Structural damage identification using image-based pattern recognition on event-based binary data generated from self-powered sensor networks

Salehi, Hadi; Das, Saptarshi; Chakrabartty, Shantanu; Biswas, Subir; Burgueño, Rigoberto

doi:10.1002/stc.2135

Cited by 26 publications

(18 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each radio on the sensor node can only be tuned to a specific channel in a time slot. To ensure that the number of channels used by a sensor node at th time slot does not exceed the number of radios, the scheduled links should satisfy the following inequality in Equation 11:…”

Section: Concurrent Transmission Linkmentioning

confidence: 99%

“…Structural health monitoring (SHM) systems are widely deployed in large civil infrastructures (especially for long‐span bridges and high‐rise buildings) to enable health diagnosis and damage detection so as to improve public safety . Most existing SHM systems were implemented based on wired monitoring networks . In recent years, with the fast development of wireless communication technologies, wireless sensors network (WSN) is emerging to replace wired monitoring technologies, because of the superiority in installation, cost, system expansion, and maintenance .…”

Section: Introductionmentioning

confidence: 99%

“…[1][2][3][4][5][6][7][8][9] Most existing SHM systems were implemented based on wired monitoring networks. 10,11 In recent years, with the fast development of wireless communication technologies, wireless sensors network (WSN) is emerging to replace wired monitoring technologies, because of the superiority in installation, cost, system expansion, and maintenance. [12][13][14] In terms of network topology, the SHM-oriented WSNs typically feature a three-dimensional long and narrow chain distribution, which will cause a much more serious network congestion and energy hole problems in contrast to conventional WSNs.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimal data collection of multi-radio multi-channel multi-power wireless sensor networks for structural monitoring applications: A simulation study

Chen

et al. 2019

Struct Control Health Monit

View full text Add to dashboard Cite

Summary Structural health monitoring (SHM) is a kind of data‐intensive applications for wireless sensors network (WSN), which usually requires a high network capacity. However, the bandwidth of traditional single‐radio single‐channel (SR‐SC) WSN is quite limited. In order to meet the requirement of structural monitoring, we investigate the multi‐radio multi‐channel multi‐power (MR‐MC‐MP) communication to improve the data collection performance of SHM‐oriented WSNs in terms of network capacity and power consumption. First, the data collection problem in MR‐MC‐MP WSNs is modeled as an optimization problem under the constraint of available time slots, radios, channels, and power levels. And then, combining the fast convergence of the particle swarm optimization (PSO) algorithm and high exploration performance of flower pollination optimization (FPA) algorithm, we propose a novel binary hybrid meta‐heuristic algorithm named BFPA‐PSO to solve the problem. In order to verify the advantage of the proposed BFPA‐PSO, some other meta‐heuristic algorithms are tested for the problem as well. Finally, several simulation experiments are carried out to test and compare the performance of different algorithms. Experiment results demonstrate that the proposed BFPA‐PSO algorithm has superior performance in terms of network capacity and energy consumption.

show abstract

Section: Concurrent Transmission Linkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimal data collection of multi-radio multi-channel multi-power wireless sensor networks for structural monitoring applications: A simulation study

Chen

et al. 2019

Struct Control Health Monit

View full text Add to dashboard Cite

show abstract

“…The application of ANNs in damage detection provides a new method for SHM. The early application of a back-propagation (BP) neural network has achieved promising results [19,20], but it has some inherent shortcomings, such as a low convergence, being time-consuming, and the over-fitting of data [21,22]. The dimensions of sample data of large structures can be huge, and the training time is not affordable [23].…”

Section: Introductionmentioning

confidence: 99%

Modal Strain Energy-Based Structural Damage Detection Using Convolutional Neural Networks

