基于LabVIEW的变压器油色谱分析故障诊断系统

Transformer DGA Fault Diagnosis System Based on LabVIEW

开发了一套基于LabVIEW的变压器油色谱故障诊断系统。故障诊断模块使用改良电协研法和基于RPROP算法的多层前馈神经网络,为了避免LabVIEW调试功能不够强大的问题,使用了动态链接库技术实现了该模块。实现了对变压器油色谱数据和故障诊断信息进行存储、查询、修改、删除及图形化显示,同时具有良好的帮助功能。通过对河北省石家庄电业局变压器进行故障诊断验证了系统的有效性。

A transformer dissolved gas-in-oil analysis （DGA） fault diagnosis system based on LabVIEW is developed, and its modules are introduced. Fault diagnosis of transformer based on threeratio method and multiplayer feedforward neural network based on R.PROP algorithm is implemented in the system to overcome the shortcomings of bad debugging ability of LabVIEW. Dynamic link library technique is used to implement the module. Recording, accessing, modification, deleting and figure display of transformer dissolved gas-in-oil data are realized, and friendly help module is developed. The effectiveness of the system is verified by the fault diagnosis result of transformers of Shijiazhuang Electric Power Bureau.