Part Build Orientation Optimization and Neural Network-Based Geometry Compensation for Additive Manufacturing Process

Abstract

Significant advancements in the field of additive manufacturing (AM) have increased the popularity of AM in mainstream industries. The dimensional accuracy and surface finish of parts manufactured using AM depend on the AM process and the accompanying process parameters. Part build orientation is one of the most critical process parameters, since it has a direct impact on the part quality measurement metrics such as cusp error, manufacturability concerns for geometric features such as thin regions and small fusible openings, and support structure parameters. In conjunction with the build orientation, the cyclic heating and cooling of the material involved in the AM processes lead to nonuniform deformations throughout the part. These factors cumulatively affect the design conformity, surface finish, and the postprocessing requirements of the manufactured parts. In this paper, a two-step part build orientation optimization and thermal compensation methodology is presented to minimize the geometric inaccuracies resulting in the part during the AM process. In the first step, a weighted optimization model is used to determine the optimal build orientation for a part with respect to the aforementioned part quality and manufacturability metrics. In the second step, a novel artificial neural network (ANN)-based geometric compensation methodology is used on the part in its optimal orientation to make appropriate geometric modifications to counteract the thermal effects resulting from the AM process. The effectiveness of this compensation is assessed on an example part using a new point cloud to part conformity metric and shows significant improvements in the manufactured part's geometric accuracy.

Machines as Craftsmen: Localized Parameter Setting Optimization for Fused Filament Fabrication 3D Printing

“…[30] The geometry of the part was then adjusted using machine learning to mitigate warping. A visual representation of the part could then be constructed to show the location of flaws.…”

Determination of optimal build orientation for additive manufacturing using Muirhead mean and prioritised average operators

“…Used MOO techniques Optimised objectives Cheng et al (1995) Weighted sum function Part accuracy; build time Lan et al (1997) Self-developed algorithm Surface quality; build time; complexity of support structure Alexander et al (1998) Self-developed algorithm Cost; support volume; contact area with support; surface accuracy McClurkin and Rosen (1998) Self-developed algorithm Build time; accuracy; surface finish Hur and Lee (1998) Genetic algorithm Part accuracy; build time; support structure volume Xu et al (1999) Self-developed algorithm Build cost; build time; building inaccuracy; surface finish Hur et al (2001) Genetic algorithm Build time; surface quality Masood et al (2003) Generic mathematical algorithm Volumetric error Thrimurthulu et al (2004) Genetic algorithm Surface finish; build time Pandey et al 2004Genetic algorithm Surface roughness; build time Kim and Lee (2005) Genetic algorithm Post-processing time and cost Ahn et al (2007) Genetic algorithm Post-machining time Canellidis et al (2009) Genetic algorithm Build time; surface roughness; post-processing time Padhye and Deb (2011) Genetic algorithm and particle swarm algorithm Surface roughness; build time Strano et al (2011) Genetic algorithm Surface roughness; energy consumption Zhang and Li (2013) Genetic algorithm Volumetric error Paul and Anand (2015) Genetic algorithm Cylindricity and flatness errors; support structure volume Ezair et al (2015) Self-developed algorithm Support structure volume Delfs et al (2016) Self-developed algorithm Surface quality; build time Luo and Wang (2016) Principal component analysis Volumetric error Zhang et al (2017) Genetic algorithm Build time; build cost; production quality Brika et al (2017) Genetic algorithm Surface roughness; build time; build cost; yield strength; tensile strength; elongation; vickers hardness; amount of support structure Chowdhury et al (2018) Genetic algorithm Support structure volume; support structure accessibility; surface area contacting support; number of build layers; number of small openings; number of sharp corners; mean cusp height Mi et al (2018) Point clustering algorithm Number of material changes Jaiswal et al (2018) Surrogate model Material error; geometric error Al-...…”

“…attributes of build orientations), such as design requirements, build cost, build time, part accuracy, mechanical properties, and thermodynamic properties, to be optimal from an infinite number of theoretical orientations or a certain number of alternative orientations. The methods based on this principle mainly include the methods proposed by Cheng et al (1995), Lan et al (1997), Alexander et al (1998), McClurkin and Rosen (1998), Hur and Lee (1998), Xu et al (1999), Hur et al (2001), Masood et al (2003), Thrimurthulu et al (2004), Pandey et al (2004), Kim and Lee (2005), Ahn et al (2007), Canellidis et al (2009), Padhye and Deb (2011), Strano et al (2011), Zhang and Li (2013), Paul and Anand (2015), Ezair et al (2015), Delfs et al (2016), Luo and Wang (2016), Zhang et al (2017), Brika et al (2017), Chowdhury et al (2018), Mi et al (2018), Jaiswal et al (2018), Al-Ahmari et al (2018), Huang et al (2018), Raju et al (2018), and Golmohammadi and Khodaygan (2019). A brief summarisation of these methods is provided in Table 1.…”

“…As can be seen from the table, different MOO techniques and optimised objectives were used. Among the used MOO techniques, genetic algorithm is the most frequently used technique, in which Brika et al (2017) and Chowdhury et al (2018) have considered significantly more numbers of optimised objectives than the others. This means that the two methods can achieve better optimisation results than other Table 1 A brief summarisation of some typical MOO methods Notes: Golmohammadi (2019) is short for Golmohammadi and Khodaygan (2019); PSO particle swarm optimisation; BFO bacterial foraging optimisation…”

Automatic determination of part build orientation for laser powder bed fusion

“…Theoretically, a 3D part has an infinite number of possible build orientations. A one-step method generally develops a specialised algorithm (Alexander, Allen, and Dutta 1998;Delfs, Tows, and Schmid 2016;Golmohammadi and Khodaygan 2019;Griffiths et al 2019;Ulu et al 2020;Wang and Qian 2020) or applies an existing optimisation algorithm, such as the genetic algorithm (Hur et al 2001;Masood, Rattanawong, and Iovenitti 2003;Thrimurthulu, Pandey, and Reddy 2004;Ahn, Kim, and Lee 2007;Padhye and Deb 2011;Zhang and Li 2013;Paul and Anand 2015;Brika et al 2017;Chowdhury, Mhapsekar, and Anand 2018), particle swarm algorithm (Padhye and Deb 2011;Cheng and To 2019;Raju et al 2019;Shen et al 2020) or bacterial foraging algorithm (Raju et al 2019), to directly search an orientation enabling one or more part orientation factors to be optimal from infinite possible orientations. In a one-step method, the 3D model of a part is first rotated with a random or fixed angle.…”