首页> 外国专利> Damage Detection Approach for Tendon of Prestressed Concrete PSC Bridge Based on Auto-Encoder

Damage Detection Approach for Tendon of Prestressed Concrete PSC Bridge Based on Auto-Encoder

机译:基于自动编码器的预应力混凝土预应力混凝土桥筋索损伤检测方法

摘要

The present invention relates to a method for estimating the tendon damage of a PSC bridge using an autoencoder, and the present invention provides acceleration, displacement, strain, etc. representing the small behavior of a PSC bridge that can be obtained through a SHM system in order to grasp the risk of the bridge in real time. A first step of collecting bridge measurement data during a set period so as to estimate the damage of the Tendon using the bridge measurement data of; A second step of generating a tendon damage estimation model capable of restoring only'non-damaged state' data by performing auto-encoder learning by considering the bridge measurement data as'non-damaged state' data; When the bridge measurement data measured in real time from the bridge measurement unit is input, a third step of determining whether or not the bridge tendon is damaged by determining whether it is'non-damaged' data through the Tendon damage estimation model; PSC using an autoencoder including It provides a method for estimating the tendon damage of a bridge.
机译:本发明涉及一种使用自动编码器来估计PSC桥的肌腱损伤的方法,并且本发明提供了代表可以通过SHM系统获得的PSC桥的小行为的加速度,位移,应变等。以便实时掌握桥梁风险。第一步,在设定的时间段内收集桥梁测量数据,以便利用桥梁的测量数据来估算肌腱的损伤;第二步,通过将桥测量数据视为“非损坏状态”数据,进行自动编码器学习,生成能够仅恢复“非损坏状态”数据的肌腱损伤估计模型;当输入来自桥梁测量单元的实时测量的桥梁测量数据时,第三步骤是通过肌腱损伤估计模型确定其是否为“未损伤”数据,从而确定桥梁肌腱是否受损;使用包括在内的自动编码器的PSC提供了一种估计桥梁的肌腱损伤的方法。

著录项

相似文献

  • 专利
  • 外文文献
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