Real-time state estimation using recurrent neural network and topological data analysis

dc.contributor.author Razmarashooli, Arman
dc.contributor.author Martinez, Daniel A. Salazar
dc.contributor.author Chua, Yang Kang
dc.contributor.author Laflamme, Simon
dc.contributor.author Hu, Chao
dc.contributor.department Civil, Construction and Environmental Engineering
dc.contributor.department Electrical and Computer Engineering
dc.date.accessioned 2024-05-31T13:55:51Z
dc.date.available 2024-05-31T13:55:51Z
dc.date.issued 2024-05-09
dc.description.abstract High-rate systems are defined as physical systems that undergo large perturbations, often exceeding 100 g’s, over very short durations, often less than 100 milliseconds. Examples include blast mitigation mechanisms and advanced weaponry. The use of control feedback to empower high-rate systems requires the capability to estimate system states of interest in the realm of microseconds. However, due to the dynamics of these high-rate systems being highly nonlinear and nonstationary, it is challenging to predict their behavior using conventional state estimation methods. To address this issue, we conduct a study that explores the integration of topological data analysis (TDA) and recurrent neural network (RNN) to improve predictive capabilities for high-rate systems. Here, TDA features are used as the input to a machine learning algorithm to determine the state of a high-rate system. We conduct practical evaluations using laboratory datasets from experiments in the dynamic reproduction of projectiles in ballistic environments for advanced research (DROPBEAR), focusing on localizing fast-changing boundary conditions on a cantilever beam. The study demonstrates the ability of the method to classify and predict a system’s fundamental frequencies. This approach helps understand the structure of the underlying high-rate dynamics, leading to improved accuracy and precision in state estimation and prediction.
dc.description.comments This proceeding is published as Razmarashooli, Arman, Daniel A. Salazar Martinez, Yang Kang Chua, Simon Laflamme, and Chao Hu. "Real-time state estimation using recurrent neural network and topological data analysis." In Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, Civil Infrastructure, and Transportation XVIII, vol. 12950, pp. 106-114. SPIE, 2024. doi: https://doi.org/10.1117/12.3010900. © 2024 SPIE. Posted with Permission.
dc.identifier.uri https://dr.lib.iastate.edu/handle/20.500.12876/VrO5menw
dc.language.iso en
dc.publisher Society of Photographic Instrumentation Engineers (SPIE)
dc.source.uri https://doi.org/10.1117/12.3010900 *
dc.subject.disciplines DegreeDisciplines::Engineering::Electrical and Computer Engineering::Systems and Communications
dc.subject.disciplines DegreeDisciplines::Physical Sciences and Mathematics::Computer Sciences
dc.subject.disciplines DegreeDisciplines::Physical Sciences and Mathematics::Computer Sciences::Theory and Algorithms
dc.subject.keywords Structural health monitoring
dc.subject.keywords High-rate systems
dc.subject.keywords Nonlinear time series
dc.subject.keywords Topological data analysis
dc.subject.keywords Recurrent neural network
dc.subject.keywords Ensemble learning
dc.title Real-time state estimation using recurrent neural network and topological data analysis
dc.type Presentation
dspace.entity.type Publication
relation.isAuthorOfPublication 84547f08-8710-4934-b91e-ba5f46ab9abe
relation.isOrgUnitOfPublication 933e9c94-323c-4da9-9e8e-861692825f91
relation.isOrgUnitOfPublication a75a044c-d11e-44cd-af4f-dab1d83339ff
File
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
2024-Laflamme-RealTimeState.pdf
Size:
3.44 MB
Format:
Adobe Portable Document Format
Description: