A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Guided Wave-Gaussian Mixture Model for Damage Quantification Under Uncertainty
The guided wave (GW) based structural health monitoring method has been a promising method because this method can cover a wide monitoring range and it is sensitive to small damage. However, online damage quantification is difficult as damage initiation and growth are affected by various uncertainties. In addition, various time-varying conditions introduce uncertainty effects on GW features, resulting in a decrease in the accuracy of damage quantification. Therefore, a multi-source feature fusion Gaussian mixture model (MSFF-GMM) is proposed to improve the accuracy of damage quantification. Firstly, MSFF-GMM is constructed by fusing the feature information from multiple channels and multiple specimens under time-varying conditions. Then, the migration index calculated by Kullback-Leibler divergence is used to measure the difference between the GMMs constructed at different damage degrees. Finally, the proposed method is validated for online damage quantification on the typical aircraft lug structure under time-varying dynamic load conditions.
Guided Wave-Gaussian Mixture Model for Damage Quantification Under Uncertainty
The guided wave (GW) based structural health monitoring method has been a promising method because this method can cover a wide monitoring range and it is sensitive to small damage. However, online damage quantification is difficult as damage initiation and growth are affected by various uncertainties. In addition, various time-varying conditions introduce uncertainty effects on GW features, resulting in a decrease in the accuracy of damage quantification. Therefore, a multi-source feature fusion Gaussian mixture model (MSFF-GMM) is proposed to improve the accuracy of damage quantification. Firstly, MSFF-GMM is constructed by fusing the feature information from multiple channels and multiple specimens under time-varying conditions. Then, the migration index calculated by Kullback-Leibler divergence is used to measure the difference between the GMMs constructed at different damage degrees. Finally, the proposed method is validated for online damage quantification on the typical aircraft lug structure under time-varying dynamic load conditions.
Guided Wave-Gaussian Mixture Model for Damage Quantification Under Uncertainty
Lecture Notes in Civil Engineering
Rizzo, Piervincenzo (editor) / Milazzo, Alberto (editor) / Xu, Qiuhui (author) / Yuan, Shenfang (author) / Ren, Yuanqiang (author) / Wang, Jie (author)
European Workshop on Structural Health Monitoring ; 2022 ; Palermo, Italy
2022-06-22
10 pages
Article/Chapter (Book)
Electronic Resource
English
| British Library Conference Proceedings | 2016
| Taylor & Francis Verlag | 2021
Uncertainty Quantification and Model Validation for Damage Prognosis
| British Library Conference Proceedings | 2003