A convolutional neural network deep learning method for model class selection
A convolutional neural network deep learning method for model class selection
The response-only model class selection capability of a novel deep convolutional
neural network method is examined herein in a simple, yet effective, manner.
Specifically, the responses from a unique degree of freedom along with their
class information train and validate a one-dimensional convolutional neural network. In doing so, the network selects the model class of new and unlabeled
signals without the need of the system input information, or full system identification. An optional physics-based algorithm enhancement is also examined using the Kalman filter to fuse the system response signals using the kinematics constraints of the acceleration and displacement data. Importantly, the method is shown to select the model class in slight signal variations attributed to the damping behavior or hysteresis behavior on both linear and nonlinear dynamic systems, as well as on a 3D building finite element model, providing a powerful tool for structural health monitoring applications.
Bayesian model selection, Earthquake Engineering, Finite Element Method, Kalman filter, OpenSees, artificial neural networks, bayesian inference, convolutional neural networks, damping, hysteresis, machine learning, model class selection-assessment, parameter estimation, pattern recognition, physics-enhanced deep learning, state estimatation, structural health monitoring, system identification
784-814
Impraimakis, Marios
e8a4540d-2348-4422-9d13-d335b128b02b
February 2024
Impraimakis, Marios
e8a4540d-2348-4422-9d13-d335b128b02b
Impraimakis, Marios
(2024)
A convolutional neural network deep learning method for model class selection.
Earthquake Engineering & Structural Dynamics, 53 (2), .
(doi:10.1002/eqe.4045).
Abstract
The response-only model class selection capability of a novel deep convolutional
neural network method is examined herein in a simple, yet effective, manner.
Specifically, the responses from a unique degree of freedom along with their
class information train and validate a one-dimensional convolutional neural network. In doing so, the network selects the model class of new and unlabeled
signals without the need of the system input information, or full system identification. An optional physics-based algorithm enhancement is also examined using the Kalman filter to fuse the system response signals using the kinematics constraints of the acceleration and displacement data. Importantly, the method is shown to select the model class in slight signal variations attributed to the damping behavior or hysteresis behavior on both linear and nonlinear dynamic systems, as well as on a 3D building finite element model, providing a powerful tool for structural health monitoring applications.
Text
Earthq Engng Struct Dyn - 2023 - Impraimakis - A convolutional neural network deep learning method for model class
- Version of Record
More information
Accepted/In Press date: 10 November 2023
e-pub ahead of print date: 22 November 2023
Published date: February 2024
Additional Information:
Funding Information:
The author would like to gratefully acknowledge the reviewers for their constructive comments, John T. Katsikadelis for the discussion on benchmark integro-differential equation problems, and Andrew W. Smyth for the previous insightful discussions on model class selection and Kalman filtering.
Publisher Copyright:
© 2023 The Authors. Earthquake Engineering & Structural Dynamics published by John Wiley & Sons Ltd.
Keywords:
Bayesian model selection, Earthquake Engineering, Finite Element Method, Kalman filter, OpenSees, artificial neural networks, bayesian inference, convolutional neural networks, damping, hysteresis, machine learning, model class selection-assessment, parameter estimation, pattern recognition, physics-enhanced deep learning, state estimatation, structural health monitoring, system identification
Identifiers
Local EPrints ID: 485130
URI: http://eprints.soton.ac.uk/id/eprint/485130
ISSN: 0098-8847
PURE UUID: 2a30c5b9-4652-4d08-954d-d651f02c5213
Catalogue record
Date deposited: 30 Nov 2023 17:34
Last modified: 17 Mar 2024 06:10
Export record
Altmetrics
Contributors
Author:
Marios Impraimakis
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics