scholarly journals A generalised approach on kerf geometry prediction during CO2 laser cut of PMMA thin plates using neural networks

2021 ◽  
Author(s):  
John Dimitrios Kechagias ◽  
Konstantinos Ninikas ◽  
Panagiotis Stavropoulos ◽  
Konstantinos Salonitis
Keyword(s):  
Laser Cutting ◽  
Linear Models ◽  
Cutting Speed ◽  
Thin Plates ◽  
Anova Analysis ◽  
Analysis Of Means ◽  
Kerf Angle ◽  
Precise Prediction ◽  
Parameter Values ◽  
Full Factorial

Abstract This study presents an application of feedforward and backpropagation neural network (FFBP-NN) for predicting the kerf characteristics, i.e. the kerf width in three different distances from the surface (upper, middle and down) and kerf angle during laser cutting of 4 mm PMMA (polymethyl methacrylate) thin plates. Stand-off distance (SoD: 7, 8 and 9 mm), cutting speed (CS: 8, 13 and 18 mm/sec) and laser power (LP: 82.5, 90 and 97.5 W) are the studied parameters for low power CO2 laser cutting. A three-parameter three-level full factorial array has been used, and twenty-seven (33) cuts are performed. Subsequently, the upper, middle and down kerf widths (Wu, Wm and Wd) and the kerf angle (KA) were measured and analysed through ANOM (analysis of means), ANOVA (analysis of variances) and interaction plots. The statistical analysis highlighted that linear modelling is insufficient for the precise prediction of kerf characteristics. An FFBP-NN was developed, trained, validated and generalised for the accurate prediction of the kerf geometry. The FFBP-NN achieved an R-all value of 0.98, in contrast to the ANOVA linear models, which achieved Rsq values of about 0.86. According to the ANOM plots, the parameter values which optimize the KA resulting in positive values close to zero degrees were the 7 mm SoD, 8 mm/s CS and 97.5 W LP.

scholarly journals A generalised approach on kerf geometry prediction during CO2 laser cut of PMMA thin plates using neural networks

2021 ◽  
Author(s):  
John Dimitrios Kechagias ◽  
Konstantinos Ninikas ◽  
Panagiotis Stavropoulos ◽  
Konstantinos Salonitis
Keyword(s):  
Laser Cutting ◽  
Linear Models ◽  
Cutting Speed ◽  
Kerf Width ◽  
Thin Plates ◽  
Beam Power ◽  
Linear Modeling ◽  
A Value ◽  
Kerf Angle ◽  
Precise Prediction

Abstract This study presents an application of feedforward and backpropagation neural network (FFBP-NN) for predicting the kerf characteristics, i.e. the kerf width in three different distances from the surface (upper, middle and down) and kerf angle during laser cutting of PMMA thin plates. Stand-off distance, cutting speed and beam power are the studied parameters for the case of low power CO2 laser cutting. A three-parameter three-level full factorial array has been used and twenty-seven (33) cuts were performed. Subsequently, the kerf width and angle were measured and analysed through ANOM, ANOVA and interaction plots. The statistical analysis highlighted that linear modeling is insufficient for the precise prediction of kerf characteristics. A FFBP-NN was developed, trained, validated and generalised for the accurate prediction of the kerf geometry. The FFBP-NN achieved an R-sq value of 0.98, in contrast to the ANOVA linear models which achieved a value of about 0.90.

scholarly journals Effect of Process Parameters on the Quality of Laser-Cut Stainless Steel Thin Plates

Metals ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 1224
Author(s):  
Irene Buj-Corral ◽  
Lluís Costa-Herrero ◽  
Alejandro Domínguez-Fernández
Keyword(s):  
Process Parameters ◽  
Laser Cutting ◽  
Pulse Width ◽  
High Speed ◽  
Linear Models ◽  
Dimensional Accuracy ◽  
Pulse Frequency ◽  
Thin Plates ◽  
Dimensional Error ◽  
Frequency Pulse

