BP神经网络在测试系统动态补偿中的应用(英文)  

Application of Back Propagation Artificial Neural Networks on Dynamic Compensation of Measurement Systems

作　　者：田社平[1] 韦红雨[1] 王志武[1] 颜国正[1] 

机构地区：[1]上海交通大学信息检测技术与仪器系,上海200030

出　　处：《测试技术学报》2005年第4期453-458,共6页Journal of Test and Measurement Technology

基　　金：国家自然科学基金资助项目(30270382)

摘　　要：测试系统的非线性动态补偿是仪器技术的一个重要方面.采用BP神经网络对测试系统进行动态补偿.BP神经网络的结果决定于网络输入、隐层和输出节点.由于其非线性映射特性,BP神经网络完全能够反映测试系统的动态响应特性.采用了收敛速度较快的递推预报误差算法训练神经网络.试验结果表明,BP神经网络的特性完全能够满足测试系统的动态补偿要求,表明本文的方法是有效的.Nonlinear dynamic compensation of measurement systems is an important aspect in the field of instrument technique. The back propagation（BP） neural network is proposed for nonlinear dynamic compensation of measurement systems, as its architecture is determined only by the number of nodes in the input, hidden and output layers. With the nonlinear mapping behavior, the BP neural network can catch up with the dynamic response of the system. A recursive prediction error algorithm which converges fast is applied to train the BP neural network. Experimental results show that the performance of the BP neural network model conforms to the measurement system to be compensated, proving the method is not only effective but of high precision.

关 键 词：动态补偿 神经网络 递推预报误差算法 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置]