首页> 外国专利> A METHOD FOR NOVEL HEALTH MONITORING SCHEME FOR SMART CONCRETE STRUCTURES

A METHOD FOR NOVEL HEALTH MONITORING SCHEME FOR SMART CONCRETE STRUCTURES

机译:一种新型混凝土结构健康监测方案的方法

摘要

The present invention relates to a method for monitoring the health of a smart concrete structure. The method comprises: a first step of receiving data from a sensor of a smart concrete structure provided with an MR damper; a second step of applying discrete wavelet decomposition to the data received from the sensor; a third step of applying an automatic regression model to the data to which the wavelet decomposition is applied, to generate a wavelet-based automatic regression model; a fourth step of checking an average square root error to measure the difference between a value estimated by the wavelet-based automatic regression model and a value of the data; a fifth step of extracting damage sensitive features (DSF); a sixth step of classifying the DSF; a seventh step of evaluating the data classified in the sixth step (S106) by using a multi-class nonlinear relevance vector machine (MNRVM); an eighth step of returning to the second step when an error value is larger than a tolerance value, or performing the next step when the error value is smaller than the tolerance value; and a ninth step of inspecting data validity.
机译:用于监测智能混凝土结构健康的方法技术领域本发明涉及一种用于监测智能混凝土结构健康的方法。该方法包括:第一步,从设有MR阻尼器的智能混凝土结构的传感器接收数据;第二步,将离散小波分解应用于从传感器接收的数据;第三步,对应用了小波分解的数据应用自动回归模型,以生成基于小波的自动回归模型;第四步,检查均方根误差,以测量基于小波的自动回归模型估计的值与数据值之间的差;提取损伤敏感特征(DSF)的第五步;对DSF进行分类的第六步;第七步骤,通过使用多类非线性相关向量机(MNRVM),对在第六步骤(S106)中分类的数据进行评估;第八步骤,当误差值大于公差值时,返回第二步骤,或者当误差值小于公差值时,进行下一步;检验数据有效性的第九步。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号