At present, laser cutting is currently employed to cut metallic plates, due to their good finish and dimensional quality, as well as because of the flexibility of the process to obtain different shapes. In the present paper, surface roughness, dimensional accuracy, and burr thickness of thin plates of 0.8 mm are studied as functions of different process parameters: pulse frequency, pulse width, and speed. Eight different experiments were performed according to a full 23 factorial design, with two replicates each. Square specimens of 10 mm × 10 mm were cut. Arithmetical mean roughness Ra was measured with a contact roughness meter, and the dimensions and burr thickness with a micrometer. Ra values ranged between 1.89 and 3.86 µm, dimensional error values between 0.22 and 0.93%, and burr thickness between 2 and 34 µm. Regression analysis was performed, and linear models were obtained for each response. Results showed that roughness depends mainly on frequency, on the interaction of frequency and pulse width and on pulse width. The dimensional error depends on pulse width, frequency, and the interaction between pulse width and speed. Burr thickness is influenced by frequency, pulse width, and the interaction between frequency and speed. Multi-objective optimization showed that, in order to simultaneously minimize the three responses, it is recommended to use high frequency (80 Hz), high pulse width (0.6 ms), and high speed (140 mm/min). The present study will help to select appropriate laser cutting conditions in thin plates, in order to favor good surface finish and dimensional accuracy, as well as low burr thickness.

EXPERIMENTAL STUDY ON THE CO2 LASER CUTTING OF NOVEL POLYAMIDE 6/FLUOROELASTOMER THERMOPLASTIC ELASTOMERIC BLENDS

2015 ◽  
Vol 88 (1) ◽  
pp. 125-137 ◽  
Author(s):  
Shib Shankar Banerjee ◽  
Anil K. Bhowmick
Keyword(s):  
Low Power ◽  
Co2 Laser ◽  
Process Parameters ◽  
Laser Power ◽  
Laser Cutting ◽  
Manufacturing Industry ◽  
Cutting Speed ◽  
Polyamide 6 ◽  
Thermoplastic Elastomers ◽  
Dynamic Vulcanization

ABSTRACT The application of the low-power CO2 laser-cutting process to fluoroelastomer (FKM), polyamide 6 (PA6), PA6/FKM thermoplastic elastomers (TPEs), and their thermoplastic vulcanizate (TPV) is reported. The main laser process parameters studied were laser power, cutting speed, and material thickness. The value of the top and bottom widths of the slit that were formed during laser cutting (kerf width), melted transverse area, and melted volume per unit time were measured and analyzed. Interestingly, TPE showed a smaller melted area and melted volume per unit time when compared with those values with PA6. Dynamic vulcanization further decreased these values. For example, the melted areas of PA6 and TPE were 510 × 10−3 mm2 and 305 × 10−3 mm2, respectively, which reduced to 238 × 10−3 mm2 for TPV at 40 W laser power. FKM showed the lowest value (melted area of 180 × 10−3 mm2). In addition, the output quality of the cut surface was examined by measuring the root mean square (RMS) roughness of the cut edges and heat-affected zone (HAZ). The obtained results indicated that the dimension of the HAZ and RMS roughness largely decreased in TPE when compared with PA6. For example, the HAZ of PA6 was 700 μm, which decreased to 230 μm for TPE at 40 W laser power. On the other hand, HAZ was nonexistent for FKM. Infrared spectroscopic analysis showed that there was no structural change of TPE or pristine polymers after applying the low-power CO2 laser on the surface of materials. CO2 laser cutting will be a new technique in this industry, and this analysis will assist the manufacturing industry to choose a suitable laser system with exhaustive information of process parameters for cutting or machining of rubber, TPEs, and TPVs.

