Machine learning algorithms to optimize the properties of bio-based poly(butylene succinate-co- butylene adipate) nanocomposites with carbon nanotubes

In this project, a simple, cost-effective and scalable solution to improve the mechanical properties of poly(butylene succinate-co- butylene adipate) (PBSA) is reported by using functionalized single-walled carbon nanotubes (SWCNTs). Different SWCNT percentages w/w (0.15, 0.25, 0.5, 0.65, 0.75, 0.85 and 1.0) have been incorporated in the PBSA matrix via simple solution casting, and the ultrasonication conditions, namely amplitude (A) and time (t) have been optimized to attain a homogenous SWCNT dispersion. The nanocomposites have been characterized in detail by scanning electron microscopy (SEM), Infrared spectroscopy, thermogravimetric analysis (TGA), differential scanning calorimetry (DSC), tensile and impact strength tests. Unprecedented increments in stiffness, up to 114 % for the nanocomposite with 0.65 wt% content,were found. Further, four machine learning (ML) algorithms were applied to predict their mechanical properties and very good correlation was attained.