Improving autoencoder-based unsupervised damage detection in uncontrolled structural health monitoring under noisy conditions

作     者：Yang Kang Wang Linyuan Gao Chao Chen Mozhi Tian Zhihui Zhou Dunzhi Liu Yang 杨抗;王淋元;高超;陈默之;周敦之;刘洋

作者机构：Department of Electrical and Computer EngineeringUniversity of FloridaGainesville 32611USA Department of Electrical and Computer EngineeringTemple UniversityPhiladelphia 19122USA School of Precision Instrument and Opto-Electronics EngineeringTianjin UniversityTianjin 300072China 

基　　金：National Science Foundation of Zhejiang under Contract(LY23E010001) 

出 版 物：《仪器仪表学报》 (Chinese Journal of Scientific Instrument)

年 卷 期：2024年第45卷第6期

页      码：91-100页

摘      要：Structural health monitoring is widely utilized in outdoor environments,especially under harsh conditions,which can introduce noise into the monitoring ***,designing an effective denoising strategy to enhance the performance of guided wave damage detection in noisy environments is *** paper introduces a local temporal principal component analysis(PCA)reconstruction approach for denoising guided waves prior to implementing unsupervised damage detection,achieved through novel autoencoder-based *** results demonstrate that the proposed denoising method significantly enhances damage detection performance when guided waves are contaminated by noise,with SNR values ranging from 10 to-5 *** the implementation of the proposed denoising approach,the AUC score can elevate from 0.65 to 0.96 when dealing with guided waves corrputed by noise at a level of-5 ***,the paper provides guidance on selecting the appropriate number of components used in the denoising PCA reconstruction,aiding in the optimization of the damage detection in noisy conditions.

主 题 词：structural health monitoring guided waves principal component analysis deep learning denoising dynamic environmental condition 

学科分类：12[管理学] 083002[083002] 1204[管理学-公共管理类] 0830[工学-生物工程类] 120402[120402] 08[工学] 080401[080401] 0804[工学-材料学] 0837[0837] 081102[081102] 0811[工学-水利类] 

核心收录：

D　O　I：10.19650/j.cnki.cjsi.J2412555

馆 藏 号：203144036...