Machine Learning-Based Structural Health Monitoring Technique for Crack Detection and Localisation Using Bluetooth Strain Gauge Sensor Network (2025)

Shah Mansouri, T., Lubarsky, G., Finlay, D. (2024). Machine Learning-Based Structural Health Monitoring Technique for Crack Detection and Localisation Using Bluetooth Strain Gauge Sensor Network. Journal of Sensor and Actuator Networks, 13(6), 1-16. Article 79. Advance online publication. https://doi.org/10.3390/jsan13060079

Shah Mansouri, Tahereh ; Lubarsky, Gennady ; Finlay, Dewar et al. / Machine Learning-Based Structural Health Monitoring Technique for Crack Detection and Localisation Using Bluetooth Strain Gauge Sensor Network. In: Journal of Sensor and Actuator Networks. 2024 ; Vol. 13, No. 6. pp. 1-16.

@article{1304b13250744136b5b5093883630804,

title = "Machine Learning-Based Structural Health Monitoring Technique for Crack Detection and Localisation Using Bluetooth Strain Gauge Sensor Network",

abstract = "Within the domain of Structural Health Monitoring (SHM), conventional approaches generally are complicated, destructive, and time-consuming. It also necessitates an extensive array of sensors to effectively evaluate and monitor the structural integrity. In this research work, we present a novel, non-destructive SHM framework based on machine learning (ML) for the accurate detection and localisation of structural cracks. This approach leverages a minimal number of strain gauge sensors linked via Bluetooth Low Energy (BLE) communication. The framework is validated through empirical data collected from 3D carbon fibre-reinforced composites, including three distinct specimens, ranging from crack-free samples to specimens with up to ten cracks of varying lengths and depths. The methodology integrates an analytical examination of the Shewhart chart, Grubbs{\textquoteright} test (GT), and hierarchical clustering (HC) algorithm, tailored towards the metrics of fracture measurement and classification. Our novel ML framework allows one to replace exhausting laboratory procedures with a modern and quick mechanism for the material, with unprecedented properties that could provide potential applications in the composites industry.",

keywords = "structural health monitoring, machine learning, BLE senor, shewhart chart, Grubb's test, hierarchical clustering, 3D composite",

author = "{Shah Mansouri}, Tahereh and Gennady Lubarsky and Dewar Finlay and James McLaughlin",

year = "2024",

month = nov,

day = "23",

doi = "10.3390/jsan13060079",

language = "English",

volume = "13",

pages = "1--16",

journal = "Journal of Sensor and Actuator Networks",

issn = "2224-2708",

publisher = "MDPI",

number = "6",

}

Shah Mansouri, T, Lubarsky, G, Finlay, D 2024, 'Machine Learning-Based Structural Health Monitoring Technique for Crack Detection and Localisation Using Bluetooth Strain Gauge Sensor Network', Journal of Sensor and Actuator Networks, vol. 13, no. 6, 79, pp. 1-16. https://doi.org/10.3390/jsan13060079

Machine Learning-Based Structural Health Monitoring Technique for Crack Detection and Localisation Using Bluetooth Strain Gauge Sensor Network. / Shah Mansouri, Tahereh; Lubarsky, Gennady; Finlay, Dewar et al.
In: Journal of Sensor and Actuator Networks, Vol. 13, No. 6, 79, 31.12.2024, p. 1-16.

Research output: Contribution to journal › Article › peer-review

TY - JOUR

T1 - Machine Learning-Based Structural Health Monitoring Technique for Crack Detection and Localisation Using Bluetooth Strain Gauge Sensor Network

AU - Shah Mansouri, Tahereh

AU - Lubarsky, Gennady

AU - Finlay, Dewar

AU - McLaughlin, James

PY - 2024/11/23

Y1 - 2024/11/23

N2 - Within the domain of Structural Health Monitoring (SHM), conventional approaches generally are complicated, destructive, and time-consuming. It also necessitates an extensive array of sensors to effectively evaluate and monitor the structural integrity. In this research work, we present a novel, non-destructive SHM framework based on machine learning (ML) for the accurate detection and localisation of structural cracks. This approach leverages a minimal number of strain gauge sensors linked via Bluetooth Low Energy (BLE) communication. The framework is validated through empirical data collected from 3D carbon fibre-reinforced composites, including three distinct specimens, ranging from crack-free samples to specimens with up to ten cracks of varying lengths and depths. The methodology integrates an analytical examination of the Shewhart chart, Grubbs’ test (GT), and hierarchical clustering (HC) algorithm, tailored towards the metrics of fracture measurement and classification. Our novel ML framework allows one to replace exhausting laboratory procedures with a modern and quick mechanism for the material, with unprecedented properties that could provide potential applications in the composites industry.

AB - Within the domain of Structural Health Monitoring (SHM), conventional approaches generally are complicated, destructive, and time-consuming. It also necessitates an extensive array of sensors to effectively evaluate and monitor the structural integrity. In this research work, we present a novel, non-destructive SHM framework based on machine learning (ML) for the accurate detection and localisation of structural cracks. This approach leverages a minimal number of strain gauge sensors linked via Bluetooth Low Energy (BLE) communication. The framework is validated through empirical data collected from 3D carbon fibre-reinforced composites, including three distinct specimens, ranging from crack-free samples to specimens with up to ten cracks of varying lengths and depths. The methodology integrates an analytical examination of the Shewhart chart, Grubbs’ test (GT), and hierarchical clustering (HC) algorithm, tailored towards the metrics of fracture measurement and classification. Our novel ML framework allows one to replace exhausting laboratory procedures with a modern and quick mechanism for the material, with unprecedented properties that could provide potential applications in the composites industry.

KW - structural health monitoring

KW - machine learning

KW - BLE senor

KW - shewhart chart

KW - Grubb's test

KW - hierarchical clustering

KW - 3D composite

U2 - 10.3390/jsan13060079

DO - 10.3390/jsan13060079

M3 - Article

SN - 2224-2708

VL - 13

SP - 1

EP - 16

JO - Journal of Sensor and Actuator Networks

JF - Journal of Sensor and Actuator Networks

IS - 6

M1 - 79

ER -

Shah Mansouri T, Lubarsky G, Finlay D, McLaughlin J. Machine Learning-Based Structural Health Monitoring Technique for Crack Detection and Localisation Using Bluetooth Strain Gauge Sensor Network. Journal of Sensor and Actuator Networks. 2024 Dec 31;13(6):1-16. 79. Epub 2024 Nov 23. doi: 10.3390/jsan13060079