基于粒子群优化聚类的汽轮机组振动故障诊断

Steam turbine vibration fault diagnosis based on particle swarm optimization clustering

针对模糊C-均值聚类算法(FCM)容易陷入局部极值和对初始值敏感的不足,提出了一种新的模糊聚类算法(PFCM),新算法利用粒子群优化算法(PSO)全局寻优、快速收敛的特点,代替了FCM算法的基于梯度下降的迭代过程,使算法具有很强的全局搜索能力,很大程度上避免了FCM算法易陷入局部极值的缺陷,同时也降低了FCM算法对初始值的敏感度。将该算法应用于汽轮机组振动故障诊断中,与电厂运行实际故障状态对照,仿真结果表明该算法提高了故障诊断的正确率。为汽轮机振动故障诊断方法的研究提供了一种新的思路。

A novel fuzzy clustering algorithm:PFCM was proposed based on the fusion of particle swarm optimization (PSO) and fuzzy c-means clustering (FCM).The conventional FCM has the two drawbacks of sensitivity to initialization and easily being trapped into local optima,due to the gradient descent approach used.With the features of global optimization and fast convergence,the hybrid algorithm presented can overcome these shortcomings and yield the optimal clustering performance.The new data clustering technique provided was also applied in the vibration fault diagnosis of steam turbine.Computer simulations demonstrate that compared with FCM,the proposed PFCM has a superior fault diagnosis capability.