基于SVM的挠度测量系统自适应修正方法  

Research on Deflection Adaptive Correction Method Based on SVM

作　　者：胡顺仁[1,2] 

机构地区：[1]重庆理工大学电子信息与自动化学院,重庆400054 [2]重庆大学光电技术及系统教育部重点实验室,重庆400044

出　　处：《仪表技术与传感器》2014年第11期96-99,共4页Instrument Technique and Sensor

基　　金：国家科技部863项目(2006AA04Z433);国家科技部重大攻关资助项目(2002BA105C);重庆市科技攻关重大专项(7289);重庆市自然科学基金资助项目(cstc2011jj A40023)

摘　　要：修复和更换桥梁结构健康监测系统传感器会造成监测数据出现前后不一致性问题,影响到整个系统的正常工作。文中以桥梁结构状态监测系统中常用的连通管挠度系统为研究对象,以监测系统中一个重要监测指标——挠度为研究目标,在分析了连通管光电挠度系统工作原理基础上,提出了一种基于支持向量机(SVM)的挠度测量系统自适应修正方法,该方法不仅有效地解决了挠度数据出现的前后不一致性问题,而且还不受温度及工况的限制,其自适应性和精度都得以提高,该方法在重庆市菜园坝长江大桥结构状态监测系统得以成功验证。It leads to inconsistency of monitoring data, and affect the system normal work to repair and change sensors of the bridge structural state monitoring system. This paper regarded the join-hoses photoelectric measurement system as the research object, and deflection as the research goal, and analyzed its principle and all kinds factors of inconsistency of monitoring data. The paper presented an improved method for deflection correction based on Support Vector Machine （SVM） by anglicizing the principle of connected pipe opto-electronic deflection measurement system. In order to avoid calculating the parameters of initial state while using the existing method, is used to calculate the theoretic values of deflection after replaced, and then the deviation of deflection can also be calculated. This method has an adaptive feature and does not have to consider whether the temperature and working condition is similar, and obviously better than the existing method. It has verified the effectiveness of the designed method and theoretical discussions through the bridge structural state monitoring system of the Chongqing CaiYuanBa Yangtze river bridge.

关 键 词：桥梁结构 连通管光电挠度系统 不一致性 自适应修正 支持向量机 

分 类 号：U446.2[建筑科学—桥梁与隧道工程]