Automatic identification of modal parameters for structures based on an uncertainty diagram and a convolutional neural network. (December 2020)

• Record Type: Journal Article
• Authors: Su, Liang; Huang, Xin; Song, Ming-liang; Michael LaFave, James
• Is Part Of: Structures. Volume 28(2021)
• Page Start: 369
• Page End: 379
• Publication Date: 2020-12
• Subjects: Automatic identification -- Uncertainty -- Uncertainty diagram -- Convolutional neural network -- Modal parameters; Structural engineering -- Periodicals; 624.1
• DOI: 10.1016/j.istruc.2020.08.077
• Languages: English
• ISSNs: 2352-0124

Abstract

Abstract: A novel method for automatic identification of structural modal parameters is proposed, based on new developments in both uncertainty quantification for stochastic subspace identification and deep learning. An uncertainty diagram is first constructed to visualize uncertainty estimates, for clearly distinguishing spurious modes. Because the uncertainty of spurious modes is significantly larger than that of the real ones, a convolutional neural network (CNN) is adopted to automatically analyse the uncertainty diagram and efficiently determine the physical structural modes. The method is then applied to identify modal parameters for a six-degree-of-freedom spring–mass model, the Heritage Court Tower building in Canada, and the Ting Kau Bridge in Hong Kong. Results indicate for all three structures that the constructed CNN is effective for analysing the uncertainty diagram and can automatically and accurately obtain the real modes.