自识别自校准滤波方法  

Self-Recognition Self-Calibration Filtering Methods

作　　者：傅惠民[1] 杨海峰 付越帅 FU Hui-Min;YANG Hai-Feng;FU Yue-Shuai(Research Center of Small Sample Technology,Beihang University,Beijing 100191,China)

机构地区：[1]北京航空航天大学小样本技术研究中心

出　　处：《机电产品开发与创新》2019年第6期8-12,共5页Development & Innovation of Machinery & Electrical Products

基　　金：国家重点基础研究发展计划(2012CB720000);工信部2018年智能制造综合标准化项目《基于数字仿真的机械产品可靠性测试方法标准研究与试验验证》

摘　　要：建立一种能够自动消除系统误差、减小偶然误差的自识别自校准滤波方法,包括量测自校准滤波方法和双未知输入自校准Kalman滤波方法。前者能够解决在线监测、故障诊断、导航与控制等工程领域中量测系统因干扰和噪声而导致的未知输入(系统误差)问题。后者则能够当系统的状态方程和量测方程均含有未知输入时,自动对其未知输入进行识别、估计和补偿,消除系统误差,并通过数据融合减小偶然误差,提高滤波精度。Self-recognition self-calibration filtering methods which can automatically eliminate systematic errors and reduce random errors are established,including measurement self-calibration filtering method and dual unknown inputs self-calibration Kalman filtering method.The former can solve the problem of unknown inputs(systematic errors)caused by interferences and noises in the measurement system in engineering fields such as online monitoring,fault diagnosis,navigation and control.The latter can recognize,estimate and compensate the unknown inputs automatically when the state equations and measurement equations of the system contain them,eliminate the influence of systematic errors,and reduce the random errors by data fusion,so as to improve the filtering accuracy.

关 键 词：在线监测 故障诊断 导航与控制 滤波 自校准 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]