基于并行变量预测模型的变压器故障诊断及优化研究.PDFVIP

第 47 卷 第 6 期 电力系统保护与控制 Vol.47 No.6 2019 年 3 月 16 日 Power System Protection and Control Mar. 16, 20 19 OI: 10.7667/PSPC180399 基于并行变量预测模型的变压器故障诊断及优化研究 马利洁，朱永利，郑艳艳 (新能源电力系统国家重点实验室(华北电力大学)，河北 保 071003) 摘要：针对传统变压器故障诊断方法存在小样本问题下分类效果 、海量监测数据的识别效率低下等问题，提出 基于 Spark 计算框架的并行化变量预测模型。首先采用 H FS 作为内存式存储系统，面向行存储的RowMatrix 作 为分布式矩阵存储结构，利用广播变量、调整分区数进行并行度优化。其次训练 4 种数学模型获取故障类型的最 佳模型及相关参数完成故障诊断。实验结果表明，并行变量预测模型识别精度高于支持向量机，计算效率优于单 机环境，对高维特征向量有较好的适应性。 关键词：故障诊断；小样本；变量预测模型；Spark 计算框架；内存式存储 Research on transformer fault diagnosis and optimization based on parallel variable prediction model MA Lij ie, ZHU Yongli, ZHENG Yanyan (State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Baoding 071003, China) Abstract: Traditional transformer fault diagnosis method has poor classification effect in the condition of small example and low recognition efficiency of mass monitoring data. Aiming at the problems above, this paper proposes a parallel variable predictive model based on the Spark computing framework. Firstly, H FS is used as memory storage system, RowMatrix is stored as a distributed matrix storage structure, and broadcast variable and adjustment of the partition number are used to optimize the degree of parallelism. Secondly, the optimal model type and model parameters are obta