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

Abstract

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