Optimizing process parameters for selective laser sintering based on neural network and genetic algorithm

Wang, Rongji; Li, Xinhua; Wu, Qingding; Wang, Lingling

doi:10.1007/s00170-008-1669-0

Cited by 71 publications

(17 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Caiazzo et al [25] applied BP-NN for trace geometry prediction with RMSE of around 5% using 30 tranining data. Rong-Ji et al [26] tested the performance of BP-NN with 5 to 10 hidden neurons and their results exposed the trend that more hidden neurons tend to make better predictions. Zhang et al [27] used recurrent NN in ME process to predict the tensile strength of the printed products and the RMSE was around 2%.…”

Section: Regression Models Assessment In Am Applicationsmentioning

confidence: 99%

Machine Learning in Additive Manufacturing: A Review

Meng

McWilliams

Jarosinski³

et al. 2020

JOM

270

View full text Add to dashboard Cite

In this review article, the latest applications of machine learning (ML) in additive manufacturing (AM) field are reviewed. These applications, such as parameter optimization and anomaly detection, are classified into different types of ML tasks, including regression, classification, and clustering. The performance of various ML algorithms in these types of AM tasks are compared and evaluated. Finally, several future research directions are suggested.

show abstract

Section: Regression Models Assessment In Am Applicationsmentioning

confidence: 99%

Machine Learning in Additive Manufacturing: A Review

Meng

McWilliams

Jarosinski³

et al. 2020

JOM

270

View full text Add to dashboard Cite

show abstract

“…Choi and Samavedam (2002) developed a combined optimization model for the RP process for minimizing the cusp height error and build time. Phatak and Pande (2012) used genetic algorithm (GA), and Rong-Ji et al (2009) used neural networks and GA-based methods to optimize the AM process for minimizing part errors. However, none of these papers has analyzed and optimized metal powder-based AM processes while considering the combined effect of process energy, part errors and part strength.…”

Section: Optimization Of Am Processesmentioning

confidence: 99%

A combined energy and error optimization method for metal powder based additive manufacturing processes

Paul

Anand

2015

Rapid Prototyping Journal

View full text Add to dashboard Cite

Purpose -The purpose of this paper is to develop a methodology to analyze the total sintering energy (TSE) required for manufacturing a part in metal powder-based additive manufacturing (AM) processes and optimize AM processes for minimizing total energy and form errors of AM parts while maximizing part strength. Design/methodology/approach -The paper uses a computational geometry approach to determine the TSE expended for manufacturing a metal AM part. The stereolithography (STL) file of a part is converted into a voxel data structure and the total sintering volume (TSV) is computed from the voxel representation. The TSE is then calculated from the TSV using the material property information of the metal powder. Findings -The TSE of an AM part is calculated for different slice thickness and part orientations, and the correlation of the total energy to these parameters is calculated. Using these correlations, the AM process is optimized to calculate the optimal values of slice thickness and part orientation which would result in lower process energy, lower part form errors and higher part strength. Originality/value -The methodology presented in this paper provides AM users a roadmap to predict the energy required for manufacturing a part. In addition, the optimization model will allow engineers to manufacture precision parts which satisfy their design specifications with minimal energy expenditure.

show abstract

“…The experiment-based methods are exploited to study the influence of process parameters and optimize them (Ho et al 2003;Cooke et al 2011;Bai et al 2016). Design of experiment (DOE) is usually utilized to reduce the experimental runs and optimize the process parameters (Raghunath and Pandey 2007;Rong-Ji et al 2009;Paul and Anand 2015).…”

Section: Introductionmentioning

confidence: 99%

Multidisciplinary topology optimization incorporating process-structure-property-performance relationship of additive manufacturing

Yuan

Zhu

et al. 2021

Struct Multidisc Optim

View full text Add to dashboard Cite

Multidisciplinary topology optimization (TO) for additive manufacturing (AM) exhibits unprecedented design and manufacturing freedom as an effective lightweight methodology. In order to fully utilize the AM advantages of materialized arrangement in spatial and voxel-by-voxel digitalized printing, multidisciplinary TO for AM requires a full understanding of the process-structure-property-performance (PSPP) relationship to establish the quantitative correlation of part property and multiple process factors, including laser-, process-, and material-related parameters. This study incorporates the PSPP relationships of laser sintered material with topology optimizer so as to provide a guideline for TO collaborative AM design. The proposed workflow involves mapping functions of PSPP relationships via a data-driven approach and then optimizes the multiple process parameters and structural topology by the gradientbased algorithm. Compared with conventional optimization approaches, three case-dependent optimizations demonstrate the effectiveness of the proposed approach yielding encouraging improvements of lightweight performance. The multidisciplinary TO can be generally applied to types of AM technologies, establishing a strong linkage of physical product and digital design.

show abstract

Optimizing process parameters for selective laser sintering based on neural network and genetic algorithm

Cited by 71 publications

References 14 publications

Machine Learning in Additive Manufacturing: A Review

Machine Learning in Additive Manufacturing: A Review

A combined energy and error optimization method for metal powder based additive manufacturing processes

Multidisciplinary topology optimization incorporating process-structure-property-performance relationship of additive manufacturing

Contact Info

Product

Resources

About