College
Bellini College of Artificial Intelligence, Cybersecurity and Computing
Mentor Information
Sylvia Thomas
Description
Electrospinning is a widely used Fabrication technique for producing continuous polymeric nanofibers with application in designing more efficient optoelectronic devices, sensors, producing filtration systems, wound healing, tissue regeneration, drug delivery , forming advanced functional nanomaterial structures. The successful formation of electro-spun fibers depends on complex interaction among polymer concentration, solution viscosity, molecular chain entanglement, solvent properties, applied voltage, tip-collector-distance, and solution flow rate. Determining the optimum electrospinning condition traditionally achieved through repeated experimental trial and error, makes the process time consuming, costly, and difficult to reproduce across different polymer-solvent systems. Developing computational tools capable of predicting fiber formation can significantly reduce experimental effort while improving process optimization. This study presents the development of a computational algorithm to predict the formation of continuous fiber during electrospinning. Experimental data were extracted from published work which systematically investigated the influence of solution properties on the electrospinning behavior in various solvent. The extracted dataset was used to establish a rule-based prediction model that classifies electrospinning outcomes based on polymer concentration while incorporating experimentally validated process parameters. This proposed computational framework serve as a rapid decision-support tool for electrospinning process design by reducing the need for extensive experimental optimization. The current model is developed from published datasets and online databases. This methodology can be expanded using larger electro-spinning databases and machine learning technique to predict optimal processing conditions across a broad range of polymer-solvent system. Such predictive tools have the potential to accelerate material development, improve experimental reproducibility, and support the integration of artificial intelligence into electrospinning research.
Computational Modeling of Electrospinning for Predicting Nanofiber Fabrication and Process Optimization
Electrospinning is a widely used Fabrication technique for producing continuous polymeric nanofibers with application in designing more efficient optoelectronic devices, sensors, producing filtration systems, wound healing, tissue regeneration, drug delivery , forming advanced functional nanomaterial structures. The successful formation of electro-spun fibers depends on complex interaction among polymer concentration, solution viscosity, molecular chain entanglement, solvent properties, applied voltage, tip-collector-distance, and solution flow rate. Determining the optimum electrospinning condition traditionally achieved through repeated experimental trial and error, makes the process time consuming, costly, and difficult to reproduce across different polymer-solvent systems. Developing computational tools capable of predicting fiber formation can significantly reduce experimental effort while improving process optimization. This study presents the development of a computational algorithm to predict the formation of continuous fiber during electrospinning. Experimental data were extracted from published work which systematically investigated the influence of solution properties on the electrospinning behavior in various solvent. The extracted dataset was used to establish a rule-based prediction model that classifies electrospinning outcomes based on polymer concentration while incorporating experimentally validated process parameters. This proposed computational framework serve as a rapid decision-support tool for electrospinning process design by reducing the need for extensive experimental optimization. The current model is developed from published datasets and online databases. This methodology can be expanded using larger electro-spinning databases and machine learning technique to predict optimal processing conditions across a broad range of polymer-solvent system. Such predictive tools have the potential to accelerate material development, improve experimental reproducibility, and support the integration of artificial intelligence into electrospinning research.
