摘要
遗传算法是一种能够借鉴生物界自然选择和进化机制发展起来的高度并行、随机、自适应搜索算法;为解决传统遗传算法早熟及收敛速度慢的问题,提出了一种改进的自适应遗传算法,改进后的遗传算法在全局优化和快速收敛能力上有较大的提高;文章针对多征兆、多故障的汽轮发电机组的故障诊断系统,对采用改进后的自适应遗传算法(AGA)和RBF径向基函数神经网络相结合进行故障模式识别的方法进行研究;仿真结果表明,该方法对于汽轮发电机组的故障诊断具有较高的实用价值。
Genetic algorithm is a reference to natural selection and evolution of living nature mechanism developed with the highly parallel, randomized, adaptive search algorithm. An improved adaptive genetic algorithm （IAGA） was proposed to avoid the premature problem and the slow convergence, and the proposed algorithm shows its better global optimal ability and its faster convergence ability. Aiming at multi--signs, multi--fault turbine diagnosis system, the combination of IAGA and RBFNN that applied to fault pattern recognition is studied. Simulation results show that the method of fault diagnosis of Turbine has high practical value.
出处
《计算机测量与控制》
CSCD
2008年第8期1090-1092,共3页
Computer Measurement &Control
基金
湖南省科学技术与科技计划项目(2006GK3130)
湖南省自然科学基金资助项目(05JJ30121)
关键词
自适应遗传算法
神经网络
故障诊断
adaptive genetic algorithm
neural network
fault diagnosis
