Machine learning to empower electrohydrodynamic processing

Wang, Fanjin; Elbadawi, Moe; Tsilova, Scheilly Liu; Gaisford, Simon; Basit, Abdul W.; Parhizkar, Maryam

doi:10.1016/j.msec.2021.112553

Cited by 16 publications

(9 citation statements)

References 155 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recall measures the proportion of correctly predicted positive instances out of all actual positive instances.where FN are the instances that are mistakenly classified as negative when they are actually positive. 36…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Siamese neural network framework for glass transition recognition

Osiecka-Drewniak,

Deptuch,

Urbańska

et al. 2024

Soft Matter

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

“…where FN are the instances that are mistakenly classified as negative when they are actually positive. 36 The results of training for the chosen Siamese neural networks are presented in Fig. 8-10.…”

Section: Resultsmentioning

confidence: 99%

A Siamese neural network framework for glass transition recognition

Osiecka-Drewniak,

Deptuch,

Urbańska

et al. 2024

Soft Matter

View full text Add to dashboard Cite

show abstract

“…To obtain sub-microwire arrays with smaller widths and improved morphologies, the printing parameters should be optimized. [27][28][29][30] Regression analysis and a genetic algorithm were used to obtain the optimal parameters for CFEJ printing with the goal of minimizing the sub-microwire width. Orthogonal design is a multi-factorial test method that uses an orthogonal table derived from combinatorial theory to design the experiment and analyze the results of the experiment.…”

Section: Orthogonal Experimental Designmentioning

confidence: 99%

Optimized coaxial focused electrohydrodynamic jet printing of highly ordered semiconductor sub-microwire arrays for high-performance organic field-effect transistors

Wang

Zhao

et al. 2023

Nanoscale

View full text Add to dashboard Cite

show abstract

“…However, creating ML models for EHD processes will require overcoming challenges related to the limited amount of available literature data and significant heterogeneity in input data. [ 9 ] So, an accurate selection of ML techniques that can overcome these limitations is necessary.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning‐Informed Predictive Design and Analysis of Electrohydrodynamic Printing Systems

Singh,

Rai,

Subramanian

2023

Adv Eng Mater

View full text Add to dashboard Cite

Electrohydrodynamic (EHD) processes are promising techniques for manufacturing nanoscopic products with different shapes (such as thin films, nanofibers, 2D/3D nanostructures, and nanoparticles) and materials at a low cost using simple equipment. A key challenge in their adoption by nonexperts is the requirement of enormous time and resources in identifying the optimum design/process parameters for the underlying material and EHD system. Machine learning (ML) has made exciting advancements in predictive modeling of different processes, provided it is trained on high‐quality datasets at appropriate volumes. This article extends the suitability of such ML‐enabled approaches to a new technological domain of EHD spraying and drop‐on‐demand printing. Different ML models like ridge regression, random forest regression, support vector regression, gradient boosting regression, and multilayer perceptron are trained and their performance using evaluation metrics like RMSE and R2_score is examined. Tree‐based algorithms like gradient boosting regression are found to be the most suitable technique for modeling EHD processes. The trained ML models show substantially higher accuracy (average error < 5%) in replicating these nonlinear processes as compared to previously reported scaling laws (average error ≈ 42%) and are well suited for predictive modeling/analysis of the underlying EHD system and process.

show abstract

Machine learning to empower electrohydrodynamic processing

Cited by 16 publications

References 155 publications

A Siamese neural network framework for glass transition recognition

A Siamese neural network framework for glass transition recognition

Optimized coaxial focused electrohydrodynamic jet printing of highly ordered semiconductor sub-microwire arrays for high-performance organic field-effect transistors

Machine Learning‐Informed Predictive Design and Analysis of Electrohydrodynamic Printing Systems

Contact Info

Product

Resources

About