基于SAAFSA优化加权模糊聚类算法的变压器故障诊断

针对加权模糊聚类算法(WFCM)应用于变压器DGA分析时存在收敛速度慢、对初始值敏感的问题,提出了一种改进人工鱼群优化加权模糊聚类算法(SAAFSA-WFCM)的变压器故障诊断方法.该方法利用模拟退火算法(SA)来改进人工鱼群算法(AFSA)以求取最佳初始聚类中心,在发挥AFSA优异的全局寻优能力的同时,利用SA的概率性突跳搜索机制对AFSA实施局部优化,提高了AFSA的搜索精度.WFCM算法以得到的最佳初始聚类中心为初值进行迭代运算,最终求得更接近实际位置的聚类中心,克服了WFCM易受初值影响的缺陷,加快了收敛速度.仿真与实例分析表明,该方法可有效应用于变压器的故障诊断,并有着较高的诊断正确率和诊断效率.

Transformer fault diagnosis based on weighted fuzzy clustering algorithm improved by SAAFSA

Aiming at the problem of the weighted fuzzy C-means (WFCM) clustering algorithm that the convergence speed is slow and sensitive to the initial value in transformer DGA analysis,a transformer fault diagnostic method based on the WFCM clustering algorithm optimized by improved artificial fish swarm algorithm (SAAFSA-WFCM) is proposed in this paper.This method adopts the artificial fish swarm algorithm (AFSA) improved by the simulated annealing (SA) to obtain the best initial clustering center,while taking advantage of the global optimization of AFSA,and the search accuracy of AFSA is improved through local optimization by using the probabilistic kick search mechanism of SA.By utilizing the obtained best initial clustering center as the initiatory value,WFCM algorithm finds the final clustering center which is getting closer to the actual location through iterative computation,and then,overcomes the shortcomings of traditional WFCM algorithm which is sensitive to the initial value and accelerates the convergence speed.Simulation and case analysis show that this method has higher accuracy and efficiency when applied to power transformer fault diagnosis.