Modelling and optimization of laser engraving qualitative characteristics of Al-SiC composite using response surface methodology and artificial neural networks
| Autor: | Rassoul Noorossana, Mahdi Shayganmanesh, Farhad Pazhuheian, Mohammad Hosein Rahimi |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Mathematical model
Artificial neural network Central composite design Computer science Laser engraving Empirical modelling Feed forward Mechanical engineering 02 engineering and technology 021001 nanoscience & nanotechnology Engraving 01 natural sciences Atomic and Molecular Physics and Optics Electronic Optical and Magnetic Materials 010309 optics visual_art 0103 physical sciences visual_art.visual_art_medium Response surface methodology Electrical and Electronic Engineering 0210 nano-technology |
| Zdroj: | Optics & Laser Technology. 112:65-76 |
| ISSN: | 0030-3992 |
| DOI: | 10.1016/j.optlastec.2018.10.058 |
| Popis: | This work deals with the study of laser engraving process of Al-SiC composite by Q-switched Nd:YAG laser. A series of experiments have been conducted to investigate the effect of process parameters such as assistant gas flow, distance between surface of workpiece and beam focus location (defocus), repetition rate frequency, and pumping current on the quality parameters such as depth, width, and contrast of engraved zone. A central composite design method was used to design experiments based on the response surface methodology (RSM). Empirical models were developed to create relationships between control factors and response variables by considering analysis of variance (ANOVA). To estimate the qualitative characteristics of the process, a feed forward back-propagation neural network (FF-BPNN) was used and accuracy of BPNN method was compared with mathematical models based on RSM model. Finally, the desirability function was used to optimize the multiple responses. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect