SHM system for anomaly detection of bolted joints in engineering structures

Ziaja, Dominika; Nazarko, Piotr

doi:10.1016/j.istruc.2021.06.086

Cited by 20 publications

(12 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The whole specimen is examined for precise indication of the damage, but further image analysis is made, omitting the regions where the PZT sensors are glued. ANN is one of the soft computing methods and is widely implemented in solving different problems like the prediction of material/component properties [37], optimization of the manufacturing process [46], as well anomaly [47], and damage detection [48]. The presented concept assumes the use of ANN for approximation of the 2nd derivatives distribution function.…”

Section: Damage Verification Using Ann-irt Resultsmentioning

confidence: 99%

A global-local damage localization and quantification approach in composite structures using ultrasonic guided waves and active infrared thermography

Balasubramaniam

Sikdar

Ziaja

et al. 2023

Smart Mater. Struct.

Self Cite

View full text Add to dashboard Cite

The paper emphasizes fast and effective quantification of hidden damages in composite structures using ultrasonic guided wave (GW) propagation based structural health monitoring (SHM) and an artificial neural network (ANN) based industrial standard infrared thermography (IRT) analysis. At the damage identification stage, a patch region is created based on the mean absolute error signal path analysis. A GW signal difference coefficient-based damage detection algorithm is applied to localize the targeted patch region's damage using an improved wavelet transform coefficient algorithm. A new pixel-threshold-based confusion matrix is implemented to study the size of the different damages. Nondestructive testing (NDT) with IRT is used to verify the damages using a newly developed ANN imaging scheme. From the SHM methodology, it is realized that only three sensors are sufficient to localize the damage, and an ANN- IRT imaging algorithm with only five hidden neurons is found to be effective in quantifying the damage. The robust SHM methods effectively identified, localized, and quantified the different damage dimensions against the NDT-IRT method in different composite structures.

show abstract

Section: Damage Verification Using Ann-irt Resultsmentioning

confidence: 99%

A global-local damage localization and quantification approach in composite structures using ultrasonic guided waves and active infrared thermography

Balasubramaniam

Sikdar

Ziaja

et al. 2023

Smart Mater. Struct.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The ANNs were trained and testing according to the Levenberg–Marquardt algorithm using the approach described in [ 26 ]. The determination of the slab condition (class of the structure) was made by a set of ANNs, not a single network.…”

Section: Resultsmentioning

confidence: 99%

“…Shallow artificial neural networks, which have been previously trained, classify the specimen’s condition. ANNs have often been applied in this type of task, enabling automation of the damage-detection process [ 24 , 25 , 26 , 27 , 28 , 29 ]. For a properly trained tool, the presence of a specialist during results analysis is not necessary.…”

Section: Introductionmentioning

confidence: 99%

Elastic Wave Application for Damage Detection in Concrete Slab with GFRP Reinforcement

2022

Self Cite

View full text Add to dashboard Cite

The aim of the presented examination is condition-monitoring of GFRP-reinforced concrete structural members using elastic wave propagation. As an example, a deck slab is selected. The deck slab is made of concrete of the targeted C30/37 class under three-point bending. During loading cycles, the specimen is observed with a digital image correlation (DIC) system, which enables calculation of the strain field. The measuring setup consists of two Baumer 12.3 Mpx cameras with VS-1220HV lenses, combined in a Q400 system by Dantec Dynamics GmbH. Elastic waves are also measured based on signals recorded with PZT (lead–zirconate–titanate) sensors. Additionally, the typical crack-opening measurements are made. The appearance of a crack and its growth causes changes in both the shape and amplitude of the registered signals. However, the changes are not obvious and depend on the location of the sensors. Due to the impossibility of determining simple parameters with respect to disturbingly wide cracks, for damage detection, an artificial neural network (ANN) is applied. Perfect determination of the specimen’s condition (100% properly classified patterns) is possible based on whether the element is under loading or not.

show abstract

“…They concluded that the BPNN model, in conjunction with the EMI approach, can accurately predict the status of the joint. Ziaja and Nazarko 143 employed a three-step procedure to detect anomalies in a steel frame. In the first step, they excited the structure at different locations using PZT transducers and collected the response signals using sensors.…”

Section: Overview Of ML Methods For Bolt Looseness Detectionmentioning

confidence: 99%

Review on recent advances in structural health monitoring paradigm for looseness detection in bolted assemblies

Chelimilla

Chinthapenta

Kali

et al. 2023

Structural Health Monitoring

View full text Add to dashboard Cite

The integrity of bolted joints is still a challenging problem owing to the gross or localized slip at the interfacial surfaces of the joints when subjected to external disturbances such as vibrations. This slip escalates the interfacial movement and, thus, leads to a decrease in preload levels, that is, looseness of the bolted assemblies. In the last decade, modal analysis, wave propagation, and percussion methods were traditionally used to detect looseness in bolted connections. With an increase in computational power, machine learning algorithms such as neural networks, random forests, decision trees, and support vector machines complemented the traditional methods in accurate looseness estimation. Subsequently, this integration paved the path for real-time health monitoring of bolted joints. This paper summarizes recent investigations on looseness detection in bolted assemblies based on traditional methods and machine learning algorithms. The working principle, advantages, challenges, and applications of the aforementioned methods are also detailed in this paper. Apart from these investigations, the latest studies on the Internet of Things-based health monitoring of structures are also reviewed to explore their adaptability in remote monitoring of bolted connections for damage detection in the future.

show abstract

SHM system for anomaly detection of bolted joints in engineering structures

Cited by 20 publications

References 24 publications

A global-local damage localization and quantification approach in composite structures using ultrasonic guided waves and active infrared thermography

A global-local damage localization and quantification approach in composite structures using ultrasonic guided waves and active infrared thermography

Elastic Wave Application for Damage Detection in Concrete Slab with GFRP Reinforcement

Review on recent advances in structural health monitoring paradigm for looseness detection in bolted assemblies

Contact Info

Product

Resources

About