基于GSA-IFCM的单位周期时间序列自适应提取方法  

Adaptive Extraction Method of Unit Period Time Series Based on GSA-IFCM

作　　者：闫啸家 梁伟阁[1] 张钢 田福庆[1] YAN Xiaojia;LIANG Weige;ZHANG Gang;TIAN Fuqing(Naval University of Engineering,Wuhan 430033,China)

机构地区：[1]海军工程大学,湖北武汉430033

出　　处：《探测与控制学报》2022年第2期60-65,72,共7页Journal of Detection & Control

基　　金：湖北省自然科学基金项目资助(2019CFB362)。

摘　　要：针对表征供输弹机构往复运动过程中近似周期振动信号的单位周期时间序列无法精确提取的问题,提出基于GSA-IFCM的单位周期时间序列自适应提取方法。通过改进模糊C-均值聚类算法(IFCM),将其与遗传模拟退火算法(GSA)相结合,提取近似周期信号极大值的聚类中心;运用时间窗能量法(t-MSV),通过设置时间窗计算时间序列能量曲线以确定单位周期时间序列的起止位置,从而提取单位周期时间序列。试验结果表明,所提方法能够有效克服数据噪声的影响,提高聚类结果的准确性,精确提取单位周期时间序列。In order to solve the problem that the unit periodic time series that characterizes the approximate periodic signal in the reciprocating motion of the bomb feeding mechanism could not be accurately extracted,an adaptive extraction method of unit periodic time series based on GSA-IFCM was proposed.First,this paper improved fuzzy c-means algorithm(improved fuzzy c-means algorithm,IFCM)by combining it with the genetic simulated annealing algorithms(GSA),extracting clusters that approximate the maximum value of the periodic signal center.Then,this paper used the time window energy method(t-mean square value,t-MSV)to calculate the time series energy curve by setting the time window to determine the start and end positions of the unit cycle time series,thus the unit cycle time series was extracted.The results from experiments showed that the proposed method could effectively overcome the influence of noisy data,improved the accuracy of clustering results,and accurately extracted time series per unit period.

关 键 词：近似周期信号 遗传模拟退火算法 单位周期时间序列 供输弹机构 

分 类 号：TH17[机械工程—机械制造及自动化]