间接测量的神经网络解析模型及灵敏系数的计算  

Analytical Model of Indirect Measurement Based on Neural Network and Calculation of Sensitivity Coefficient

作　　者：朱坚民[1] 王中宇[2] 夏新涛[3] 

机构地区：[1]河南科技大学医学技术与工程学院 [2]北京航空航天大学仪器科学与光电工程学院 [3]河南科技大学机电工程学院

出　　处：《农业机械学报》2006年第5期129-131,147,共4页Transactions of the Chinese Society for Agricultural Machinery

基　　金：国家自然科学基金资助项目(项目编号:50375011)

摘　　要：针对无测量模型的间接测量不确定度评定问题,以径向基函数神经网络模型为基础,提出了建立间接测量解析模型和利用该模型计算灵敏系数的方法,导出了间接测量模型的解析表达式和灵敏系数的计算公式。仿真结果表明:神经网络解析模型的建模方法及灵敏系数的计算方法具有较高的精度,从而保证了间接测量结果的估计精度及测量不确定度的评定精度。A new method is developed to solve the problem of evaluating the measurement u in indirect measurement with no given measurement model. An analytical model based network using Radial Basis Function is set up. The expression of indirect measurement the calculation formula of the sensitivity coefficient are derived. The simulation resul that the analytical model based on neural network and the method of sensitivity calculation has high precision, thus effectively guarantees the precision of measurement its uncertainty estimation in indirect measurement. ncertainty on neural model and ts showed coefficient result and its uncertainty estimation in indirect measurement,

关 键 词：间接测量 测量不确定度 神经网络 解析模型 灵敏系数 

分 类 号：S119[农业科学—农业基础科学] TG801[金属学及工艺—公差测量技术]