Chen

Liu

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

In this paper, a convolutional neural network (CNN) was used to extract the damage features of a steel frame structure. As structural damage could induce changes of the modal parameters of the structure, the convolution operation was used to extract the features of modal parameters, and a classification algorithm was used to judge the damage state of the structure. The finite element method was applied to analyze the free vibration of the steel frame and obtain the first-order modal strain energy for various damage scenarios, which was used as the CNN training sample. Then vibration experiments were carried out, and modal parameters were obtained from the modal analysis of the vibration signals. The experimental data were inputted into the CNN to verify its damage detection capability. The result showed that the CNN was effective in detecting the intact structure, single damage, and multi damages with an accuracy of 100%. For comparison, the same samples were also applied to the traditional back propagation (BP) neural network, which failed to detect the intact structure and multiple-damage cases. It was found that: (1) The proposed CNN could be trained from finite element simulation data and used in real frame structure damage detection, and it performed better in structural damage detection than BP neural networks; (2) the measured data of a real structure could be supplemented by numerical simulation data, and satisfactory results have been demonstrated.

show abstract

“…However, the communicated data are in a binary format, resulting in discrete and asynchronous event‐based binary information at the data collection unit, or sink. To tackle the nature of discrete binary data, the authors previously presented an SHM approach based on pattern recognition (PR) assuming full data availability for damage detection in plate‐like structures . PR methods were examined only from the aspect of dealing with binary data.…”

Section: Introductionmentioning

confidence: 99%

Damage identification in aircraft structures with self‐powered sensing technology: A machine learning approach

Salehi

Das

Chakrabartty

et al. 2018

Struct Control Health Monit

Self Cite

View full text Add to dashboard Cite

Progress in self-powered wireless sensor networks for structural health monitoring (SHM) have motivated the development of power-efficient data communication protocols. One such approach is the energy-aware pulse switching architecture, which employs ultrasonic pulses to transmit binary data through the material substrate. However, this technology creates time delays on the generated data due to the power budgets demanded for sensing and communication. The nature of data collected from such protocol thus requires the development of new analysis and interpretation methods. This study presents a robust damage identification strategy for aircraft structures, within the context of data-driven SHM, using discrete time-delayed binary data. A novel machine learning framework integrating low-rank matrix completion, pattern recognition, k-nearest neighbor, and a data fusion model was developed for damage identification. Performance and accuracy of the proposed data-driven SHM strategy was investigated and tested for an aircraft horizontal stabilizer wing.Damage states were simulated on a finite element model by reducing stiffness in a region of the stabilizer's skin. The reliability of the proposed strategy with noise-polluted data was also validated. Further, the effect of variations in harvested energy on the performance of the approach was investigated. Results demonstrate that the developed machine learning framework can effectively detect the presence and location of damage based on time-delayed binary data from a self-powered sensor network. and sensing data becomes a significant concern. Harvesting power from ambient energy was thus introduced to address the problem, and it has attracted significant attention in recent years. Energy harvesting technologies were developed to extend the lifetime of WSNs by addressing the energy constraint problem. 9 Recently, self-powered sensors have become a reality by overcoming the gap between the achievable scavenged energy and the energy required for sensing, computing, and communication, 10,11 thus leading to the emergence of power-efficient WSNs.Recently, the authors have developed an energy-aware through-substrate ultrasonic self-powered sensor network for SHM on the basis of what is termed "pulse switching protocol." 12 The major feature of pulse switching is to minimize the communication energy demand in a sensor network by using a minimal number of pulses to represent the event location and forwarding information. However, the communicated data are in a binary format, resulting in discrete and asynchronous event-based binary information at the data collection unit, or sink. To tackle the nature of discrete binary data, the authors previously presented an SHM approach based on pattern recognition (PR) assuming full data availability for damage detection in plate-like structures. 13-15 PR methods were examined only from the aspect of dealing with binary data. Yet an SHM system employing pulse switching technology requires dealing with power budgets for measuring and communi...

show abstract

Structural damage identification using image-based pattern recognition on event-based binary data generated from self-powered sensor networks

Cited by 26 publications

References 38 publications

Optimal data collection of multi-radio multi-channel multi-power wireless sensor networks for structural monitoring applications: A simulation study

Optimal data collection of multi-radio multi-channel multi-power wireless sensor networks for structural monitoring applications: A simulation study

Modal Strain Energy-Based Structural Damage Detection Using Convolutional Neural Networks

Damage identification in aircraft structures with self‐powered sensing technology: A machine learning approach

Contact Info

Product

Resources

About