摘要
电力变压器是电力系统的重要设备之一,它的安全稳定运行对电力系统的安全生产具有重要的现实意义。传统的电力变压器故障诊断数据来源比较单一,对诊断结果准确性的贡献效果存在不足。文章提出了一种基于多源信息融合的电力变压器故障诊断方法,首先,将深度信念网络(Deep Belief Network,DBN)与DS证据理论相结合;然后,通过反复训练网络与调优,使算法准确率达到最好;最终,通过算例仿真验证了所提方法的有效性和可行性。
Transformer is an important equipment of power system, and it is of great significance to maintain the safe operation of power system. The traditional power transformer fault diagnosis data is relatively simple and is insufficient to the accuracy of diagnosis. Therefore, this paper proposes a transformer fault diagnosis method based on multi-source information fusion. First, the deep belief neural network and DS evidence theory are combined. Through repeated training network and tuning, the best accuracy of the algorithm is achieved. Finally, the effectiveness and feasibility of the proposed method are verified by an example simulation.
作者
赵文清
祝玲玉
高树国
李刚
ZHAO Wenqing;ZHU Lingyu;GAO Shuguo;L(School of Control and Computer Engineering,North China Electric Power University,Baoding 071003,China;State Grid Hebei Electric Power Research Institute,Shijiazhuang 050021,China)
出处
《电力信息与通信技术》
2018年第10期25-30,共6页
Electric Power Information and Communication Technology
基金
国家自然科学基金(51407076)
国家电网公司总部科技项目资助(5204DY170010)
中央高校基本科研业务费专项资金(2018MS075)
关键词
故障诊断
多源信息融合
深度信念网络
DS证据理论
fault diagnosis
multi-source information fusion
deep belief network
DS evidence theory
