基于油色谱分析的变压器故障在线预测方法

Online Fault Predicting Method Based on Dissolved Gas Analysis for Transformer

电力变压器是电力系统中的关键设备之一,变压器故障可能会造成长时间的供电中断.因此,尽早发现变压器故障具有重要的意义.介绍了能够在线监测变压器油中H2,CO,CH4,C2H4,C2H2,C2H6等6种气体在线监测装置的基本结构.根据油中各溶解气体的在线监测数据,采用灰色预测技术建立了灰色预测模型,并利用BPNN进行变压器的故障预测.该方法能够有效地预测未来时刻变压器油中溶解气体的浓度、诊断变压器在未来时刻的绝缘状况.现场运行结果表明,该方法能够满足工程实际的需要.

Power transformers are key elements in a power system. Failure of one power transformer may cause long interruptions in supply. It is therefore highly desirable to detect incipient failure as early as possible. The basic structure of the on-line monitoring unit is described. It can synchronously detect six kinds of gases dissolved in transformer oil, including H 2 , CO, CH 4 , C 2 H 4 , C 2 H 2 , C 2 H 6 . According to the on-line monitoring data and grey predicting theory, a predicting model is constructed and BPNN is used to diagnose transformer faults. It can availably predict the concentrations of the dissolved gases in transformer oil and diagnose insulation condition of transformer in future. The field operation results prove that this on-line fault predicting method is efficient and practicable.