Title: Optimisation of natural frequency modes of FDM manufactured polycarbonate samples using I-optimal design and ANN-GA approach

Authors: Boppana V. Chowdary; Fahraz Ali

Addresses: Department of Mechanical and Manufacturing Engineering, The University of the West Indies, St. Augustine Campus, Trinidad and Tobago ' Department of Mechanical and Manufacturing Engineering, The University of the West Indies, St. Augustine Campus, Trinidad and Tobago

Abstract: Additive manufacturing (AM) offers tremendous potential for design novelty and customisation as well as complex component manufacturing and rapid prototyping. However, as the AM technologies are maturing, issues related to use of different materials and manufacturing reliable parts are still active areas of research. The current research focuses on implementation of machine learning based artificial neural network and genetic algorithm (ANN-GA) approach for optimisation of natural frequency. Further, I-optimal experimental design was selected for investigation of variations in raster angle, raster to raster air gap, build orientation and number of contours on natural frequency. The study found that the optimum natural frequency obtained by the ANN-GA methodology is superior over the traditional means. Moreover, variation of raster angle was observed to have the greatest influence on natural frequency with low raster angles producing higher frequencies. The proposed methodology can be extended to optimise various dynamic characteristics of 3D-printing parts.

Keywords: I-optimal design; fused deposition modelling; ANOVA; machine learning; artificial neural network; ANN; genetic algorithm; polycarbonate; natural frequency.

DOI: 10.1504/IJQET.2023.134885

International Journal of Quality Engineering and Technology, 2023 Vol.9 No.4, pp.321 - 348

Received: 09 Dec 2022
Accepted: 10 Aug 2023
Published online: 15 Nov 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article