A Review of Machine Learning Algorithms for vibration-based SHM and vision-based SHM

Indhu, R.; Sundar, G. Ram; Parveen, H. Summia

doi:10.1109/icais53314.2022.9742818

Cited by 9 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, powering the wireless sensors using solar energy harvesting realizes a self-contained system, enabling the sustainable sensor networks envisioned by [24]. And by leveraging both real-time on-premises edge processing and cloud machine learning, our solution overcomes the prior constraints around computational costs described in [25,26], demonstrating affordable analytics scaling.…”

Section: A Digital Twin For Shm In Railway Bridgesmentioning

confidence: 99%

“…The article [26] provides a review of machine learning algorithms that have been successfully applied in SHM, specifically in the domains of vision-based and vibrationbased SHM. In this regard, this paper leverages a vibration-based approach.…”

Section: Related Research Summarymentioning

confidence: 99%

“…Secondly, it implements sustainable solar energy harvesting in the full SHM solution, building on the potential shown in [24]. And thirdly, it delivers a hybrid edge-cloud machine learning pipeline to make large-scale analytics financially feasible, addressing the barriers called out in [25,26].…”

Section: A Digital Twin For Shm In Railway Bridgesmentioning

confidence: 99%

See 2 more Smart Citations

Integration of Railway Bridge Structural Health Monitoring into the Internet of Things with a Digital Twin: A Case Study

Armijo,

Zamora-Sánchez

2024

Sensors

View full text Add to dashboard Cite

Structural health monitoring (SHM) is critical for ensuring the safety of infrastructure such as bridges. This article presents a digital twin solution for the SHM of railway bridges using low-cost wireless accelerometers and machine learning (ML). The system architecture combines on-premises edge computing and cloud analytics to enable efficient real-time monitoring and complete storage of relevant time-history datasets. After train crossings, the accelerometers stream raw vibration data, which are processed in the frequency domain and analyzed using machine learning to detect anomalies that indicate potential structural issues. The digital twin approach is demonstrated on an in-service railway bridge for which vibration data were collected over two years under normal operating conditions. By learning allowable ranges for vibration patterns, the digital twin model identifies abnormal spectral peaks that indicate potential changes in structural integrity. The long-term pilot proves that this affordable SHM system can provide automated and real-time warnings of bridge damage and also supports the use of in-house-designed sensors with lower cost and edge computing capabilities such as those used in the demonstration. The successful on-premises–cloud hybrid implementation provides a cost effective and scalable model for expanding monitoring to thousands of railway bridges, democratizing SHM to improve safety by avoiding catastrophic failures.

show abstract

Section: A Digital Twin For Shm In Railway Bridgesmentioning

confidence: 99%

Section: Related Research Summarymentioning

confidence: 99%

See 1 more Smart Citation

Integration of Railway Bridge Structural Health Monitoring into the Internet of Things with a Digital Twin: A Case Study

Armijo,

Zamora-Sánchez

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…But in recent years, with the progress made in the scientific field, the SHM system of bridges has undergone fundamental changes. Advances in technology, such as optical sensors, lasers, image processing systems, and cheap sensors have allowed for advances in SHM system performance [56][57][58][59][60][61]. Also, in recent years, other technologies like blockchain technology and information security, as well as the rise of 5G Internet and the IoT, have made many researchers interested in using these technologies [62][63][64][65][66][67][68].…”

Section: Challenges and Different Sorts Of Shm Systemsmentioning

confidence: 99%

The State of the Art of Artificial Intelligence Approaches and New Technologies in Structural Health Monitoring of Bridges

et al. 2022

View full text Add to dashboard Cite

The challenges of urban administration are growing, as the population, automobiles, and cities rise. Making cities smarter is thus one of the most effective solutions to urban issues. A key feature of the “smart cities” of today is that they use cutting-edge technology in their infrastructure and services. With strategic planning, the smart city utilizes its resources in the most efficient manner. With reduced expenses and enhanced infrastructure, smart cities provide their residents with more and better services. One of these important urban services that can be very helpful in managing cities is structural health monitoring (SHM). By combining leading new technologies like the Internet of Things (IoT) with structural health monitoring, important urban infrastructure can last longer and work better. A thorough examination of recent advances in SHM for infrastructure is thus warranted. Bridges are one of the most important parts of a city’s infrastructure, and their building, development, and proper maintenance are some of the most important aspects of managing a city. The main goal of this study is to look at how artificial intelligence (AI) and some technologies, like drone technology and 3D printers, could be used to improve the current state of the art in SHM systems for bridges, including conceptual frameworks, benefits and problems, and existing methods. An outline of the role AI and other technologies will play in SHM systems of bridges in the future was provided in this study. Some novel technology-aided research opportunities are also highlighted, explained, and discussed.

show abstract

“…Through supervised machine learning and various feature selection techniques, the study identifies minimal sets of univariate features that accurately distinguish between different healthy and damaged states, serving as a valuable benchmark for SHM practitioners and researchers. Further, there are a number of comprehensive review papers in the field of Structural Health Monitoring (SHM) that encapsulate current trends, particularly the application of machine learning/deep learning (ML/DL) in SHM [45][46][47][48][49]. From the above discussion, it is evident that the recent trend in anomaly detection in SHM is the use of machine learning (ML) techniques.…”

Section: Introductionmentioning

confidence: 99%

Anomaly detection in Structural Health Monitoring using spectral distance and t-SNE–GMM framework under ambient excitation

Laha,

Swarnakar,

Kansabanik

2024

Asian J Civ Eng

View full text Add to dashboard Cite

Structural damage detection is crucial for ensuring the safety and reliability of civil infrastructure. In this paper, we propose a novel vibration-based structural damage detection framework using Spectral Distance and a combination of t-Distributed Stochastic Neighbor Embedding (t-SNE) and Gaussian Mixture Model (GMM). By integrating these three procedures, a unique, comprehensive and highly effective approach for detecting structural damage is achieved. First, we extract spectral distance-based features from structural response data under ambient excitations, which provide information about the deviation of the spectral content of the signal from the undamaged structural response. Then, we apply t-SNE to embed the dimensional data into lower dimensional feature space and visualize the data in a low-dimensional space. Finally, we use GMM-based clustering to classify the data into normal and anomalous classes. To evaluate the proposed approach, the experimental data from the Phase II benchmark structural health monitoring problem introduced by the IASC-ASCE Structural Health Monitoring Task Group, is utilized. The results show that our method can effectively detect structural damage anomalies. Moreover, the proposed framework is computationally efficient, making it suitable for real-time structural health monitoring applications. This paper presents novel structural damage indicators (SDI) based on power spectral density deviations between damaged and undamaged structural responses. The study compares the performance of proposed spectral-distance measures and emphasizes the significance of spectral Kullback-Leibler distance as an indicator of structural deterioration. Additionally, the effectiveness of t-SNE-GMM is demonstrated in efficiently segregating damage configurations.

show abstract

A Review of Machine Learning Algorithms for vibration-based SHM and vision-based SHM

Cited by 9 publications

References 18 publications

Integration of Railway Bridge Structural Health Monitoring into the Internet of Things with a Digital Twin: A Case Study

Integration of Railway Bridge Structural Health Monitoring into the Internet of Things with a Digital Twin: A Case Study

The State of the Art of Artificial Intelligence Approaches and New Technologies in Structural Health Monitoring of Bridges

Anomaly detection in Structural Health Monitoring using spectral distance and t-SNE–GMM framework under ambient excitation

Contact Info

Product

Resources

About