Electrospun Fiber Experimental Attributes Dataset (FEAD)

Understanding the intricate relationships between the structure and properties of electrospun PVDF fibers is crucial for designing effective devices. However, the complexity of these relationships makes them challenging to model through traditional trial-and-error experiments. Machine learning has emerged as a powerful tool for modeling multidimensional relationships, but it requires a diverse and high-quality training dataset to effectively learn these intricate connections.
To comprehensively investigate the intricate relationships between the structure and properties of electrospun PVDF fibers, a high-quality training dataset is imperative, encompassing a wide array of experimental conditions. There is no single comprehensive source that provides a holistic understanding of how the various parameters impact the PVDF fiber properties. Existing studies predominantly present results from a limited range of parameter variations, necessitating the creation of a meta dataset for robust insights. In response to this gap, we introduce the "Electrospun Fiber Experimental Attributes Dataset (FEAD)," a meticulously curated compilation that collates data from diverse literature sources and complements with our own experimental findings and computations.
FEAD comprises a total of 565 data points sourced from 48 distinct references. This dataset encapsulates a broad spectrum of solvents and solvent systems, including DMAC, DMF, DMAC/Acetone, DMSO/Acetone, DMF/Acetone, NMP/Acetone, among others. While certain parameters such as polymer concentration, solvent ratio, feed rate, and applied voltage were directly extracted from the literature, other critical factors like solubility parameters, interaction radii, and RED were computed.
Experiments involving the use of surfactants and electrolytes to alter polymer viscosity and electrical conductivity are not included in the dataset. This exclusion ensures a focus on understanding the genuine impact of polymer concentration and solubility factors on the resulting fibers. The development of this novel materials database is an ongoing effort, and we anticipate its continual improvement over time as more datapoints are incorporated.