Intelligent transportation systems (ITS) collect traffic data from various sensors deployed in smart cities. Yet, such information that are ubiquitous in real-world transportation systems mainly suffer from irregular spatial and temporal resolution. Consequently, missing and incomplete traffic data are inevitable as a result of detector and communication malfunctions when collecting information from ITS. Reconstructing missing values is then of great importance yet challenging due to difficulties in capturing spatiotemporal traffic patterns. This paper presents a transportation data reconstruction/imputation model that leverages Bayesian inference and tensor decomposition/completion to effectively address the missing data problem. On this basis, Bayesian tensor train (TT) decomposition is incorporated with Markov chain Monte Carlo Gibbs sampler to learn parameters of the model. Results of the experiments indicate that the proposed Bayesian TT model can effectively impute missing traffic data with acceptable accuracy.
This study presents a novel methodology for structural health monitoring (SHM), using a self-powered sensing concept, within the context of machine learning (ML) and pattern recognition (PR). The proposed method is based on the interpretation of data provided by a self-powered discrete analog wireless sensor used to measure the structural response along with an energy-efficient pulse switching technology employed for data communication. A system using such an energy-aware sensing technology demands dealing with power budgets for sensing and communication of binary data, resulting in missing and incomplete data received at the SHM processor. Numerical studies were conducted on an aircraft wing stabilizer subjected to dynamic loading to evaluate and verify the performance of the proposed methodology. Damage was simulated on a finite element model by decreasing stiffness in a region of the stabilizer’s skin. Several features, i.e., patterns or images, were extracted from the strain response of the stabilizer. The obtained features were fed into a ML methodology incorporating low-rank matrix decomposition and PR for damage diagnosis of the wing. Different ML algorithms, including support vector machine, k-nearest neighbor, and artificial neural networks, were integrated within the learning methodology to assess the performance of the damage detection approach. Different levels of harvested energy were also considered to evaluate the robustness of the damage detection method with respect to such variations. Further, reliability of the proposed methodology was evaluated through an uncertainty analysis. Results demonstrate that the developed SHM methodology employing ML is efficient in detecting damage from a novel self-powered sensor network, even with noisy and incomplete binary data.
This study proposes a novel strategy for damage identification in aircraft structures. The strategy was evaluated based on the simulation of the binary data generated from self-powered wireless sensors employing a pulse switching architecture. The energy-aware pulse switching communication protocol uses single pulses instead of multi-bit packets for information delivery resulting in discrete binary data. A system employing this energy-efficient technology requires dealing with time-delayed binary data due to the management of power budgets for sensing and communication. This paper presents an intelligent machine-learning framework based on combination of the low-rank matrix decomposition and pattern recognition (PR) methods. Further, data fusion is employed as part of the machine-learning framework to take into account the effect of data time delay on its interpretation. Simulated time-delayed binary data from self-powered sensors was used to determine damage indicator variables. Performance and accuracy of the damage detection strategy was examined and tested for the case of an aircraft horizontal stabilizer. Damage states were simulated on a finite element model by reducing stiffness in a region of the stabilizer’s skin. The proposed strategy shows satisfactory performance to identify the presence and location of the damage, even with noisy and incomplete data. It is concluded that PR is a promising machine-learning algorithm for damage detection for time-delayed binary data from novel self-powered wireless sensors.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.