摘要
针对三相电能表在流水线上进行检定的过程中需对外界环境影响所带来的电能表超差进行预测,对造成超差的外界误差因素进行筛选和赋权,从而确定影响程度最大的几个因素;利用SPSS权重分析对输入变量进行加权归一化,并运用基于遗传算法的BP神经网络算法,对测量结果进行模拟;通过对比预测结果与实际结果,分析其准确性来达到风险预警的目的。
Addressing the prediction of out-of-tolerance in the three-phase electric energy meter during its verification process on the assembly line due to external environmental influences.This paper screens and assigns weights to the external error factors leading to this out-of-tolerance,aiming to pinpoint the factors with the most significant impact.Using SPSS for weight analysis,the input variables are weighted and normalized.Subsequently,the BP neural network algorithm,based on the genetic algorithm,is employed to simulate measurement results.By comparing the forecasted results with actual outcomes,we analyze their accuracy,thus achieving the goal of risk warning.
作者
周思阳
郭钧
ZHOU Siyang;GUO Jun(School of Mechanical and Electronic Engineering,Wuhan University of Technology,Wuhan 430070,China)
关键词
遗传算法
BP神经网络算法
三相电能表检定
风险预警
genetic algorithm
BP neural network algorithm
three-phase electric energy meter verification
risk warning