Optimization of the operational parameters in a fast axial flow CW CO2 laser using artificial neural networks and genetic algorithms

Adineh, V. R.; Aghanajafi, Cyrus; Dehghan, Gholamhossein; Jelvani, S.

doi:10.1016/j.optlastec.2008.03.003

Cited by 34 publications

(14 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, a hybrid method for choosing the optimal number of nodes for hidden layers is proposed. This is a hybrid of the empirical formula given by [38] with the increasing method [39]. In this hybrid method, at first the maximum number of nodes for hidden layers is chosen according to the following equation: h 2 i +1, where h and i are the number of hidden and input units respectively [38].…”

Section: Processingmentioning

confidence: 99%

Strength modeling and optimizing ultrasonic welded parts of ABS-PMMA using artificial intelligence methods

Norouzi

Adineh

2011

Int J Adv Manuf Technol

View full text Add to dashboard Cite

The present work deals with modeling and optimization of ultrasonic welding (USW) process parameters including welding time, pressure, and vibration amplitude influencing strength of the welded parts of acrylonitrile butadiene styrene (ABS) and poly(methyl methacrylate) (PMMA) using artificial intelligence (AI) methods. Experiments performed on samples by spot welding workpieces of ABS and PMMA. The experimental data are used for training of artificial neural networks (ANN), adaptive neuro-fuzzy inference systems, and hybrid systems. It is found that ANN had better predictions compared with the other AI methods. The best model was a feed-forward back-propagation network, with uniform transfer functions (TANSIG-TANSIG-TANSIG) and 4/2 neurons in the first/second hidden layers. The best predictor is then presented to genetic algorithm (GA) and particle swarm optimization (PSO), as the fitness function and for optimizing the USW machine parameters. After the optimization, results of this part revealed that GA and PSO have comparable results and the calculated strength increased by 10%, as compared with a non-optimized case. In order to confirm the computational results, validating experiments are performed which their outputs demonstrates good agreement with the optimization result.

show abstract

Section: Processingmentioning

confidence: 99%

Strength modeling and optimizing ultrasonic welded parts of ABS-PMMA using artificial intelligence methods

Norouzi

Adineh

2011

Int J Adv Manuf Technol

View full text Add to dashboard Cite

show abstract

“…GAs are robust optimizers that can handle real/discrete variables [30]. GA is able to search very large solution spaces effectively by providing a lower computational time [31]. Since the space of different combinations of features is a very large and complex space, employing GA for exploring this space provides a more effective search.…”

Section: Rgaci Model For Constructive Inductionmentioning

confidence: 99%

“…Crossover operator is mostly responsible for the progress of search. It swaps the parent strings partially, causing the offsprings to be generated [31].…”

Section: B Crossover Operatormentioning

confidence: 99%

A real-coded genetic algorithm for constructive induction

HajAbedi

2009

2009 IEEE Congress on Evolutionary Computation

View full text Add to dashboard Cite

Constructive Induction (CI) is a process applied to representation space prior to learning algorithms. This process transforms original representation space into a representation that highlights regularities. In this new improved space learning algorithms work more effectively, generating better solutions. Most CI methods apply a greedy strategy to improve representation space. Greedy methods might converge to local optima, when search space is complex. Genetic Algorithms (GA) as a global search strategy is more effective in such situations. In this paper, a real-coded GA (RGACI) model is represented for CI. This model optimizes the representation space by discretization of feature's values, constructing new features with a GA and evaluation and selection of features upon a PNN Classifier accuracy. Results reveal that PNN Classifier accuracy will improved considerably after it is integrated with RGACI model.

show abstract

“…The main high-power CO 2 lasers used for laser processing contain multichannel slab discharge CO 2 lasers [1][2][3][4][5], waveguide CO 2 lasers [6][7][8], transverse flow CW CO 2 lasers [9][10][11], fast axial flow CW CO 2 lasers [12][13][14], and axisymmetric-fold combination cavity (ASFC) CO 2 lasers [15][16][17][18][19][20]. The above CO 2 lasers have many advantages; for example, the waveguide and slab CO 2 lasers with output power of 500-1000 W have a small volume and can be fixed directly with machine tools for laser processing.…”

Section: Introductionmentioning

confidence: 99%

Misalignment analysis of combination-cylinder discharge CO_2 laser

2014

Appl. Opt.

View full text Add to dashboard Cite

The axes of a laser resonator will deviate away from the initial places when the combination-cylinder discharge CO₂ laser (CCDCL) is misaligned. The new cavity axes are established through using the misaligned augmented matrixes. The influences of the misalignments on the properties of the laser beams are studied in detail, such as the line deviations and angle deviations of oscillation beams in CCDCL, the near- and far-field distribution of output beams, the diffraction loss and output power, and the beam quality factor. It is shown that the influences of the misalignments on the above properties of the laser beams are obvious when the misaligned angle of the laser resonator exceeds 30 s. The studied results can afford references for the design of a CCDCL.

show abstract

Optimization of the operational parameters in a fast axial flow CW CO2 laser using artificial neural networks and genetic algorithms

Cited by 34 publications

References 13 publications

Strength modeling and optimizing ultrasonic welded parts of ABS-PMMA using artificial intelligence methods

Strength modeling and optimizing ultrasonic welded parts of ABS-PMMA using artificial intelligence methods

A real-coded genetic algorithm for constructive induction

Misalignment analysis of combination-cylinder discharge CO_2 laser

Contact Info

Product

Resources

About