×

Prediction of Tensile Strength of ABS Material Manufactured by Fused Deposition Modeling Using Machine Learning

Author : Assistant Professor Ch. Raju, Assistant Professor A. Bhargav, Ch. Akshay, V. Dinesh Reddy, T. Shiva shanker, K. Laxmi Narasimha Journa Name: INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH AND ENGINEERING TRENDS Country : India Volume: 10 issue: 3 Year: 2024 Views : 649
Abstract:
Additive Manufacturing (AM) processes, such as Fused Deposition Modelling (FDM), are increasingly used to fabricate functional parts using Acrylonitrile Butadiene Styrene (ABS) material in which the tensile strength of 3D printed materials, such as those fabricated using Acrylonitrile Butadiene Styrene (ABS), is a critical mechanical property that determines their suitability for various applications. However, predicting the tensile strength of these parts remains challenging due to the complex interplay of various printing parameters. This study proposes a machine learning approach to predict the tensile strength of ABS parts based on their defined printing parameters such as Layer height, Infill density, printing speed, nozzle temperature and Bed temperature. In order to conduct the experiment, Taguchi’s Design of the Experiment is employed to create an L25 orthogonal array sample dataset. This dataset encompasses a range of combinations of the printing parameters, allowing for a comprehensive analysis of their effect on Tensile strength. The machine learning algorithms are then applied to this dataset, and their performance is compared to identify the most accurate model-fit. Using a Universal testing machine the tensile strength value of each specimen is known. From these experiment values, A machine learning model was trained and validated, Various machine learning algorithms, like linear regression, random forest regressor, are employed to model and analyze the complex relationships between the printing parameters and Tensile strength. The best machine learning model is selected based on the least error.
Leave Your Comment

Related Reviewers

Chat with Expert