Please use this identifier to cite or link to this item:
|Title:||Investigation of relationships between continuous-wave process parameters and physical properties of SLM-manufactured Ti-64 using machine learning||Authors:||Seah, Jia Jun||Keywords:||Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
|Issue Date:||2022||Publisher:||Nanyang Technological University||Source:||Seah, J. J. (2022). Investigation of relationships between continuous-wave process parameters and physical properties of SLM-manufactured Ti-64 using machine learning. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/157962||Project:||B278||Abstract:||Selective Laser Melting (SLM) technology has numerous process parameters that can influence the physical properties of the printed part. As a result, there is high dimensionality in the dataset containing data of process parameters used to print the parts and the corresponding physical properties. Hence, it is time-consuming and costly to utilise conventional statistical approaches to identify the underlying parameter-property relationships. In this study, a data-driven approach is taken to find out the relationships. Before the investigation of the parameter-property relationships, data were collated from the online literature. As each research work, from the online literature, focuses on various process parameters and physical properties, the dataset built was not complete. Thus, five imputation techniques were explored in this study to fill up the missing values, and the median of the imputed results from the five approaches was taken as the final value. Thereafter, Self-Organising Map (SOM) and Accumulated Local Effect (ALE) plots were used to visualise the relationships. The ALE plots were generated based on three different models, namely Random Forest, Gradient Boosting, and neural network. From the SOM plots, UTS, yield strength, Young’s modulus, and density are directly correlated. Scan speed is inversely correlated to energy density and microhardness. Layer thickness, laser power, and hatch spacing are directly correlated. From the ALE plots, increase in energy density and its constituent process parameters tend to increase most of the physical properties before experiencing a decrease. This observation conforms with the interaction between energy density and density. Both lack and surplus of energy density would lead to drop in density due to LOF and keyhole porosities respectively. Since many of the physical properties are dependent on density, they move in tandem with density.||URI:||https://hdl.handle.net/10356/157962||Fulltext Permission:||restricted||Fulltext Availability:||With Fulltext|
|Appears in Collections:||MAE Student Reports (FYP/IA/PA/PI)|
Updated on Dec 6, 2022
Updated on Dec 6, 2022
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.