Hybrid neural network–particle swarm optimization algorithm and neural network–genetic algorithm for the optimization of quality characteristics during CO2 laser cutting of aluminium alloy

Vagheesan, Senthilkumar; Jayaprakash, G.

doi:10.1007/s40430-019-1830-8

Cited by 23 publications

(11 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also utilized a genetic algorithm for optimizing the output parameters [11]. Vagheesan et al [12] also applied a neural network and particle swarm optimization (PSO) based modelling and optimization approach for the study of laser cutting (CO2 laser) of aluminium alloys. Norkey et al [13] also attempted an ANN-based modelling technique for studying the HAZ for laser machining of aerospace material like duralumin.…”

Section: Introductionmentioning

confidence: 99%

Dual-stage artificial neural network (ANN) model for sequential LBMM-μEDM-based micro-drilling

Noor

Saleh

Rashid

et al. 2021

Int J Adv Manuf Technol

View full text Add to dashboard Cite

A sequential process combining laser beam micromachining(LBMM) and micro electrodischarge machining (μEDM) for the micro-drilling purpose was developed to incorporate both methods' benefits. In this sequential process, a guiding hole is produced through LBMM first, followed by μEDM applied to that same hole for more fine machining. This process facilitates a more stable, efficient machining regime with faster processing (compared to pure μEDM) and much better hole quality (compared to LBMMed holes). Studies suggest that strong correlations exist between the various input and output parameters of the sequential process. However, a mathematical model that maps and simultaneously predicts all these output parameters from the input parameters is yet to be developed. Our experimental study observed that the µEDM finishing operation's various output parameters are influenced by the morphological condition of the LBMMed holes. Hence, an artificial neural network(ANN) based dual-stage modelling method was developed to predict the sequential process's outputs. The first stage of the dual-stage model was utilized to predict various LBMM process outputs from different laser input parameters. Furthermore, in the second stage, LBMM predicted outputs (such as pilot hole entry area, exit area, recast layer, and heat affected zone) were used for the final prediction of the sequential process outputs (i.e. machining time by μEDM, machining stability during μEDM in terms of short circuit count and tool wear during μEDM). The model was evaluated based on the average RMSE (Root Mean Square Errors) values for the individual output parameters' complete set data, i.e. μEDM time, short circuit count and tool wear. The values of Average RMSE for the parameters as mentioned earlier were found to be 0.1272(87.28% accuracy), 0.1085(89.15% accuracy), 0.097 (90.3% accuracy), respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Dual-stage artificial neural network (ANN) model for sequential LBMM-μEDM-based micro-drilling

Noor

Saleh

Rashid

et al. 2021

Int J Adv Manuf Technol

View full text Add to dashboard Cite

show abstract

“…Vagheesan and Govindarajalu [11] presented the experiments were carried out based on neural network-genetic algorithm for the optimization.…”

Section: Literature Reviewmentioning

confidence: 99%

Optimization of responses in electron beam welding of inconel-718 alloy using genetic algorithm approach

Vishnu¹,

Satheesh²,

Dhas³

et al. 2021

IJATEE

View full text Add to dashboard Cite

Inconel 718 alloy is a chromium-titanium-nickelbased austenitic alloy with increased strength and better resistance to carburization and oxidation at increased temperatures. This is an important and efficient alloy material for the power plants of next generation [1]. These alloys can be used in sea water, power plant applications with temperature ranges up to 900ºC. The combination of resistance and the improved mechanical property makes this alloy useful in case of various applications, such as exposure of long-term and higher temperatures in corrosive area. High temperature tubes of heat exchanger in gascooled nuclear reactors and super heater tubes are the other applications of Inconel 718 alloy [2]. In addition, EBW process is a metal fabrication technique in the presence of multi-factors and multi-objectives. *Author for correspondenceThis connection of normal metals, like aluminium, steel, and magnesium of 1mm to 6mm thickness in almost all positions can be done using this process [3]. The weld joint quality highly depends on the parameters of the input process and the control of this input process parameter acts as a basic problem to the manufacturer in obtaining increased weld quality in welded joint [4]. Highly skilled engineers or operators select the parameters depending on trial and error method in order to produce a welded joint with necessary indications, but the selection of parameters using this method was time consuming [5]. The welds are utilized to find, whether they are suitable to meet the all the required specification [6]. Many researchers have studied the effect of mechanical properties of Inconel-718 alloy material and few authors published about fabrication, solidification and characterization of these alloys. It is understood that there is lack of papers on the effect of electron beam welding parameters and with their responses of bead width and depth of penetration with quality optimization.

show abstract

“…Currently, laser cutting is frequently used, being one of the modern processes for cutting a wide variety of materials. Research was developed on laser cutting of metallic materials such as: mild steels, alloy steels, aluminum, nickel alloys, titanium, or very hard materials [ 3 , 6 , 7 , 8 ].…”

Section: Introductionmentioning

confidence: 99%

“…The main characteristics of Hardox 400 steel are: high wear resistance, excellent corrosion resistance, good weldability, good strength-to-weight ratio, good cold plastic deformation properties, high fatigue resistance, and good impact load resistance. In addition, the material is not intended for additional heat treatment [ 7 , 9 ].…”

Section: Introductionmentioning

confidence: 99%

Simulation of Melting Efficiency in Laser Cutting of Hardox 400 Steel

Girdu

Gheorghe

2022

Materials

View full text Add to dashboard Cite

Laser cutting has experienced a sharp development in recent years due to the advantages it implies in industrial production, the most important being: great diversity of processed materials, reduced cutting time, low processing cost, small percentage of removed material, and low impact on the natural environment. The problem of energy has become acute in the last year, so a new direction of research has taken shape, consisting of the optimization of the high energy consumptions involved in laser cutting. The objective of this research is to develop a computational and experimental model to estimate the melting efficiency. Additionally, the research seeks to establish some mathematical relationships that describe the law of variation of the melting efficiency depending on the input parameters in the CO2 laser cutting. The experimental determinations were carried out on Hardox 400 steel plates of 8 mm thickness. The input parameters were laser power, assist gas pressure, and cutting speed. The experimental data were statistically processed, and the results were verified with the Lagrange interpolation method. It was found that the maximum melting efficiency is influenced mainly by laser power (F = 3.06; p = 0.049), followed by speed and pressure. The results obtained show that the melting efficiency varies in the range (13.6–20.68) mm3/KJ. The maximum value of the melting efficiency (20 J/mm3) was obtained when the laser power was 5100 W, the cutting speed 1900 mm/min, and the gas pressure 0.5 bar, and the minimum efficiency under conditions of speed setting at 1700 mm/min and laser power of 5000 W. Linear and quadratic regression models were established to estimate the global mean efficiency according to two independent variables that act at the same time. The established calculation relationships contribute to the improvement of the literature and constitute a tool for practical applications. The results obtained allow the modeling of cutting parameters and the optimization of production costs in industrial processes that use laser cutting.

show abstract

Hybrid neural network–particle swarm optimization algorithm and neural network–genetic algorithm for the optimization of quality characteristics during CO2 laser cutting of aluminium alloy

Cited by 23 publications

References 27 publications

Dual-stage artificial neural network (ANN) model for sequential LBMM-μEDM-based micro-drilling

Dual-stage artificial neural network (ANN) model for sequential LBMM-μEDM-based micro-drilling

Optimization of responses in electron beam welding of inconel-718 alloy using genetic algorithm approach

Simulation of Melting Efficiency in Laser Cutting of Hardox 400 Steel

Contact Info

Product

Resources

About