Analysis of wear assessment of FDM printed ABS specimens using hybrid artificial intelligent soft computing techniques.

Abstract

Fused Deposition Modeling (FDM) is gaining significant recognition among researchers for its capability in advanced material innovation and complex design fabrication. The performance of FDM-fabricated components is heavily influenced by input parameters, which play a critical role in determining wear characteristics. This study focuses on investigating the wear behavior of FDM-printed acrylonitrile butadiene styrene (ABS) specimens. An optimal custom design approach, rooted in response surface methodology (RSM), was employed to construct an experimental matrix encompassing 17 distinct parameter combinations. These specimens were fabricated using a MakerBot Method X printer and tested for wear resistance using a Pin-on-Disc setup in compliance with ASTM G99 standards. To achieve optimized wear performance, a hybrid artificial intelligence (AI) framework integrating Artificial Neural Networks (ANN) with Genetic Algorithm (GA) was implemented. This approach facilitated the prediction and minimization of specific wear rate (SWR), achieving an optimized value of 28.79×10-7 mm3/Nm, experimentally validated with a high accuracy of 98.92%. The wear morphology analysis using Field Emission Scanning Electron Microscopy (FESEM) revealed a significant reduction in surface damage for the optimized specimens. The findings highlight the effectiveness of hybrid optimization techniques, such as ANN and GA, in enhancing the tribological properties of FDM components.