融合粗糙集与灰色理论的电力变压器故障预测.pdfVIP

第28 卷 第16 期 中 国 电 机 工 程 学 报 Vol.28 No.16 Jun. 5, 2008 154 2008 年6 月5 日 Proceedings of the CSEE ©2008 Chin.Soc.for Elec.Eng. 0258-8013 (2008) 16-0154-07 TM 835 A 470 40 文章编号： 中图分类号： 文献标识码： 学科分类号： ⋅ 融合粗糙集与灰色理论的电力变压器故障预测 费胜巍，孙 宇 (南京理工大学机械工程学院，江苏省 南京市 210094) Fault Prediction of Power Transformer by Combination of Rough Sets and Grey Theory FEI Sheng-wei, SUN Yu (School of Mechanical Engineering, Nanjing University of Science Technology, Nanjing 210094, Jiangsu Province, China) ABSTRACT: A new transformer fault prediction method 的正常运行是整个电力系统安全运行的关键，一旦 based on rough sets and grey theory was presented. The 发生故障，将会带来巨大经济损失[1] 。研究发现， improved three-ratio attribute decision table was constructed 电力变压器故障大部分由其内部潜伏性故障引发 and simplified by the knowledge acquisition method based on 的，潜伏性故障具有很强的隐蔽性，不易诊断、发 rough sets, and the minimal rules were obtained. Then, the 觉，因此，研究变压器的故障预测，在其故障发生 prediction models of three ratios in decision table were constructed respectively. The ratios of feature gases could be 之前，根据预测的故障类型预先采取针对性维修措 predicted by grey model and their future state feature was 施，确保变压器安全可靠的运行，具有非常重要意 obtained. According to the minimal rules, the incipient failure 义。然而，电力变压器结构复杂，造成故障的原因 could be predicted, and its probability was acquired by [2] [3-6] 很多，故障预测是比较困难的 。研究表明 ，变 combination rules’ credibility with the number of the failure 压器中故障气体的组成、含量及其比值关系与故障 ac