A novel approach to crack refinement measurement under impact loading based on OFDR technique DOI
Yongliang Li, Liyun Yang, Jie Zuo

и другие.

Measurement Science and Technology, Год журнала: 2025, Номер 36(3), С. 035213 - 035213

Опубликована: Фев. 24, 2025

Abstract The dynamic crack propagation characteristics of brittle materials are a crucial focus in impact dynamics. randomness growth under loading poses significant challenges to accurately monitoring behavior during experiments. In this study, two novel refinement measurement techniques based on optical frequency domain reflectometry technology were developed provide more comprehensive strain distribution data and capture detailed behavior. Additionally, trending algorithm was introduced process large datasets pinpoint locations. study begins by presenting the innovative deployment methods fabrication custom specimens. After conducting tests specimens, resulting compared with actual propagation. results demonstrated precise location identification down millimeter level, extension path mapped using profiles from fiber-optic measurements. These findings validate effectiveness proposed approach, which shows great potential for monitoring, locating, quantifying cracks distributed fibers.

Язык: Английский

Intelligent monitoring of spatially-distributed cracks using distributed fiber optic sensors assisted by deep learning DOI
Yiming Liu, Yi Bao

Measurement, Год журнала: 2023, Номер 220, С. 113418 - 113418

Опубликована: Авг. 6, 2023

Язык: Английский

Процитировано

73

A Machine Learning Approach to Credit Card Customer Segmentation for Economic Stability DOI Open Access
Yujuan Qiu, Jian-Xiong Wang

Опубликована: Янв. 1, 2024

Credit card usage is a vital component of the global economy, but unpredictable customer behavior poses significant challenges. Machine learning (ML) has emerged as powerful tool for segmentation in credit industry. This paper systematically examines different clustering algorith

Язык: Английский

Процитировано

45

Developing an integrative framework for digital twin applications in the building construction industry: A systematic literature review DOI
Wuyan Long, Zhikang Bao, Ke Chen

и другие.

Advanced Engineering Informatics, Год журнала: 2024, Номер 59, С. 102346 - 102346

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

39

Machine learning-assisted intelligent interpretation of distributed fiber optic sensor data for automated monitoring of pipeline corrosion DOI
Yiming Liu, Xiao Tan, Yi Bao

и другие.

Measurement, Год журнала: 2024, Номер 226, С. 114190 - 114190

Опубликована: Янв. 19, 2024

Язык: Английский

Процитировано

34

Monitoring of pipelines subjected to interactive bending and dent using distributed fiber optic sensors DOI Creative Commons
Xiao Tan, Sina Poorghasem, Ying Huang

и другие.

Automation in Construction, Год журнала: 2024, Номер 160, С. 105306 - 105306

Опубликована: Фев. 3, 2024

Язык: Английский

Процитировано

33

A deep learning-based approach with anti-noise ability for identification of rock microcracks using distributed fibre optic sensing data DOI
Shuai Zhao, Dao-Yuan Tan,

Shaoqun Lin

и другие.

International Journal of Rock Mechanics and Mining Sciences, Год журнала: 2023, Номер 170, С. 105525 - 105525

Опубликована: Июль 6, 2023

Язык: Английский

Процитировано

28

Machine Learning Applications in Optical Fiber Sensing: A Research Agenda DOI Creative Commons
Erick Reyes-Vera, Alejandro Valencia-Arías, Vanessa García Pineda

и другие.

Sensors, Год журнала: 2024, Номер 24(7), С. 2200 - 2200

Опубликована: Март 29, 2024

The constant monitoring and control of various health, infrastructure, natural factors have led to the design development technological devices in a wide range fields. This has resulted creation different types sensors that can be used monitor environments, such as fire, water, temperature, movement, among others. These detect anomalies input data system, allowing alerts generated for early risk detection. advancement artificial intelligence improved sensor systems networks, resulting with better performance more precise results by incorporating features. aim this work is conduct bibliometric analysis using PRISMA 2020 set identify research trends machine learning applications fiber optic sensors. methodology facilitates dataset comprised documents obtained from Scopus Web Science databases. It enables evaluation both quantity quality publications study area based on specific criteria, trends, key concepts, advances concepts over time. found deep techniques Bragg gratings been extensively researched focus structural health future research. One main limitations lack use novel materials, graphite, designing presents an opportunity studies.

Язык: Английский

Процитировано

16

Boosted dipper throated optimization algorithm-based Xception neural network for skin cancer diagnosis: An optimal approach DOI Creative Commons

Xiaofei Tang,

Fatima Rashid Sheykhahmad

Heliyon, Год журнала: 2024, Номер 10(5), С. e26415 - e26415

Опубликована: Фев. 18, 2024

Skin cancer is a prevalent form of that necessitates prompt and precise detection. However, current diagnostic methods for skin are either invasive, time-consuming, or unreliable. Consequently, there demand an innovative efficient approach to diagnose utilizes non-invasive automated techniques. In this study, unique method has been proposed diagnosing by employing Xception neural network optimized using Boosted Dipper Throated Optimization (BDTO) algorithm. The deep learning model capable extracting high-level features from dermoscopy images, while the BDTO algorithm bio-inspired optimization technique can determine optimal parameters weights network. To enhance quality diversity ISIC dataset utilized, widely accepted benchmark system diagnosis, various image preprocessing data augmentation techniques were implemented. By comparing with several contemporary approaches, it demonstrated outperforms others in detecting cancer. achieves average precision 94.936%, accuracy 94.206%, recall 97.092% surpassing performance alternative methods. Additionally, 5-fold ROC curve error have presented validation showcase superiority robustness method.

Язык: Английский

Процитировано

10

Applications of machine learning methods for design and characterization of high-performance fiber-reinforced cementitious composite (HPFRCC): a review DOI
Pengwei Guo, Seyed Amirhossein Moghaddas, Yiming Liu

и другие.

Journal of Sustainable Cement-Based Materials, Год журнала: 2025, Номер unknown, С. 1 - 24

Опубликована: Фев. 6, 2025

Язык: Английский

Процитировано

2

Scour assessment for offshore wind turbines: a state-of-the-art review DOI
Xin Feng, Jinhui Zheng, Yiming Liu

и другие.

Journal of Civil Structural Health Monitoring, Год журнала: 2025, Номер unknown

Опубликована: Апрель 11, 2025

Язык: Английский

Процитировано

2