Towards an interpretable machine learning model for electrospun polyvinylidene fluoride (PVDF) fiber properties

Sarma, S. Das; Verma, Akarshit Kumar; Phadkule, Saket Sanjay; Saharia, Manabendra

doi:10.1016/j.commatsci.2022.111661

Cited by 17 publications

(9 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this method, it is imperative to choose a solvent which can amply dissolve the host polymer and do not react with the nanofillers. Hansen solubility parameters and relative energy difference (RED) combined with Flory-Huggins interaction parameter χ offers a convenient way to choose the appropriate solvent for dissolving a polymer [13]. It is important to note that the solvents for dispersing the nanofillers and dissolving the polymer could be different but the solvents must be miscible.…”

Section: Physical Methodsmentioning

confidence: 99%

“…Characterization techniques such as microscopy and spectroscopy techniques can open up structural details of the composites, the scattering of the fillers, interconnection between filler and matrix, and bring forth information at molecular level [5]. This can, in turn help one understand the static and dynamic mechanical and thermal behaviours portrayed by the composites and impart some ability in controlling the dispersion of the NPs, interfacial adhesion, size and shape, scalability, cost etc Data-driven models can be developed to predict properties of the composites, provided composition, constituents and individual material properties are known as priori [13]. UV-vis spectroscopy, Raman spectroscopy, x-ray photoelectron spectroscopy (XPS), Auger electron spectroscopy (AES), Scanning electron microscopy (SEM), x-ray diffraction (XRD), and Transmission electron microscopy (TEM) are some of the commonly used spectroscopic methods for hybrid PNCs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Emerging synthesis and characterization techniques for hybrid polymer nanocomposites

Sarma,

Rao

2023

Nanotechnology

Self Cite

View full text Add to dashboard Cite

Metallic nanoparticles and carbon nanotubes are two of the most promising nanomaterials, due to their distinctive properties occurring from spatial confinement of electron-hole pairs. The unique combination of metallic nanoparticles and carbon nanotubes (CNTs) in a polymer matrix offers unparalleled advantages, making them highly desirable in various fields. Advanced methods and techniques for synthesizing and characterizing hybrid metal-CNT-polymer nanocomposites (PNCs) have undergone significant progress in recent years, paving their integration into various fields, including aerospace, electronics, energy, water treatment and environmental remediation. These advances have allowed better understanding of nanocomposite properties and imparted ability to tune specific properties through size, shape, and distribution control of the nanofillers within the matrix material or by altering filler properties through functionalization. This review aims to critically judge the emerging tools, techniques and methods used in polymer nanocomposites with specific focus on metal-CNT based hybrid polymer nanocomposites, and suggest new avenues for research in the field. Furthermore, by examining the mechanisms affecting the performance of these composites, we can understand how the inclusion of fillers alters the microstructure and overall behavior of the material. Ultimately, this knowledge could lay the foundation for the development of novel nanocomposites with tailored properties and enhanced performance in a plethora of applications.

show abstract

Section: Physical Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Emerging synthesis and characterization techniques for hybrid polymer nanocomposites

Sarma,

Rao

2023

Nanotechnology

Self Cite

View full text Add to dashboard Cite

show abstract

“…The nanofiber characteristics considered were the average diameter, curcumin release percentage, and encapsulation efficiency. Sarma et al 23 presented the development of multiple machine learning strategies to model the diameter of the produced nanofiber using a large number of experimental parameters that were collected from the literature. Pervez et al 24 presented a locally weighted kernel partial least-squares regression (LW-KPLSR) model based on Taguchi statistical orthogonal design to predict the membrane diameter of chitosan-based electrospun nanofibers.…”

Section: ■ Introductionmentioning

confidence: 99%

Data-Driven Machine Learning Approach for Modeling the Production and Predicting the Characteristics of Aligned Electrospun Nanofibers

López-Flores,

Ornelas-Guillén,

Pérez-Nava

et al. 2024

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

The generation of electrospun nanofibrous with controlled size, shape, and spatial orientation is crucial for the development of biomedical and electronic devices. Aligned nanofibers are advantageous over random nanofibers because control of the spatial orientation can improve electrical and optical properties and play an important role in tissue engineering applications, impacting the mechanical and biological properties of the scaffold. Therefore, different machine learning models have been developed to predict the optimal production of electrospun-aligned poly(vinyl alcohol) nanofibers. The database was obtained by multiple assays using the airgap electrospinning setup and varying the voltage, the distance between the tip and collector, and polymer concentration. Binary classification models were developed, which can predict the production or not of aligned nanofibers. In addition, regression models have been developed to predict the orientation, angle, and diameter of the nanofibers when there is a production of nanofibers. A convolutional neural network has also been developed. It was concluded that for the binary classification, the artificial neural network performs better predictions obtaining an accuracy equal to 0.94, and for the validation set, an accuracy equal to 0.90 and an F1-score equal to 0.87 were obtained.

show abstract

“…However, emerging technologies, particularly articial intelligence (AI) and machine learning, offer a promising tool for determining the optimal parameter ranges. [27][28][29] The emergence of machine learning and deep learning (a branch of machine learning) has transformed physical modeling into data-driven modeling. This method of analysis can potentially be the best approach with the lowest error for prediction of the physical properties of electrospun scaffolds to save time, cost, and material.…”

Section: Introductionmentioning

confidence: 99%

Machine learning-guided morphological property prediction of 2D electrospun scaffolds: the effect of polymer chemical composition and processing parameters

Golbabaei,

Varnoosfaderani,

Hemmati

et al. 2024

RSC Adv.

View full text Add to dashboard Cite

show abstract

Towards an interpretable machine learning model for electrospun polyvinylidene fluoride (PVDF) fiber properties

Cited by 17 publications

References 35 publications

Emerging synthesis and characterization techniques for hybrid polymer nanocomposites

Emerging synthesis and characterization techniques for hybrid polymer nanocomposites

Data-Driven Machine Learning Approach for Modeling the Production and Predicting the Characteristics of Aligned Electrospun Nanofibers

Machine learning-guided morphological property prediction of 2D electrospun scaffolds: the effect of polymer chemical composition and processing parameters

Contact Info

Product

Resources

About