由于故障电弧的物理特性复杂, 且电路中存在与故障电弧波形相似的负载, 因此传统 检测故障电弧的方法误判率较高. 提出了一种多传感器数据融合算法, 用于提高故障电弧的检测精度. 该算法包括自适应加权融合算法和神经网络融合算法, 实现了对温度传感器、声音传 感器和弧光强度传感器所获取的传感信号的数据融合. 自适应加权融合算法克服了单个传感 器的不确定性, 实现了同质传感器中故障电弧特征的提取, 为神经网络融合算法提供了精确的测试样本数据; 神经网络融合算法可自行调整各类异质传感器的权重, 使故障电弧的辨识率更高. 实验结果表明, 该算法可有效提取故障电弧的特征, 辨识精度超过98%, 实现了高精度的故障电弧检测.
Since physical characteristics of arc fault are complex and there are loads with waveforms similar to arc fault in circuits, misjudgment of traditional arc fault detection methods is high. To improve the arc fault detection accuracy, a multi-sensor data fusion algorithm that includes an adaptive weighted fusion algorithm and a neural network fusion algorithm is proposed. Date is acquired with a temperature sensor, an acoustic sensor and a light sensor. The adaptive weighted fusion algorithm can overcome uncertain of single sensor, extract the arc fault characteristics of homogeneous sensors, and provide accurate test sample date for neural network fusion, making the probability of identifying arc fault more accurately by automatically adjusting the weights for all kinds of heterogeneous sensors. Experimental results show that the algorithm can effectively extract the arc fault characteristics and improve identification accuracy up to 98%, meeting the high accuracy arc fault detection requirement.
[1] Sidhu T S, Sagoo G S, Sachdev M S. Multisensor secondary device for detection of low-level arcing faults in metal-clad MCC switchgear panel [J]. IEEE Transactions on Power Delivery,2002, 17(1): 129-134.
[2] Sidhu T S, Sachdev M S, Sagoo G S. Detection and location of low-level arcing faults in metal- clad electrical apparatus [C]// Seventh International Conference on Developments in Power System Protection Conference Publication. 2001: 157-160.
[3] 杨 建 红, 张 认 成, 杜 建 华. 基 于 多 信 息 融 合 的 故 障 电弧保 护系 统的应 用研究 [J]. 高 压 电 器, 2007,43(3): 194-196.
[4] 杨建红, 张认成, 房怀英. Duffing 振子信号探测在故障电弧短路保护中的应用 [J]. 电力系统自动化,2006, 30(24): 69-72.
[5] Johnson J, Kang J. Arc-fault detector algorithm evaluation method utilizing prerecorded arcing signatures [C]// Photovoltaic Specialists Conference. 2012: 001378-001382.
[6] Spyker R, Schweickart D L, Horwath J C, et al. An evaluation of diagnostic techniques relevant to arcing fault current interrupters for direct current power systems in future aircraft [C]// Electrical Insulation Conference and Electrical Manufacturing Expo Proceedings. 2005:146-150.
[7] Por C S, Choo K L, Jian L Y. A study of arc fault current in low voltage switchboard [C]// Sustainable Utilization and Development in Engineering and Technology. 2012: 52-56.
[8] Kim C H, Kim H, Ko Y H, et al. A novel fault-detection technique of high-impedance arcing faults in transmission lines using the wavelet transform [J]. IEEE Transaction on Power Delivery,2002, 17(4): 921-929.
[9] 杨艺, 董爱华, 付永丽. 低压故障电弧检测概述 [J]. 低压电器, 2009, 27(5): 1-4.
[10] Cudina M, Prezelj I.Evaluation of the sound signalbased on the welding current in the gas—metal arc welding process [J]. Journal of Mechanical Engineers, 2003, 217(5): 483-494.
[11] 李战明, 陈若珠, 张保梅. 同类多传感器自适应加权估计的数据级融合算法研究 [J]. 兰州理工大学 学报, 2006, 32(4): 78-82.
[12] Ji C, Cai Z Z, Tao N B. Molten steel breakout prediction based on genetic algorithm and BP neural network in continuous casting process [C]// Control Conference. 2012: 3402-3406.
[13] 王庆晖. 基于模糊神经网络的火灾信号处理设计 [J]. 上海电气技术, 2011, 4(4): 35-39.
