基于BP神经网络的汽轮机最末级组相对内效率应达值的确定

The Determining Method of Norm Relative Internal Efficiency for the Last Stages of Steam Turbine Based on the BP Neural Network

当采用级组的相对内效率来诊断汽轮机通流部分的故障时,需要将各级组的实测相对内效率与对应负荷下的应达值进行比较,来诊断出故障发生的部位以及故障的严重程度。对于由最后一段抽汽与低压缸排汽构成的最末级组,由于其排汽处于湿蒸汽区,目前尚无成熟准确的测量排汽焓的技术,所以很难确定最末级组相对内效率的应达值。在分析了影响凝汽式汽轮机最末级组相对内效率的主要因素后,给出了利用BP神经网络确定汽轮机最末级组相对内效率应达值的方法,为汽轮机通流部分的故障诊断奠定了基础。

In order to diagnose the position and the degree of fault in steam turbine flow passage, compared the measured relative internal efficiency of stages with the norm relative internal efficiency is needed, on the condition that the relative internal efficiency of stages is used to diagnosis fault of steam turbine flow passage. It is difficult to determine the norm relative internal efficiency of the last stages locating between the last extraction opening and exhaust steam casing, beeause the last stages lie in wet steam region and the exhaust steam enthalpy can＇ t be exactly obtained. In the paper, a method based on BP neural network to determine the norm of relative internal efficiency of the last stages is proposed by analyzing various effect factors of the last stages. The studying results fall foundations for fault diagnosis of steam turbine flow passage.