Artificial neural network in prediction of mixed-mode I/II fracture load

Bahrami, Bahador; Talebi, Hossein; Ayatollahi, M.R.; Khosravani, Mohammad Reza

doi:10.1016/j.ijmecsci.2023.108214

Cited by 24 publications

(4 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, the topic of machine learning-aided fracture mechanics, or more narrowly, machine learning for crack detection, is a broad field, with potentially hundreds of different models for various configurations developed recently (see more in the recent reviews [31,32]). Research topics may include constructing surrogate models from training datasets to predict overall damage properties [33] to predicting fracture parameters [34] or monitoring fault diagnosis processes [35]. While our paper naturally fits into the broader picture outlined above, it proposes a more efficient model compared to the basic approach in predicting a mechanical property of material failure, through relatively basic and controllable examples.…”

Section: Discussionmentioning

confidence: 99%

Deep artificial neural network-powered phase field model for predicting damage characteristic in brittle composite under varying configurations

Nguyen,

Le,

Tran

et al. 2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

This work introduces a novel artificial neural network-powered phase field model, offering rapid and precise predictions of fracture propagation in brittle materials. To improve the capabilities of the ANN model, we incorporate a loop of conditions into its core to regulate the Absolute Percentage Error for each observation point, that filters and consistently selects the most accurate outcome. This algorithm enables our model to better adapt to the highly sensitive validation data arising from varying configurations. The effectiveness of the approach is illustrated through three examples involving changes in the microgeometry and material properties of steel fiber-reinforced high-strength concrete structures. Indeed, the predicted outcomes from the improved ANN phase field model in terms of stress-strain relationship, and crack propagation path demonstrates an outperformance compared with that based on the Extreme Gradient Boosting method (XGB), a leading regression machine learning technique for tabular data. Additionally, the introduced model exhibits a remarkable speed advantage, being 180 times faster than traditional phase field simulations, and provides results at nearly any fiber location, demonstrating superiority over the phase field model. This study marks a significant advancement in the application of artificial intelligence for accurately predicting crack propagation paths in composite materials, particularly in cases involving the relative positioning of the fiber and initial crack location.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep artificial neural network-powered phase field model for predicting damage characteristic in brittle composite under varying configurations

Nguyen,

Le,

Tran

et al. 2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…In another study, Bahrami et al . [2] developed artificial neural networks (ANN) models trained with three different algorithms to predict the failure load of various types of cracked samples made of brittle materials. The results showed the effectiveness of the ML-based approach in the fracture prediction of new samples and materials that were not used during the model's training process.…”

Section: Introductionmentioning

confidence: 99%

“…In a recent study, Dehestani et al [1] accurately predicted the fracture load and fracture toughness of Brazilian disc samples made of fibre-reinforced concrete, marble, white travertine, cement mortar, granite and sandstone under pure opening mode, pure sliding mode and mixed-mode I/II loading using 20 different ML algorithms. In another study, Bahrami et al [2] developed artificial neural networks (ANN) models trained with three different algorithms to predict the failure load of various types of cracked samples made of brittle materials. The results showed the effectiveness of the ML-based approach in the fracture prediction of new samples and materials that were not used during the model's training process.…”

Section: Introductionmentioning

confidence: 99%

Data-driven based fracture prediction of notched components

Talebi,

Bahrami,

Daneshfar

et al. 2023

Phil. Trans. R. Soc. A.

Self Cite

View full text Add to dashboard Cite

A data-driven approach is developed to predict the fracture load of a notched component. To do so, more than 1500 fracture tests (507 unique experimental data points) on mixed-mode I/II loading of notched brittle samples were collected from the literature. After pre-processing the raw data, six features of maximum tangential stress ( σ θ θ max ) , maximum tangential stress angle ( θ σ θ θ max ) , ultimate tensile strength ( σ u ) , fracture toughness ( K I c ) , notch opening angle ( 2 α ) and notch tip radius ( ρ ) were selected by using the neighbourhood component analysis (NCA) technique. To predict the fracture load of various types of notched samples, several machine learning (ML) models were trained using the methods of Gaussian process regression (GPR), decision tree ensemble and artificial neural network (ANN). Then, the Bayesian optimization algorithm was applied to find the optimum hyperparameters for each model. Lastly, the performance of the models in predicting fracture load was evaluated against 124 unseen data points. The results revealed the high potential of data-driven methods for assessing the fracture load of notched brittle components with acceptable precisions of 92%, 89% and 88% accuracy, respectively, for GPR, decision tree ensemble and ANN models. The superior performance of the GPR method can be attributed to its ability to capture complex nonlinear relationships in the data while providing reliable uncertainty estimates. Furthermore, thanks to its interpolation capabilities, GPR is able to seamlessly fill the gaps between data points, resulting in more comprehensive and precise predictions across the entire range of input data. Additionally, the presented models were capable of predicting the fracture load of VO-shaped notched samples with acceptable accuracy, though this type of notch was not used in the model training process. This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 2)'.

show abstract

“…ML models are categorized into shallow ML methods and deep learning methods based on the complexity of their structures. In recent years, many shallow ML methods have been employed for life prediction, including artificial neural network (ANN) [17][18][19][20][21] , support vector machine (SVM) 22,23 , and Gaussian process 24 . However, traditional shallow ML algorithms largely rely on prior knowledge and data processing methods, which poses challenges in processing and analyzing extensive data.…”

Section: Introductionmentioning

confidence: 99%

A deep learning and physics-based method for multiaxial fatigue life prediction

Zhou,

Wang,

Hou

et al. 2023

Preprint

View full text Add to dashboard Cite

The prediction of fatigue life for mechanical structures under multiaxial loadings is considered an important task in engineering design, but the conventional models are mostly limited to special loading conditions and materials. In this work, a deep learning and physics-based method is proposed for predicting the multiaxial fatigue life. The relationships between the damage parameters and fatigue life are quantified by establishing a deep belief network (DBN) model. The hyperparameters of the DBN model are adaptively adjusted using a particle swarm optimization (PSO) algorithm. Importantly, the input features of the PSO-DBN model are determined based on the physical model. The proposed method is validated through fatigue tests conducted under various loading paths. The results demonstrate the high effectiveness and applicability of the proposed method for accurately predicting multiaxial fatigue life.

show abstract

Artificial neural network in prediction of mixed-mode I/II fracture load

Cited by 24 publications

References 68 publications

Deep artificial neural network-powered phase field model for predicting damage characteristic in brittle composite under varying configurations

Deep artificial neural network-powered phase field model for predicting damage characteristic in brittle composite under varying configurations

Data-driven based fracture prediction of notched components

A deep learning and physics-based method for multiaxial fatigue life prediction

Contact Info

Product

Resources

About