Data-driven machine learning for pattern recognition and detection of loosening torque in bolted joints

Coelho, Jefferson S.; Machado, Marcela R.; Dutkiewicz, Maciej; O. Teloli, Rafael

doi:10.1007/s40430-023-04628-6

Cited by 7 publications

(5 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The equation of motion was employed to quantify changes in higher frequency and damping ratio, serving as the damage identification index [129]. Cohelo et al presented an ML-based SHM technique for the identification of loosening bolts in a beam-based frequency response [130].…”

Section: Global/vibration-based Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A comprehensive review on health monitoring of joints in steel structures

Naresh,

Kumar,

Pal

et al. 2024

Smart Mater. Struct.

View full text Add to dashboard Cite

Steel-framed structures find extensive application in civil engineering projects, including buildings, bridges, and towers, due to their dependable material characteristics, expeditious construction capabilities, and cost-efficiency. In such structures, beams and columns are interconnected through either welding or bolting methods. However, it's imperative to recognize that joints represent the critical areas susceptible to damage stemming from a variety of factors, both human-induced and environmental, in addition to the effects of aging. Over the past few decades, substantial attention has been dedicated to the field of Structural Health Monitoring (SHM) at the joints of steel structures. This study seeks to comprehensively evaluate various methods employed for structural health monitoring at the joints of steel structures, encompassing both bolted and welded connections. While there have been numerous prior review studies that focus on localized and vibration-based techniques for detecting damage at these joints, there is a conspicuous absence of research covering the amalgamation of localized and global approaches across diverse steel structure types. This review paper addresses this gap by offering a thorough examination, incorporating the most recent applications of SHM methodologies employed in research and practical contexts for joint damage detection. Furthermore, it serves as a valuable resource for professionals, engineers, and academics engaged in civil structure design, construction, and maintenance.

show abstract

Section: Global/vibration-based Methodsmentioning

confidence: 99%

“…Histogram of Oriented Gradients features were extracted from the trained images and used with SVM to distinguish between loosened and tightened bolts [231]. Coelho et al presented an SHM method at the joint of a beam using different types of ML algorithms [130].…”

Section: Machine Learning (Ml) and Deep Learning (Dl) Based Methodsmentioning

confidence: 99%

A comprehensive review on health monitoring of joints in steel structures

Naresh,

Kumar,

Pal

et al. 2024

Smart Mater. Struct.

View full text Add to dashboard Cite

show abstract

“…Xin 21 highlighted the application prospect of new technology in sports analysis and provides a new idea for improving the automatic recognition of basketball sports behavior. Coelho et al 22 emphasized the application of machine learning in materials science and engineering, which provided feasibility for real-time monitoring of sports behavior. Wang et al 23 emphasized the prospect of combining optical sensing technology with machine learning in sports behavior monitoring.…”

Section: Literature Reviewmentioning

confidence: 99%

Boxing behavior recognition based on artificial intelligence convolutional neural network with sports psychology assistant

Kong,

Duan

2024

Sci Rep

View full text Add to dashboard Cite

The purpose of this study is to deeply understand the psychological state of boxers before the competition, and explore an efficient boxing action classification and recognition model supported by artificial intelligence (AI) technology through these psychological characteristics. Firstly, this study systematically measures the key psychological dimensions of boxers, such as anxiety level, self-confidence, team identity, and opponent attitude, through psychological scale survey to obtain detailed psychological data. Then, based on these data, this study innovatively constructs a boxing action classification and recognition model based on BERT fusion 3D-ResNet, which not only comprehensively considers psychological information, but also carefully considers action characteristics to improve the classification accuracy of boxing actions. The performance evaluation shows that the model proposed in this study is significantly superior to the traditional model in terms of loss value, accuracy and F1 value, and the accuracy reaches 96.86%. Therefore, through the comprehensive application of psychology and deep learning, this study successfully constructs a boxing action classification and recognition model that can fully understand the psychological state of boxers, which provides strong support for the psychological training and action classification of boxers.

show abstract

“…Additionally, the inherent variabilities and uncertainties within the system further compound the complexity of the structural health monitoring process [ 5 , 6 ]. To overcome certain monitoring processes, the present dataset has been acquired to support and evaluate the methodologies proposed in [ 1 , 3 , 4 ] and structural health monitoring techniques based on vibration signature. Methodologies that integrate vibration physics-based models and data-driven involve preprocessing and feature selection of the dataset inputs to facilitate the training and validation that will benefit from these datasets.…”

Section: Introductionmentioning

confidence: 99%

Experimental vibration dataset collected of a beam reinforced with masses under different health conditions

de Sousa,

Machado

2024

Data in Brief

Self Cite

View full text Add to dashboard Cite

Data-driven machine learning for pattern recognition and detection of loosening torque in bolted joints

Cited by 7 publications

References 55 publications

A comprehensive review on health monitoring of joints in steel structures

A comprehensive review on health monitoring of joints in steel structures

Boxing behavior recognition based on artificial intelligence convolutional neural network with sports psychology assistant

Experimental vibration dataset collected of a beam reinforced with masses under different health conditions

Contact Info

Product

Resources

About