The Study of Quality Monitoring and Control for Laser Cutting Based on Pulse-Induced Acoustic Sound

2012 ◽  
Vol 182-183 ◽  
pp. 422-426 ◽  
Author(s):  
Hui Juan Hao ◽  
Guang He Cheng ◽  
Ji Yong Xu
Keyword(s):  
Adaptive Control ◽  
Laser Cutting ◽  
Cutting Speed ◽  
Processing Parameters ◽  
Wavelet Denoising ◽  
Quality Monitoring ◽  
Monitoring And Control ◽  
Time Frequency ◽  
And Control ◽  
The Impact

In this paper, the pulse-induced acoustic sound in laser cutting is collected, and the data processing is performed with wavelet denoising and time-frequncy analyzing. The impact of laser processing parameters on the acoustic signal is discussed; and further analysis of the effect of cutting speed is conducted. The corresponding relationship between the best velocity and the maximum time-frequency energy density is got; also the plan of adaptive control in laser cutting is designed. The results in this paper can provide important parameters for adaptive control of laser cutting.

Improvement of cutting performance for thick stainless steel plates by step-like cutting speed increase in high-power fiber laser cutting

2018 ◽  
Vol 103 ◽  
pp. 311-317 ◽  
Author(s):  
Sangwoo Seon ◽  
Jae Sung Shin ◽  
Seong Yong Oh ◽  
Hyunmin Park ◽  
Chin-Man Chung ◽  
...  
Keyword(s):  
Stainless Steel ◽  
Fiber Laser ◽  
High Power ◽  
Laser Cutting ◽  
Cutting Speed ◽  
Cutting Performance ◽  
Steel Plates ◽  
Speed Increase

scholarly journals STUDY OF AUXILIARY GAS PRESSURE ON LASER CUTTING TECHNOLOGY

2017 ◽  
Vol 3 ◽  
pp. 163
Author(s):  
Lyubomir Lazov ◽  
Hristina Deneva ◽  
Erika Teirumnieka
Keyword(s):  
Laser Power ◽  
Laser Cutting ◽  
Sheet Steel ◽  
Cutting Speed ◽  
Major Effect ◽  
Gas Pressure ◽  
Experimental Results ◽  
Focus Position ◽  
Angle Deviation ◽  
Basic Parameters

Two types of electrical sheet steel M250-35A and M530-50A were used to cut by melting with a TruLaser 1030 technological system. It was observed that pressure of auxiliary gas had a major effect on kerf width b and cut angle deviation α. Nitrogen as an assisted gas has been taken. The basic parameters as laser power, cutting speed, focus position were constantly supported and the pressure was changed from 4 bar to 20 bar by step 2 bar. As well as the experimental results of gas pressure on entrance and exit kerf widths, have been analyzed and discussed in this study.

Thermal hardening and calculation of the mathematical model of face milling of parts made of steel 95X18-Sh to improve the quality of the surface layer

2021 ◽  
pp. 200-206
Author(s):  
I.N. Sedinin ◽  
V.F. Makarov
Keyword(s):  
Mathematical Model ◽  
Cutting Speed ◽  
Physical And Mechanical Properties ◽  
Face Milling ◽  
Experiment Planning ◽  
Depth Of Cut ◽  
Machined Surface ◽  
The Mathematical Model ◽  
Full Factorial

It is considered the complex of operations of the technological process for the heat treatment of steel 95X18-Sh, as a result of which the material of the samples increases the hardness to 59...61 HRC, and also improves the physical and mechanical properties. A full-scale full factorial experiment of face milling of samples was carried out using the method of mathematical planning. In the experiments, a high-precision machine and a carbide cutting tool were used. To calculate the values of the roughness function, the following are taken as independent variables: cutting speed, feed per tooth and depth of cut. In order to determine the coefficients of the linear equation, a central compositional orthogonal plan of the second order for three factors was used. A matrix of levels of variation of independent variable factors and a matrix of experiment planning were compiled. A regression analysis of the obtained experimental statistical data was carried out using the Microsoft Excel, Statistica and Wolfram Alpha programs. As a result of the calculations, a mathematical model of the roughness of the machined surface and optimal cutting conditions were determined.

