运用免疫遗传神经网络的汽轮机振动故障诊断  

Vibration Fault Diagnosis of Steam Turbine Using Immune Genetic Neural Networks

作　　者：程力旻[1] 谢志江[1] 刘利云[2] 孙红岩[1] 

机构地区：[1]重庆大学机械工程学院,重庆400030 [2]中国船舶重工集团公司第七一九研究所,武汉430064

出　　处：《振动．测试与诊断》2010年第6期675-678,共4页Journal of Vibration,Measurement & Diagnosis

基　　金：重庆市自然科学基金资助项目(编号:2008BB3179)

摘　　要：提出了基于疫苗接种策略的免疫遗传神经网络(VIG-NN)算法,并将其用于汽轮机的振动故障诊断。该算法将疫苗接种、基于浓度的抗体选择、自适应交叉和变异概率引入遗传算法,不仅保持了优良抗体在进化中的主导地位,而且充分发掘了强成长性抗体的寻优潜力,对全局最优解的搜索快速且有效。实践表明,与传统算法相比,VIG-NN能够更准确地模拟故障征兆与故障类型之间的非线性关系,提高了汽轮机振动故障诊断的准确率。An immune genetic neural networks based on vaccine inoculation（VIG-NN）is proposed.VIG-NN is used to diagnose vibration fault of a steam turbine.The key of the algorithm lies in vaccine inoculation,antibodies selection based concentration and adaptive probability of cross and aberrance.The algorithm not only keeps the leading position of excellent antibody,but also develops the potential of rapidly growing antibody in seeking optimum.The search of algorithm to global optimum is fast and effective.The practice shows that VIG-NN can simulate the nonlinear mapping relationship between fault symptom and fault type more accurately.The diagnosis accuracy of the steam turbine vibration fault is improved.

关 键 词：免疫遗传算法 神经网络 汽轮机 故障诊断 

分 类 号：TK267[动力工程及工程热物理—动力机械及工程]