artificial intelligence-assisted parameter optimization for electrospinning

Aim and background: electrospinning is the easiest and least expensive benchtop method for fabricating continuous nanofibers. the size of nanofibers is important, but modifying the solution s composition and the electrospinning apparatus s configuration can increase efficiency and control the size. combining theoretical and experimental approaches is necessary to fully characterize experimental observations and predict and control effective parameters.methods: models have been developed to link fiber morphology to spinning solutions and controllable processing parameters. however, there are requirements that conflict with these models, such as surface tension, solution viscosity, and fluid flow rate. to ensure the best performance, it is necessary to train and compare several ai systems.results and discussion: response surface methodology and artificial neural networks are the most widely used models for this purpose. response surface methodology combines statistical and mathematical techniques to optimize a response of interest, while artificial neural networks estimate the response using trained data from the range of the independent investigation. fiber diameters are predicted using neural network modeling as a function of inputs, which are measured variables influencing the output. a neural network model could also be used to examine how electrospinning processing affects the mechanical behavior of nanofibers.conclusion: understanding dynamic and quantum-like phenomena in the electrospinning process may undergo a revolution if a real mathematical model, or, more precisely, a real physical model, is developed. it is imperative that a new theory be developed that can connect the quantum and newtonian worlds.