Damage identification using the PZT impedance signals and residual learning algorithm

Al-Azzawi, Osama; Wang, Dansheng

doi:10.1007/s13349-021-00505-9

Cited by 19 publications

(6 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other successful applications of CNN models were reported by Ai [ 24 , 25 ], who demonstrated the identification of concurrent compressive stresses and damage (crack number and width), and minor mass loss of a concrete specimen. The application of a deep residual network to the EMI data evaluation for damage, and its potential to overcome the necessity of programmer-dependent preprocessing, was demonstrated by Alazzawi [ 26 ], who managed to directly evaluate time domain impedance data for crack quantification and localization in a steel beam. This potential for the evaluation of electromechanical admittance raw data was also found for a deep neural network by Nguyen [ 27 ], who applied it to the EMI data-based prestress loss monitoring of a post-tensioned reinforced concrete girder, in laboratory conditions.…”

Section: Introductionmentioning

confidence: 99%

Sandwich Face Layer Debonding Detection and Size Estimation by Machine-Learning-Based Evaluation of Electromechanical Impedance Measurements

Kralovec

Lehner

Kirchmayr

et al. 2023

Sensors

View full text Add to dashboard Cite

The present research proposes a two-step physics- and machine-learning(ML)-based electromechanical impedance (EMI) measurement data evaluation approach for sandwich face layer debonding detection and size estimation in structural health monitoring (SHM) applications. As a case example, a circular aluminum sandwich panel with idealized face layer debonding was used. Both the sensor and debonding were located at the center of the sandwich. Synthetic EMI spectra were generated by a finite-element(FE)-based parameter study, and were used for feature engineering and ML model training and development. Calibration of the real-world EMI measurement data was shown to overcome the FE model simplifications, enabling their evaluation by the found synthetic data-based features and models. The data preprocessing and ML models were validated by unseen real-world EMI measurement data collected in a laboratory environment. The best detection and size estimation performances were found for a One-Class Support Vector Machine and a K-Nearest Neighbor model, respectively, which clearly showed reliable identification of relevant debonding sizes. Furthermore, the approach was shown to be robust against unknown artificial disturbances, and outperformed a previous method for debonding size estimation. The data and code used in this study are provided in their entirety, to enhance comprehensibility, and to encourage future research.

show abstract

Section: Introductionmentioning

confidence: 99%

Sandwich Face Layer Debonding Detection and Size Estimation by Machine-Learning-Based Evaluation of Electromechanical Impedance Measurements

Kralovec

Lehner

Kirchmayr

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Impedance signals were collected at various loading levels, and the degree of signal attenuation increase was used as the damage detection index [99]. Alazzawi and Wang presented a weld damage identification method at the joint of a beam using impedance responses and the residual learning algorithm [100].…”

Section: Piezoelectric Active Sensing-based Shm Methods Atmentioning

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

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

“…Therefore, the impedance based method is usually applied for minor defects detection in an early stage, for instance looseness of bolted connection (Nguyen et al, 2017;Li et al, 2020;Na, 2021;Zhou et al, 2021) and interfacial bond damage (Sun et al, 2015;Sun et al, 2017;Deng et al, 2021;Zhu et al, 2022). Furthermore, with the development of artificial intelligence, many studies (Castro et al, 2019;Alazzawi and Wang, 2021;Li et al, 2021;Nguyen et al, 2022;Ai and Cheng, 2023) used machine learning algorithms to cooperate with impedance-based technique, and the capability and accuracy for damage detection and localization are greatly enhanced.…”

Section: Figurementioning

confidence: 99%

Impedance-based damage assessment of steel-ECC composite deck using piezoelectric transducers

Sun

Qin

et al. 2022

Front. Mater.

View full text Add to dashboard Cite

The excellent crack and fatigue resistance of Engineering Cementitious Composites (ECC) materials makes it promising to be used in orthotropic bridge deck system. However, overloading and fatigue load might cause structural damage and, consequently, structural performance degradation. In this work, the piezoelectric lead-zirconate-titanate (PZT) transducers are used to identify the structural damage of the steel-ECC composite deck by implementing both experimental test and numerical simulation. Two steel-ECC composite deck are prepared and four-point bending loading tests are performed on the two specimens to introduce several damage scenarios by gradually increasing the load. The impedance output signals of the piezoelectric sensors are measured under different damage scenarios, and the damage index are extracted to identify the structural damage. A finite element model of the steel-ECC composite deck is established, and the impedance signals with different damage scenarios are calculated and used to assess the structural damages. According to the experimental test and numerical simulation, the impedance-based technology performs to be an effective way to identify the structural damage of the steel-ECC composite deck.

show abstract

Damage identification using the PZT impedance signals and residual learning algorithm

Cited by 19 publications

References 40 publications

Sandwich Face Layer Debonding Detection and Size Estimation by Machine-Learning-Based Evaluation of Electromechanical Impedance Measurements

Sandwich Face Layer Debonding Detection and Size Estimation by Machine-Learning-Based Evaluation of Electromechanical Impedance Measurements

A comprehensive review on health monitoring of joints in steel structures

Impedance-based damage assessment of steel-ECC composite deck using piezoelectric transducers

Contact Info

Product

Resources

About