摘要
根据接触电阻的特点与以往接触电阻计算方法存在的不足,运用结合模糊逻辑的智能计算方法对接触电阻进行计算.根据接触电阻与影响因素之间的关系进行试验,得到大量试验数据,将试验数据分成训练数据与测试数据两部分,训练数据用于训练模糊系统,测试数据用来测试模糊系统,检验其可靠性.通过训练数据运用梯度下降结合模拟退火算法训练模糊系统,建立接触电阻模型,运用回归分析对接触电阻进行计算.通过测试数据测试两种模型,基于模糊系统的模型优于回归分析,说明用梯度下降结合模拟退火算法训练模糊系统建立的接触电阻模型精确可靠.
Based on the characteristics of the contact resistance and the disadvantages of the traditional method for calculating contact resistance,an intelligent method combined with fuzzy logic is proposed in this paper. According to the relationship between contact resistance and influencing factors,a test is processed. The massive obtained data are divided into two parts,namely,training data and testing data,which are then used to train and test the fuzzy system respectively. The gradient descent algorithm is combined with simulated annealing algorithm through training data to establish the model of contact resistance. The regression analysis model of contact resistance is also built. The two models are tested by testing data. The prediction effect of the model based on the fuzzy system is better than that of the regression analysis model. The results show that the fuzzy system trained by gradient descent algorithm combined with simulated annealing algorithm is reliable to predict the contact resistance
作者
王刚
王之军
杨欣可
常林晶
徐健涛
WANG Gang WANG Zhijun YANG Xinke CHANG Linjing XU Jiantao(Pinggao Group Co. Ltd. , Pingdingshan, Henan 467001, China)
出处
《昆明理工大学学报（自然科学版）》
CAS
2017年第1期39-43,共5页
Journal of Kunming University of Science and Technology(Natural Science)
基金
国家电网科技项目(SGNXJX00YJJS1400105)
关键词
接触电阻
训练数据
测试数据
模糊系统
梯度下降算法
回归分析
contact resistance
training data
testing data
fuzzy system
gradient descent algorithm
regression analysis
