变压器油中溶解气体含量检测故障诊断仪的设计

研究了应用变压器油中溶解气体含量检测来诊断变压器故障的方法,针对气体传感器之间存在的"交叉敏感"设计了基于人工神经网络的气体检测系统.神经网络采用使用最为广泛的BP网络.从而能构成对气体的较准确的分析测试.单片机选择Intel 16位的80C196KB,简化了接口电路的设计.设计中采用了油中气体分析法来确定变压器的故障并通过数码管显示出故障类型并由单片机来实现.

The Design of The Fault Detector of Dissolved Gas Concentration in Transformer oil

In this paper the dissolved gas analysis is applied to diagnose the transformer fault.A gas detection system based on artificial neural networks is also utilized to avoid the cross sensitivity among gas sensors.We choose B-P network which is widely used as the neural networks and can reflect the non-linear relation among the gas signals and analyze the mixed gases more accurately.MCU Intel 80C196KB is used,it predigests the design work of interface circuit.The method DGA is used to diagnose what faults the transformer has and the final result should be displayed on the LED.We can make the MCU to realize this method.