanced datasets. Robustness is evaluated under different training sizes and Gaussian noise levels. The PINN achieved the highest fault detection accuracy of 99.86% and multiclass classification accuracy of 99.79% on the clean dataset, while maintaining high accuracy under 2-5% noise and 1-60% training data. By embedding power-system equations and providing millisecond-level inference, the proposed framework bridges traditional impedance-based protection and scalable data-driven grid analytics for real-time protection and wide-area monitoring and control.
