Convolutional neural network for predicting crack pattern and stress-crack width curve of air-void structure in 3D printed concrete

Chang, Ze; Zhi, Wei; Xu, Yading; Schlangen, Erik; Šavija, Branko

doi:10.1016/j.engfracmech.2022.108624

Cited by 28 publications

(6 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To predict intricate crack propagation patterns in composite materials, DL pipeline methodologies were employed in the literature, which involve the training of distinct and sequential DL models for separate prediction tasks, such as stress distribution and crack growth patterns. [35][36][37] For instance, a U-Net-based DL model was trained to predict stress distributions (output) derived from composite configurations (input), while another U-Net-based DL model is trained using stress distributions (input) and crack behaviors (output). [35][36][37] A DL pipeline that sequentially concatenates two DL models has demonstrated exceptional results in predicting crack behavior.…”

Section: Predicting Crack Phase Fields At Crack Initiation and Comple...mentioning

confidence: 99%

“…[35][36][37] For instance, a U-Net-based DL model was trained to predict stress distributions (output) derived from composite configurations (input), while another U-Net-based DL model is trained using stress distributions (input) and crack behaviors (output). [35][36][37] A DL pipeline that sequentially concatenates two DL models has demonstrated exceptional results in predicting crack behavior. However, such methods may sequentially amplify errors from each model, potentially resulting in unexpected or unphysical crack predictions for previously unseen composite configurations.…”

Section: Predicting Crack Phase Fields At Crack Initiation and Comple...mentioning

confidence: 99%

See 1 more Smart Citation

Hierarchical Generative Network: A Hierarchical Multitask Learning Approach for Accelerated Composite Material Design and Discovery

Park,

Lee,

Park

et al. 2023

Adv Eng Mater

View full text Add to dashboard Cite

Deep learning (DL) methods combined with computational simulations have shown promise for novel material discovery and establishing structure–response relationships within extensive design spaces. However, obtaining sufficient simulation data for precise predictions on nonlinear responses remains challenging, limiting DL models' predictive capabilities for unexplored composite configurations. To address this, we introduce the hierarchical generative network (HGNet), comprising three customized convolutional neural networks (NNs). HGNet predicts stress fields and crack patterns during mechanical failure events, encompassing linear response regimes, ultimate strength, and complete fracture. By jointly training these networks within a unified DL model, predictive capacity significantly improves. HGNet is applied to a two‐phase composite optimization problem with vast design configurations, demonstrating accurate predictions of complex stress distributions and fracture patterns in unseen configurations. Moreover, it explores uncharted designs with superior stiffness and strength across vast design spaces using genetic algorithms. The methodology provides insight into the model's reasoning through visualizing the inference process. Overall, this approach represents a potent and versatile tool for accelerating material discovery, facilitating a more efficient and cost‐effective approach to finding novel materials, even with limited training data.

show abstract

Section: Predicting Crack Phase Fields At Crack Initiation and Comple...mentioning

confidence: 99%

Section: Predicting Crack Phase Fields At Crack Initiation and Comple...mentioning

confidence: 99%

Hierarchical Generative Network: A Hierarchical Multitask Learning Approach for Accelerated Composite Material Design and Discovery

Park,

Lee,

Park

et al. 2023

Adv Eng Mater

View full text Add to dashboard Cite

show abstract

“…Costs: Deep learning-based detection system helps reduce operating costs associated with solar panel maintenance by improving the analysis process and increasing protection. Early detection of defects can also reduce downtime and maximize energy output and revenue from your solar installation [14][15][16][17][18][19].…”

Section: Introductionmentioning

confidence: 99%

Classification of Solar Cell Cracks Using Deep Learning

Shamala N.

2024

jes

View full text Add to dashboard Cite

This study evaluates the efficacy of a Deep Learning model in classifying solar cell images with and without cracks, crucial for early detection and maintenance of photovoltaic systems. The model demonstrates high overall accuracy (94%) and sensitivity (91%), indicating its proficiency in recognizing images with cracks while minimizing false positives. Receiver Operating Characteristic (ROC) analysis supports the model's robust discrimination between positive and negative cases, with an Area Under the Curve (AUC) of 0.93. Despite promising results, opportunities for improvement include dataset expansion to encompass diverse solar cell conditions and types of cracks. Real-world deployment considerations, such as integration into automated monitoring systems, pose challenges requiring further research. The study underscores the importance of ongoing development to enhance model performance for practical application in solar cell inspection and maintenance.

show abstract

“…Moreover, Chang et al utilized a CNN to predict crack patterns and stress-crack width curves in 3D-printed concrete structures, a material of increasing importance in construction and engineering applications [14]. CNNs' successful application to predicting crack behavior in such complex materials underscores their versatility.…”

Section: Introductionmentioning

confidence: 99%

A Survey of CNN-Based Approaches for Crack Detection in Solar PV Modules: Current Trends and Future Directions

Hassan,

Dhimish

2023

Solar

View full text Add to dashboard Cite

Detection of cracks in solar photovoltaic (PV) modules is crucial for optimal performance and long-term reliability. The development of convolutional neural networks (CNNs) has significantly improved crack detection, offering improved accuracy and efficiency over traditional methods. This paper presents a comprehensive review and comparative analysis of CNN-based approaches for crack detection in solar PV modules. The review discusses various CNN architectures, including custom-designed networks and pre-trained models, as well as data-augmentation techniques and ensemble learning methods. Additionally, challenges related to limited dataset sizes, generalizability across different solar panels, interpretability of CNN models, and real-time detection are discussed. The review also identifies opportunities for future research, such as the need for larger and more diverse datasets, model interpretability, and optimized computational speed. Overall, this paper serves as a valuable resource for researchers and practitioners interested in using CNNs for crack detection in solar PV modules.

show abstract

Convolutional neural network for predicting crack pattern and stress-crack width curve of air-void structure in 3D printed concrete

Cited by 28 publications

References 43 publications

Hierarchical Generative Network: A Hierarchical Multitask Learning Approach for Accelerated Composite Material Design and Discovery

Hierarchical Generative Network: A Hierarchical Multitask Learning Approach for Accelerated Composite Material Design and Discovery

Classification of Solar Cell Cracks Using Deep Learning

A Survey of CNN-Based Approaches for Crack Detection in Solar PV Modules: Current Trends and Future Directions

Contact Info

Product

Resources

About