Application of machine learning to optimize process parameters in fused deposition modeling of PEEK material

Abstract

Due to the high-performance mechanical properties and the desirable chemical and temperature resistance, PEEK is often used as a replacement for metals in both academia and industry. Fused deposition modeling is a rapidly growing additive technology for producing PEEK parts. However, the high thermal gradients and varying heat distributions during processing frequently result in residual stresses and considerable deformations of the parts. The focus of this paper is on a framework for applying machine learning to tune process parameters with the aim of minimizing the warpage effect.