Analysis of process efficiency in laser fusion cutting and some single- and multi-objective optimization aspects

2021 ◽  
pp. 095440892110627
Author(s):  
Miloš Madić ◽  
Mohamed H Gadallah ◽  
Dušan Petković
Keyword(s):  
Laser Power ◽  
Laser Cutting ◽  
Optimization Problem ◽  
Removal Rate ◽  
Cutting Speed ◽  
Process Efficiency ◽  
Laser Fusion ◽  
Cut Quality ◽  
Dross Formation ◽  
Laser Fusion Cutting

For an efficient use of laser cutting technology, it is of great importance to analyze the impact of process parameters on different performance indicators, such as cut quality criteria, productivity criteria, costs as well as environmental performance criteria (energy and resource efficiency). Having this in mind, this study presents the experimental results of CO2 laser fusion cutting of AISI 304 stainless steel using nitrogen, with the aim of developing a semi-empirical mathematical model for the estimation of process efficiency as an important indicator of the achievable energy transfer efficiency in the cutting process. The model was developed by relating the theoretical power needed to melt the volume per unit time and used laser power, where the change of kerf width was modeled using an empirical power model in terms of laser cutting parameters such as laser power, cutting speed, and focus position. The obtained results indicated the dominant effect of the focus position on the change in process efficiency, followed by the cutting speed and laser power. In addition, in order to maximize process efficiency and simultaneously ensure high cut quality without dross formation, a laser cutting optimization problem with constraints was formulated and solved. Also, a multi-objective optimization problem aimed at simultaneous optimization of process efficiency and material removal rate was formulated and solved, where the determined set of Pareto non-dominated solutions was analyzed by using the entropy method and multi-criteria decision analysis method, that is, the Technique for Order of Preference by Similarity to Ideal Solution. The optimization results revealed that in order to enhance process efficiency and material removal rate, while ensuring high cut quality without dross formation, focusing the laser beam deep into the bulk of material is needed with particular trade-offs between laser power and cutting speed levels at high pressure levels of nitrogen.

scholarly journals Experimental Optimization of Nimonic 263 Laser Cutting Using a Particle Swarm Approach

Metals ◽  
2019 ◽  
Vol 9 (11) ◽  
pp. 1147 ◽  
Author(s):  
Sibalija ◽  
Petronic ◽  
Milovanovic
Keyword(s):  
Laser Cutting ◽  
Particle Swarm ◽  
Cutting Speed ◽  
Cutting Parameters ◽  
Parameter Tuning ◽  
Pso Algorithm ◽  
Ann Model ◽  
Suggested Approach ◽  
Process Measure ◽  
Control Factors

This paper presents an experimental study carried out on Nimonic 263 alloy sheets to determine the optimal combination of laser cutting control factors (assisted gas pressure, beam focus position, laser power, and cutting speed), with respect to multiple characteristics of the cut area. With the aim of designing laser cutting parameters that satisfy the specifications of multiple responses, an advanced multiresponse optimization methodology was used. After the processing of experimental data to develop the process measure using statistical methods, the functional relationship between cutting parameters and the process measure was determined by artificial neural networks (ANNs). Using the trained ANN model, particle swarm optimization (PSO) was employed to find the optimal values of laser cutting parameters. Since the effectiveness of PSO could be affected by its parameter tuning, the settings of PSO algorithm-specific parameters were analyzed in detail. The optimal laser cutting parameters proposed by PSO were implemented in the validation run, showing the superior cut characteristics produced by the optimized parameters and proving the efficacy of the suggested approach in practice. In particular, it is demonstrated that the quality of the Nimonic 263 cut area and the microstructure were significantly improved, as well as the mechanical characteristics.

Sign in / Sign up

Export Citation Format

Share Document