非线性MIMO传感器信号重构中粗差的探测与修复  

Gross error detection and recovery in nonlinear signals reconstruction for MIMO sensors

作　　者：刘丹[1] 魏国[1] 孙金玮[1] 刘昕[1] 

机构地区：[1]哈尔滨工业大学智能测试及信息处理技术研究所,哈尔滨150001

出　　处：《电子测量技术》2008年第7期141-146,共6页Electronic Measurement Technology

基　　金：国家自然科学基金资助(60672008;60772007)

摘　　要：本文以多输入多输出(MIMO)非线性传感器系统为背景,在Ferguson-Srikantan检验法和RBF神经网络拟合法的基础上提出了一种训练样本集中粗差定位与修复方法。传统粗差检验方法以残差作为诊断统计量,容易对高杠杆点和粗差点产生误判。而建立在学生氏残差和外学生氏残差基础上的F-S检验法能高效地区分两者,并定位粗差点,然后利用RBF神经网络拟合法估计并替换粗差点,从而完成训练样本集的修复。实验表明,该方法具有很强的鲁棒性,在精确定位和准确修复粗差数据的同时提高了传感器信号重构的效率。Based on multi-input multi-output （MIMO） nonlinear sensor, a novel method combined Ferguson-Srikantan test and RBF neural network regressing is proposed in this paper to deteet and eorreet gross error data of sample set. Conventional gross error deteeting method regards residual error as diagnostie statistics and is liable to misjudge potential ease and gross error. Whereas, F-S test introdueed in the research is founded upon studentized residual and externally studentized to be eapable of distinguishing these two eases effieiently. Thereafter, gross errors will be located and replaeed with the estimations ealeulated by RBF neural network regressing method. Since all gross errors are eorreeted, the sample set is recovered to be taken as training data for the following signal reeonstruetion. Emulation experiments and corresponding analysis indieate that the proposed method is provided with higher robustness. Additionally, the preeise deteetion and aeeurate recovery of gross error remarkably enhanee the signal reeonstruetion of MIMO nonlinear sensor.

关 键 词：非线性传感器 信号重构 粗差定位 F-S检验 RBF神经网络 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置]