Machine learning approach for prediction analysis of aluminium alloy on the surface roughness using CO 2 laser machining

Abstract

A comprehensive analysis investigated the impact of cutting speed, nozzle diameter, gas pressure and the addition of SiC and ZrO₂ particles on the surface quality of aluminum alloy 6062. The correlation between experimental and predicted values was established using deep neural network (DNN), support vector machine regression and response surface methodology. To validate the models, root mean squared error and mean absolute error were computed for four hidden layers with the DNN approach. The surface roughness was significantly affected by the higher cutting speed (3000 mm/min) and lower nitrogen gas pressure (10 bar). The results from the developed models closely matched experimental data. Additionally, the study analyzed the impact of laser parameters on crack width due to rapid thermal changes. The scanning electron microscopy, energy-dispersive X-ray spectroscopy and optical microscopy were utilized to examine the laser-cut surface's microstructure for crack formation analysis.

Keywords

Deep neural network support vector machine regression crack formation

Get full access to this article

View all access options for this article.

References

Wang

, et al. Machine learning methods for prediction analyses of 4HeSiC microfabrication via femtosecond laser processing. J Mater Res Technol 2022; 18: 2152–2165.

Sivanaga Malleswara Rao

Venkata Rao

Hemachandra Reddy

KS,

et al. Prediction and optimization of process parameters in wire cut electric discharge machining for high-speed steel (HSS). Int J Comput Appl 2017; 39: 140–147.

Xia

Zengxi

, et al. Modelling and prediction of surface roughness in wire arc additive manufacturing using machine learning. J Intell Manuf 2021; 33: 1467–1482.

Dazhong

Yupeng

, et al. Predictive modelling of surface roughness in fused deposition modelling using data fusion. Int J Prod Res 2019; 57: 3992–4006.

Jennings

, et al. A comparative study on machine learning algorithms for smart manufacturing: tool wear prediction using random forests. J Manuf Sci Eng 2017; 139: 071018 (9 pages).

Tian

Luo

. A study on the prediction of inherent deformation in fillet-welded joint using support vector machine and genetic optimization algorithm. J Intell Manuf 2020; 31: 575–596.

Yusoff

Mohd Zain

Sharif

, et al. Potential ANN prediction model for multiperformances WEDM on Inconel 718. Neural Comput Appl 2018; 30: 2113–2127.

Amini

Yazdi

, et al. Optimization of process parameters in wire electrical discharge machining of TiB2 nanocomposite ceramic. Proc Inst Mech Eng, Part B 2011; 225. DOI: 10.1177/0954405411412249.

Butola

Singari

Murtaza

, et al. Comparison of response surface methodology with artificial neural network for prediction of the tensile properties of friction stir-processed surface composites. Proc Inst Mech Eng, Part B 2022; 236(1): 126–137.

10.

Patange

Jegadeeshwaran

. A machine learning approach for vibration-based multipoint tool insert health prediction on vertical machining centre (VMC). Measurement (Mahwah N J) 2021; 173: 108649.

11.

Rahimi

Shayganmanesh

Noorossana

, et al. Modelling and optimization of laser engraving qualitative characteristics of Al-SiC composite using response surface methodology and artificial neural networks. Opt Laser Technol 2019; 112: 65–76.

12.

Gautam

Mishra

, et al. Firefly algorithm based optimization of kerf quality characteristics in pulsed Nd:YAG laser cutting of basalt fiber reinforced composite. Composite Part B 2019; 176: 107340.

13.

Wang

Xie

Lou

, et al. Algal bloom prediction by support vector machine and relevance vector machine with genetic algorithm optimization in freshwater reservoirs. Eng Comput 2017; 34: 664–679.

14.

Karabulut

Karakoc

Çıtak

. Influence of B4C particle reinforcement on mechanical and machining properties of Al6061/ B4C composites. Compos Part B Eng 2016; 101: 87–98.

15.

Yilbas

S. Laser cutting of thick sheet metals: effects of cutting parameters on kerf size variations. J Mater Process Technol 2008; 201: 285–290.

16.

Cheng

Y-N

Jin

Y-B

Gai

X-Y

, et al. Prediction of tool wear in milling process based on BP neural network optimized by firefly algorithm. Proc Inst Mech Eng, Part B. 2023. DOI: 10.1177/09544089231160492.

17.

Reza Kashyzadeh

Ghorbani

. New neural network-based algorithm for predicting fatigue life of aluminum alloys in terms of machining parameters. Eng Fail Anal 2023; 146: 107128.

18.

Araujo

Carpio

Mendez

, et al. Microstructural study of CO₂ laser machined heat affected zone of 2024 aluminum alloy. Appl Surf Sci 2007; 208: 210–217.

19.

Mathew

Moat

Paddea

, et al. Prediction of residual stresses in girth welded pipes using an artificial neural network approach. Int J Press Vessels Pip 2017; 150: 89–95. DOI: 10.1016/j.ijpvp.2017.01.002.

20.

Sarkheyli

Zain

Sharif

. A multi-performance prediction model based on ANFIS and new modifed-GA for machining processes. J Intell Manuf 2015; 26: 703–716.

21.

Biswal

Tripathy

. Machining performance analysis for PMEDM of biocompatible material Ti-6Al-7Nb alloy: a machine learning approach. Mater Lett 2022; 320: 132337.

22.

Nicholas

Monica

, et al. Application of machine learning for improved surface quality classification in ultra-precision machining of germanium. J Mfg Systems 2022; 65: 296–316.

23.

Singh

Deepika

Belokar

, et al. Experimental probe on machining attributes of Al 7075-T6/SiC/crumb rubber/MoS2-based green hybrid composite using artificial neural network model. Proc Inst Mech Eng, Part B 2023; 237; 1643–1652.

24.

Satish

Arun Kumar

Chandna

, et al. A novel approach of GEF and GA for the optimization of multi-objective wire EDM process during the machining of DC53 super alloy. Proc Inst Mech Eng, Part B 2021; 235: 1119–1131.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.24 MB