摘要
以测量数据中广泛应用的最小二乘原理为基础 ,详细阐述了多维自回归 (AR)序列参数估计的最小二乘算法和阶数确定的FPE准则 ,并将此法应用于电容型设备的在线监测数据处理 ,分析了各相关物理量之间的影响关系。
Based on the least squares criterion widely used in surveying data processing, time-do main analysis method of multi-dimensional AR (Auto-regressive) series is illustrated in this paper, which includes parameter estimations by the least squares algorithm and rank confirmation by final prediction error (FPE). Online monitoring data of capacitive equipment is modeled by multi-dimensional series, and the interactions of the correlative variables are analyzed.
出处
《高电压技术》
EI
CAS
CSCD
北大核心
2004年第z1期124-126,128,共4页
High Voltage Engineering
关键词
时间序列分析
多维AR序列
最小二乘估计FPE准则
在线监测
time series analysis multi-dimensional AR series least square estimation final prediction error(FPE) online monitoring
