Damage detection technique using ultrasonic guided waves and outlier detection: Application to interface delamination diagnosis of integrated circuit package

Lee, Hyunseong; Koo, Bonsung; Chattopadhyay, Aditi; Neerukatti, Rajesh Kumar; Liu, Kuang C.

doi:10.1016/j.ymssp.2021.107884

Cited by 15 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This research will help to improve molecular sensing technologies based on SERS, enabling sensitive and targeted detection in biomedical diagnostics, environmental monitoring, and food safety. 26,81–97…”

Section: Introductionmentioning

confidence: 99%

Polyacrylonitrile as a versatile matrix for gold nanoparticle-based SERS substrates

Sharma,

Kumar,

Yadav

2024

Nanoscale Adv.

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Polyacrylonitrile as a versatile matrix for gold nanoparticle-based SERS substrates

Sharma,

Kumar,

Yadav

2024

Nanoscale Adv.

View full text Add to dashboard Cite

show abstract

“…Another non-destructive testing method that can be used to identify and track the development of delamination in sandwich constructions is Ultrasonic Testing (UT) [19][20][21]. UT includes penetrating the material using high-frequency sound waves to look for delamination [22][23][24].…”

Section: Introductionmentioning

confidence: 99%

“…UT includes penetrating the material using high-frequency sound waves to look for delamination [22][23][24]. UT has the benefit of being able to spot delamination growth in materials that aren't evident from the surface [19]. The depth and size of delamination growth can also be estimated using it.…”

Section: Introductionmentioning

confidence: 99%

Deep learning-based prediction of delamination growth in composite structures: bayesian optimization and hyperparameter refinement

Demircioğlu,

Bakır

2023

Phys. Scr.

View full text Add to dashboard Cite

In this study, a novel method for detecting the growth of delamination in sandwich structures has been proposed. To this end, we suggested hybridizing the Deep Learning techniques (DL) and Finite Element Method (FEM) for predicting the growth of delamination in this structures. A dataset of simulated delamination growth under different delamination sizes has been produced using the FEM method. Then, a DL model has been trained using this dataset to precisely predict the growth of delamination. This study focused on predicting delamination growth using a tuned and optimized deep learning based regressor. Therefore, to find the ideal set of hyperparameters, the Bayesian optimization algorithm has been used for selecting the best structure and enhancing the regressor performance. Afterward, the model was evaluated and multiple processes were conducted to improve its behavior and solve its stability and overfitting issues. Particularly, an inconsistency between validation loss and training loss has been initially detected in the behaviour of the model, which may indicate overfitting. To tackle this issue, dropout regularization has been added, which improved the consistency between the loss functions but results in less smooth convergence from the expectations. So, in a third study, dropout and L1 regularization has been combined to improve the stability of the model. This combination achieved a consistent and smooth convergence between the validation and training loss functions. The findings highlight the importance of hyperparameter optimization and regularization techniques in improving regression model performance. The study shows the efficiency of Bayesian optimization in hyperparameter tuning and the iterative optimization of a regression model. Furthermore, the outcomes show that the suggested method can identify and predict delamination growth with high accuracy.

show abstract

“…Sci. 2022, 12, 691 2 of 16 system [2] to monitor moving loads, unmanned aerial vehicles [3], terrestrial laser scanning [4], and ultrasonic waves [5] etc. to detect surface and internal damages of bridges.…”

Section: Introductionmentioning

confidence: 99%

Synchronized Assessment of Bridge Structural Damage and Moving Force via Truncated Load Shape Function

Zhong

Xiang

Cheng³

2022

Applied Sciences

View full text Add to dashboard Cite

Moving load and structural damage assessment has always been a crucial topic in bridge health monitoring, as it helps analyze the daily operating status of bridges and provides fundamental information for bridge safety evaluation. However, most studies and research consider these issues as two separate problems. In practice, unknown moving loads and damage usually coexist and influence the bridge vibration synergically. This paper proposes an innovative synchronized assessment method that determines structural damages and moving forces simultaneously. The method firstly improves the virtual distortion method, which shifts the structural damage into external virtual forces and hence transforms the damage assessment as well as the moving force identification to a multi-force reconstruction problem. Secondly, a truncated load shape function (TLSF) technique is developed to solve the forces in the time domain. As the technique smoothens the pulse function via a limited number of TLSF, the singularity and dimension of the system matrix in the force reconstruction is largely reduced. A continuous beam and a three-dimensional truss bridge are simulated as examples. Case studies show that the method can effectively identify various speeds and numbers of moving loads, as well as different levels of structural damages. The calculation efficiency and robustness to white noise are also impressive.

show abstract

Damage detection technique using ultrasonic guided waves and outlier detection: Application to interface delamination diagnosis of integrated circuit package

Cited by 15 publications

References 28 publications

Polyacrylonitrile as a versatile matrix for gold nanoparticle-based SERS substrates

Polyacrylonitrile as a versatile matrix for gold nanoparticle-based SERS substrates

Deep learning-based prediction of delamination growth in composite structures: bayesian optimization and hyperparameter refinement

Synchronized Assessment of Bridge Structural Damage and Moving Force via Truncated Load Shape Function

Contact Info

Product

Resources

About