Machine learning methods for prediction analyses of 4H–SiC microfabrication via femtosecond laser processing
Source abstract
Abstract
In this study, the effects of processing parameters on the geometry of femtosecond laser fabricated microgrooves on 4H–SiC wafer were investigated. To achieve a fast, accurate and intelligent manufacturing process, response surface methodology (RSM) and artificial neural network (ANN) method were applied for modeling and predicting the geometric features of microgrooves. In addition, analysis of variance (ANOVA) was employed to determine the most significant input variables on the responses. The RSM result showed that the third-order polynomial model equation was in high accordance with the experiments. During the analysis, laser power, scanning speed, and scanning times were set as input variables, and the depth, width and surface roughness (Ra) were set as response/output variables. Finally, the predictive capabilities of the RSM and ANN models were compared with each other in terms of coefficient of determine (R2), root mean squared error (RMSE), and relatively error (RE). The results indicated that the ANN method have a higher accuracy compared to those of the RSM model.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Surface Polishing Techniques · Advanced Machining and Optimization Techniques · Advanced machining processes and optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (39)
Show source-provided references
1. A survey of wide bandgap power semiconductor devices10.1109/TPEL.2013.2268900 ↗
2. Silicon carbide as a platform for power electronics10.1126/science.1168704 ↗
3. Highly efficient planarization of sliced 4H–SiC (0001) wafer by slurryless electrochemical mechanical polishing10.1016/j.ijmachtools.2019.103431 ↗
4. Study of Schottky barrier detectors based on a high quality 4H-SiC epitaxial layer with different thickness10.1016/j.apsusc.2020.147801 ↗
5. Foreword to the special issue on wide-bandgap (WBG) semiconductors: from fundamentals to applications10.1016/j.npe.2021.01.001 ↗
6. High efficient polishing of sliced 4H-SiC (0001) by molten KOH etching10.1016/j.apsusc.2020.146532 ↗
7. Preparation and analysis of micro-holes in C/SiC composites and ablation with a continuous wave laser10.1016/j.jeurceramsoc.2020.08.033 ↗
8. Study on precision dicing process of SiC wafer with diamond dicing blades10.1063/10.0005152 ↗
9. Characterization of a hybrid laser-assisted mechanical micromachining (LAMM) process for a difficult-to-machine material10.1016/j.ijmachtools.2006.09.004 ↗
10. Characterization and prediction of the heat-affected zone in a laser-assisted mechanical micromachining process10.1016/j.ijmachtools.2008.01.004 ↗
11. Ultra-short pulsed laser manufacturing and surface processing of microdevices10.1016/j.eng.2018.10.004 ↗
12. Study on the effect of cutting parameters on bamboo surface quality using response surface methodology10.1016/j.measurement.2021.109002 ↗
13. Design and optimization of turbine blade preform forging using RSM and NSGA II10.1007/s10845-015-1058-0 ↗
14. Modeling and optimization of tool vibration and surface roughness in boring of steel using RSM, ANN and SVM10.1007/s10845-016-1197-y ↗
15. Optimization of drilling parameters using Taguchi technique and response surface methodology (RSM) in drilling of AISI 304 steel with cryogenically treated HSS drills10.1007/s10845-013-0783-5 ↗
16. Experimental investigations on the laser-assisted machining of single crystal Si for optimal machining10.1016/j.optlastec.2021.107113 ↗
17. Estimation of mechanical properties of friction stir processed Al 6061/Al2O3-Tib2 hybrid metal matrix composite layer via artificial neural network and response surface methodology
18. An inverse model for injection molding of optical lens using artificial neural network coupled with genetic algorithm10.1007/s10845-014-0999-z ↗
19. Process parameter optimization for laser-magnetic welding based on a sample-sorted support vector regression10.1007/s10845-017-1378-3 ↗
20. Optimizing pulsed Nd:YAG laser beam welding process parameters to attain maximum ultimate tensile strength for thin AISI316L sheet using response surface methodology and simulated annealing algorithm10.1016/j.optlastec.2017.12.042 ↗
21. Analysis of the effect of friction stir welding parameters on characteristics of AA6061 composites using response surface methodology10.1007/s12666-021-02214-9 ↗
22. Response surface and corrosion behavior analysis of nanosecond laser patterned ZK60A magnesium alloy10.1016/j.optlastec.2021.107501 ↗
23. An artificial neural network approach for the control of the laser milling process10.1007/s00170-012-4457-9 ↗
24. Application of artificial neural network in predicting the wear rate of copper surface composites produced using friction stir processing
25. Prediction of laser drilled hole geometries from linear cutting operation by way of artificial neural networks10.1007/s00170-021-06857-2 ↗
26. Modelling and optimization of laser engraving qualitative characteristics of Al-SiC composite using response surface methodology and artificial neural networks10.1016/j.optlastec.2018.10.058 ↗
27. Modelling and optimisation of hardness behaviour of sintered Al/SiC composites using RSM and ANN: a comparative study10.1016/j.jmrt.2020.09.087 ↗
28. Optimization of laser cutting parameters for Al6061/SiCp/Al2O3 composite using grey based response surface methodology (GRSM)10.1016/j.measurement.2015.06.003 ↗
29. Modeling and optimization on Nd:YAG laser turned micro-grooving of cylindrical ceramic material10.1016/j.optlaseng.2009.03.016 ↗
30. Role of trochoidal machining process parameter and chip morphology studies during end milling of AISI D3 steel10.1007/s10845-019-01517-5 ↗
31. Evaluation of thermal conductivity of COOH-functionalized MWCNTs/water via temperature and solid volume fraction by using experimental data and ANN methods10.1007/s10973-015-4565-5 ↗
32. Applicability of artificial neural network and nonlinear regression to predict mechanical properties of equal channel angular rolled Al5083 sheets10.1590/1679-78252154 ↗
33. Laser power based surface characteristics models for 3-D printing process10.1007/s10845-015-1167-9 ↗
34. Ultrasound assisted extraction of phenolic compounds from P. lentiscus L. leaves: comparative study of artificial neural network (ANN) versus degree of experiment for prediction ability of phenolic compounds recovery10.1016/j.indcrop.2015.08.062 ↗
35. Extraction of phenolic compounds from cocoa shell: modeling using response surface methodology and artificial neural networks10.1016/j.seppur.2021.118779 ↗
36. Comparative study of ANN and RSM for simultaneous optimization of multiple targets in Fenton treatment of landfill leachate10.1016/j.wasman.2017.03.048 ↗
37. Femtosecond laser micromachining of grooves in silicon with 800 nm pulses10.1007/s00339-004-2941-2 ↗
38. Influence of laser cutting parameters on CFRP part quality10.1016/j.phpro.2010.08.051 ↗
39. Comparison of RSM with ANN in predicting tensile strength of friction stir welded AA7039 aluminium alloy joints10.1016/S1003-6326(08)60221-6 ↗