基于多RBF神经网络的汽车衡误差补偿  

Error Compensation for Truck Scale Based on Multiple RBF Neural Networks

作　　者：林海军[1,2] 滕召胜[1] 迟海[1] 吴阳平[1] 唐立军[1] 

机构地区：[1]湖南大学电气与信息工程学院,湖南长沙410082 [2]湖南师范大学工学院,湖南长沙410081

出　　处：《湖南大学学报（自然科学版）》2010年第5期40-44,共5页Journal of Hunan University:Natural Sciences

基　　金：国家自然科学基金资助项目(60272051);商务部优化机电和高新技术产品进出口结构资金项目(财企[2007]301号)

摘　　要：传统汽车衡称重误差补偿过程繁琐、称重结果准确度低,为此提出了一种基于多径向基函数神经网络(RBFNN)的汽车衡误差补偿方法.根据汽车衡不同检定秤量段的最大允许误差确定多个子RBFNN,每个子RBFNN负责一段秤量范围的误差补偿,建立相应秤量段的称重误差补偿模型,并给出补偿模型的训练算法.将各子RBFNN并联组合,利用自适应选择网络,自动选择合适的子RBFNN,完成不同称重段的最优补偿,从而获得全量程的最佳补偿效果.仿真实验表明,这种多RBFNN补偿方法与由单个RBFNN实现全量程补偿的方法相比,子RBFNN规模小,补偿效果更好.Conventional method of error compensation for truck scales is fussy and the weighing results are not precise,so an error compensation method based on multiple radial basis function neural networks（RBFNN） was proposed.The sub-RBFNNs were confirmed according to the maximum permissible error of scale＇s different verified weighing capacities.The compensation models were established and then the algorithm of training RBFNN was presented.Sub-RBFNNs were combined and one of them was chosen to fully compensate weighing error of every capacity by adaptive network,and then optimum compensation of total weighing range was obtained.Simulation experiments show that the sub-RBFNN＇s size of this proposed method is smaller and the errors are less than those of the method that compensates the error of total weighing range with single RBFNN.

关 键 词：汽车衡 称重误差 自适应补偿 多径向基函数神经网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]