汽轮发电机组转子复合故障的研究  

A New Method for Diagnosis Research of Compound Faults for Rotor in Turbine Generator Set

作　　者：董彩凤[1] 隗喜斌[1] 王天宇[1] 

机构地区：[1]哈尔滨工业大学,哈尔滨150001

出　　处：《汽轮机技术》2003年第6期377-379,共3页Turbine Technology

摘　　要：研究了一种综合应用神经网络的分类功能和D S推理融合诊断的故障决策新方法。针对大型汽轮发电机组多重故障复合发生的实际情况,首先应用神经网络技术对复杂故障进行了初步诊断,然后应用D S证据理论对诊断结果进行融合决策。解决了汽轮发电机组多重复合故障的诊断问题,并给出了诊断实例。A new method of synthetic application of neural network technique sorting function and Dempster-Shafer theory(D-S ) fusion diagnosis of faults decision-making is researched. Aiming at the practical run of turbine generator set with compound faults, neural network technique is used for primary diagnosis on compound faults. D-S reasoning theory is used to do fusion decision-making based on the diagnosis result. Compound faults for rotor in turbine generator set are solved. Diagnosis examples are given.

关 键 词：汽轮发电机组 复合故障 神经网络 D—S证据理论 

分 类 号：TP206.3[自动化与计算机技术—检测技术与自动化装置]