Design Optimization of Components for Additive Manufacturing-Repair: An Exploration of Artificial Neural Network Requirements and Application
Keywords:
Additive manufacturing, (ANN), hybrid artificial intelligence, design optimization, restorationAbstract
The integration of artificial intelligence (AI) in additive manufacturing (AM) technology is currently a promising and leading area of research for component repair and restoration. The Issues of high cost and time consumption for AM repair have been a subject of discussion among researchers in this field of study. Moreover, the potential challenges in dealing with complex components for repair and restoration in the (AM) domain require the establishment of a critical technical platform based on hybrid (AI). At this point, the proposed optimization method must cover all important parameters for the complex configuration of structural components under restoration. For the purpose of this study, a design optimization framework was developed using a MATLAB-SIMULINK mathematical model for AM solution purposes by improving the functionality and integration of monitoring. This improvement is based on facilitating the real-time identification of failures with accuracy and giving a clear monitoring vision according to the intended targets like geometric distortions, residual stresses evaluation, and defect characterization. The improvement involves overcoming a number of challenges such as the pre-fabrication stage by expanding the data repository besides offering a theoretical set of algorithmic with some options that improve the current procedure. Also, this study will conclude and suggest a further framework and new knowledge for restoration and product life cycle extension. This developed ANN can be used at the real pace of modeling the MATLAB-Simulink system and merged with another suitable algorithm to form a hybrid ANN. This model development using a neural network has attained a good manipulation of AM. The predicted data from ANN model that was determined and achieved in this study can be used to facilitate and enhance any further study as base knowledge in merging the ANN with another AI to form a hybrid algorithm.
Downloads
Downloads
Published
Issue
Section
License
Copyright (c) 2023 International Journal of Integrated Engineering
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Open access licenses
Open Access is by licensing the content with a Creative Commons (CC) license.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.