Application of machine learning methods on dynamic strength analysis for additive manufactured polypropylene-based composites

Cai, Ruijun; Wang, Kui; Wen, Wei; Peng, Yong; Baniassadi, Majid; Ahzi, Saı̈d

doi:10.1016/j.polymertesting.2022.107580

Cited by 39 publications

(30 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performances of the two models were evaluated by four wide used regression models evaluation metrics [ 23 ] : regression score function ( R 2 ), mean absolute error (MAE), root mean square error (RMSE), and median absolute error (MedAE). The equations and brief explanations of these metrics were presented in the Supplementary material.…”

Section: Experiments and Modelingmentioning

confidence: 99%

“…Because the utilization of the FFD could statistically attenuate the over-fitting phenomenon and better reflect the interactive influences of factors on responses. [23,34] In addition, 27 test datasets were randomly selected from the factor combination space to validate the models.…”

Section: Datasets Preparationmentioning

confidence: 99%

“…These two approaches were selected based on the previous study for predicting the dynamic strength of 3D‐printed parts. [ 23 ] More specifically, ANN was suitable to achieve high prediction accuracy, and RF was recommended if the importance of factor was required. The importance of factor could be used to evaluate the extent of factors' influence on response.…”

Section: Experiments and Modelingmentioning

confidence: 99%

“…Although theoretical and numerical methods could be utilized to study the dynamic mechanical properties of materials, considering the complex microstructure of 3D-printed composites, their prediction accuracy and efficiency were still challenging. [23,27] Recent advancements in machine learning (ML) methods offer new possibilities for developing fast, computationally affordable, and high-fidelity predictive models. Specifically, ML methods allowed for automatic discovery of patterns and trends in the existing data and prediction at unseen points without having to perform new physical modeling or experiments.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Investigation on dynamic strength of 3D‐printed continuous ramie fiber reinforced biocomposites at various strain rates using machine learning methods

et al. 2022

Self Cite

View full text Add to dashboard Cite

3D-printed continuous natural fiber reinforced biocomposites have promising prospects due to their environmental friendliness and suitable mechanical properties. Understanding the dynamic mechanical properties of 3D-printed biocomposites is essential to expand their application. In this study, the continuous ramie fiber reinforced biocomposites (CRFRC) with different layer thicknesses and hatch spacings were fabricated via 3D printing technique with microstructure characterized. In addition, the dynamic strengths of 3D-printed CRFRC at four strain rates were investigated. The experimental results exhibited that the printing parameters presented nonlinear and interactive influences on the dynamic strength of CRFRC. Given this circumstance, machine learning methods were employed to link the dynamic strength of 3Dprinted CRFRC with different printing parameters. The experimental data were used to train, calibrate, and validate the machine learning models. The trained models were then utilized to predict the dynamic strength of CRFRC printed using different conditions. Behaviors under multiple strain rates were investigated over the whole parameter space. A good agreement was found between experimental results and predictions. Based on the prediction results, the relationships between parameters, microstructural characteristics and dynamic strength of printed CRFRC were quantitatively analyzed.

show abstract

Section: Experiments and Modelingmentioning

confidence: 99%

Section: Datasets Preparationmentioning

confidence: 99%

Section: Experiments and Modelingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Investigation on dynamic strength of 3D‐printed continuous ramie fiber reinforced biocomposites at various strain rates using machine learning methods

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Erban [ 15 ] adopted ML technology to accelerate the design process of composites by replacing the time-consuming FEM analysis. Veivers [ 16 ] used particle swarm optimization (PSO) to optimize the layup design of generic tubular geometries under simultaneous thermal and mechanical loading conditions, and Cai [ 17 ] studied the application of ML methods to analyze the dynamic strength of 3D-printed polypropylene (PP) composites. A number of results in the literature show the successful application of machine learning in composite materials, which provides a good idea for the integration of machine learning and composites.…”

Section: Introductionmentioning

confidence: 99%

Accelerating the Layup Sequences Design of Composite Laminates via Theory-Guided Machine Learning Models

Liao

Qiu

Yang³

et al. 2022

Polymers

View full text Add to dashboard Cite

Experimental and numerical investigations are presented for a theory-guided machine learning (ML) model that combines the Hashin failure theory (HFT) and the classical lamination theory (CLT) to optimize and accelerate the design of composite laminates. A finite element simulation with the incorporation of the HFT and CLT were used to generate the training dataset. Instead of directly mapping the relationship between the ply angles of the laminate and its strength and stiffness, a multi-layer interconnected neural network (NN) system was built following the logical sequence of composite theories. With the forward prediction by the NN system and the inverse optimization by genetic algorithm (GA), a benchmark case of designing a composite tube subjected to the combined loads of bending and torsion was studied. The ML models successfully provided the optimal layup sequences and the required fiber modulus according to the preset design targets. Additionally, it shows that the machine learning models, with the guidance of composite theories, realize a faster optimization process and requires less training data than models with direct simple NNs. Such results imply the importance of domain knowledge in helping improve the ML applications in engineering problems.

show abstract

Methods, progresses, and opportunities of materials informatics

Li,

Zheng

2023

InfoMat

View full text Add to dashboard Cite

As an implementation tool of data intensive scientific research methods, machine learning (ML) can effectively shorten the research and development (R&D) cycle of new materials by half or even more. ML shows great potential in the combination with other scientific research technologies, especially in the processing and classification of large amounts of material data from theoretical calculation and experimental characterization. It is very important to systematically understand the research ideas of material informatics to accelerate the exploration of new materials. Here, we provide a comprehensive introduction to the most commonly used ML modeling methods in material informatics with classic cases. Then, we review the latest progresses of prediction models, which focus on new processing–structure–properties–performance (PSPP) relationships in some popular material systems, such as perovskites, catalysts, alloys, two‐dimensional materials, and polymers. In addition, we summarize the recent pioneering researches in innovation of material research technology, such as inverse design, ML interatomic potentials, and microtopography characterization assistance, as new research directions of material informatics. Finally, we comprehensively provide the most significant challenges and outlooks related to the future innovation and development in the field of material informatics. This review provides a critical and concise appraisal for the applications of material informatics, and a systematic and coherent guidance for material scientists to choose modeling methods based on required materials and technologies.

show abstract

Application of machine learning methods on dynamic strength analysis for additive manufactured polypropylene-based composites

Cited by 39 publications

References 58 publications

Investigation on dynamic strength of 3D‐printed continuous ramie fiber reinforced biocomposites at various strain rates using machine learning methods

Investigation on dynamic strength of 3D‐printed continuous ramie fiber reinforced biocomposites at various strain rates using machine learning methods

Accelerating the Layup Sequences Design of Composite Laminates via Theory-Guided Machine Learning Models

Methods, progresses, and opportunities of materials informatics

Contact Info

Product

Resources

About