Artificial Neural Network-Based Predictive Model for Finite Element Analysis of Additive-Manufactured Components

Additive manufacturing is becoming one of the most utilized tools in an increasing number fields from Industry 4.0 concepts, engineering, and to aerospace medical applications. One important issue with additive-manufactured components their orthotropic behaviour where mechanical properties are concerned. This due layer-by-layer process particularly hard predict since it depends on a factors, including parameters used during (speed, temperature, etc.). study aimed create train artificial neural network-based predictive model using empirical tensile strength data obtained additive manufactured test parts FDM method PLA material. The was designed characteristics for different orientation axis, which were set material finite element analysis. Results indicate strong correlation between predicted analysis real-world tests components. network trained accuracy ~93% predicting 3D-printed Using defining custom profile analysis, simulated failure mode complex geometry component agreed test.