Data-driven decision-making and benchmarking in PBF-LB/M
Nadeem, Usama (2024-05-30)
Data-driven decision-making and benchmarking in PBF-LB/M
(30.05.2024)
Julkaisu on tekijänoikeussäännösten alainen. Teosta voi lukea ja tulostaa henkilökohtaista käyttöä varten. Käyttö kaupallisiin tarkoituksiin on kielletty.
avoin
Julkaisun pysyvä osoite on:
https://urn.fi/URN:NBN:fi-fe2024061048744
https://urn.fi/URN:NBN:fi-fe2024061048744
Tiivistelmä
This thesis proposes a novel framework for decision-making built on the backend of MATLAB application facilitating the selection of comparable technologies of Laser powder bed fusion for metals (PBF-LB/M). The aim of this research is to enhance the PBF-LB/M benchmarking process by introducing a simplified geometric benchmark artifact that facilitates the proposed framework for precise measurement, result interpretation, and technological comparison. The purpose of the study is to streamline the technology selection process in PBF-LB/M by reducing the reliance on trial-and-error methods.
Main findings include the successful development of a decision-making framework that integrates extensive data collection and analysis from geometrical benchmark artifacts using various metrology tools. The literature review reveals a significant gap in structured decision-making processes within additive manufacturing, which this framework aims to address. The experimental part demonstrates that the framework can save time and material consumption and improve resource management by minimizing the trial-and-error phase typically associated with machine selection.
The use case study included in this thesis highlights the practical benefits of the framework, showing its potential to transform decision-making processes in additive manufacturing. However, further studies and real-world testing are necessary to validate the statistical predictions and future studies could incorporate machine learning algorithms with additional parameters. Overall, this research provides a structured and data-driven approach to technology selection, with the potential to optimize technology usage and decision-making processes.
Main findings include the successful development of a decision-making framework that integrates extensive data collection and analysis from geometrical benchmark artifacts using various metrology tools. The literature review reveals a significant gap in structured decision-making processes within additive manufacturing, which this framework aims to address. The experimental part demonstrates that the framework can save time and material consumption and improve resource management by minimizing the trial-and-error phase typically associated with machine selection.
The use case study included in this thesis highlights the practical benefits of the framework, showing its potential to transform decision-making processes in additive manufacturing. However, further studies and real-world testing are necessary to validate the statistical predictions and future studies could incorporate machine learning algorithms with additional parameters. Overall, this research provides a structured and data-driven approach to technology selection, with the potential to optimize technology usage and decision-making processes.