Artificial neural network-based geometry compensation to improve the printing accuracy of selective laser melting fabricated sub-millimetre overhang trusses

Abstract

Selective laser melting processes deposit and join metal powders to near net shape in a layerby-layer manner. The process of melting and re-solidification of several layers of deposited material can result in geometric deviations, and the impact is particularly significant for submillimetre structures oriented at a wide range of overhang angles with respect to the building platform. This paper assesses and benchmarks the capabilities of a neural network-based geometric compensation approach for truss lattice structures with circular cross-sections. The neural network method is capable to generate free-form cross-sections with enhanced geometric freedom for compensation compared to more established analytical compensation approaches limited to predefined geometric shapes. For neural network training, lattice dome structures composed of trusses with different overhang angles were designed and printed by selective laser melting and measured via X-ray computed tomography, resulting in point cloud data sets containing more than 20,000 data points for each overhang angle. For experimental validation, neural network-compensated dome structures were benchmarked against dome structures with elliptical parameter compensation. Results show that the neural network compensated lattice trusses achieve higher printing dimensional accuracy compared to the uncompensated structures and those compensated based on elliptical parameter estimates.

Comparison of the fatigue life of pure titanium and titanium alloy clasps manufactured by laser powder bed fusion and its prediction before manufacturing

“…Wang et al [31] discussed the support structures of partial dentures. In the next step of the present study, the same building orientation as that of a clinical clasp [20] without the cylindrical chucking part would be used by developing a geometry compensation methodology [32] for the chucking part.…”

Selective Laser Melting Process for Sensor Embedding into SUS316L with Heat Dissipative Inner Cavity Design

“…In the case of Ruochen's study, a geometric prediction model based on artificial neural network (ANN) was created by collecting extensive data on the overhang angle using a dome-shaped truss lattice structure with various overhang angles applied to predict and complement the shape according to the overhang angle. [19]. Kenneth et al modeled and simulated the heat to solve the heat distortion that occurs in a thin sculpture with an overhang, and based on this, modeled a non-contact heat dissipating sculpture different from the existing supporters [20].…”

Simultaneous optimisation of support structure regions and part topology for additive manufacturing

“…During the SLM printing process, a laser melts the powder and the liquid metal pool will seep into the powder below, creating an irregular under surface in overhanging regions (Hong, et al 2021). As the metal solidifies and cools, the thermally induced residual stresses tend to lift the part upwards, which can cause permanent deformation of the part and/or a collision with the recoat blade .…”