The comparison of metaheuristic algorithms in parametric optimization of laser-based processes (original) (raw)
Related papers
International Journal of Advanced Intelligence Paradigms, 2012
In this study, eight population-based metaheuristic algorithms were employed for the design of truss structures with continuous design variables. The selected algorithms were genetic, ant colony, particle swarm, artificial bee colony, gravitational search, firefly, gray wolf optimization and Jaya. The purpose was to objectively evaluate the performance of these algorithms under the same conditions and select the best efficient algorithm by assessing three example truss structures. The results obtained from the examples showed that the algorithms were both computationally efficient and robust when the number of design variables was approximately 10 and a significant number of iterations were performed. When the number of design variables was increased to 53, artificial bee colony, Jaya and gray wolf optimization were found to be computationally more effective than the remaining algorithms.
Computer-aided genetic algorithm based multi-objective optimization of laser trepan drilling
The laser trepan drilling (LTD) has proven to produce better quality holes in advanced materials as compared with laser percussion drilling (LPD). But due to thermal nature of LTD process, it is rarely possible to completely remove the undesirable effects such as recast layer, heat affected zone and micro cracks. In order to improve the hole quality, these effects are required to be minimized. This research paper presents a computer-aided genetic algorithm-based multi-objective optimization (CGAMO) methodology for simultaneous optimization of multiple quality characteristics. The optimization results of the software CGAMO has been tested and validated by the published literature. Further, CGAMO has been used to simultaneously optimize the recast layer thickness (RLT) at entrance and exit in LTD of nickel based superalloy sheet. The predicted results show minimization of 99.82% and 85.06% in RLT at entrance and exit, respectively. The effect of significant process parameters on RLT has also been discussed.
Experimental Optimization of Nimonic 263 Laser Cutting Using a Particle Swarm Approach
Metals, 2019
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 par...
Materials Today: Proceedings, 2018
In the present research work, comparison of four different multi-response optimization techniques viz., multi-response signal-tonoise ratio (MRSN), weighted signal-to-noise ratio (WSN), grey relational grade analysis (GRA) and the technique for order preference by similarity to ideal solution method (TOPSIS) have been applied in a case study of laser welding process for joining automotive gears of 16MnCr5 Alloy Steel. It has been observed that (MRSN) method gives the closest results and can be considered as the best suitable method for this case. The authors conclude that this approach could be applicable for any manufacturing application.
This paper presents a new integrated methodology based on evolutionary algorithms (EAs) to model and optimize the laser beam cutting process. The proposed study is divided into two parts. Firstly, genetic programming (GP) approach is used for empirical modelling of kerf width (Kw) and material removal rate (MRR) which are the important performance measures of the laser beam cutting process. GP, being an extension of the more familiar genetic algorithms, recently has evolved as a powerful optimization tool for nonlinear modelling resulting in credible and accurate models. Design of experiments is used to conduct the experiments. Four prominent variables such as pulse frequency, pulse width, cutting speed and pulse energy are taken into consideration. The developed models are used to study the effect of laser cutting parameters on the chosen process performances. As the output parameters Kw and MRR are mutually conflicting in nature, in the second part of the study, they are simultaneously optimized by using a multi-objective evolutionary algorithm called nondominated sorting genetic algorithm II. The Pareto optimal solutions of parameter settings have been reported that provide the decision maker an elaborate picture for making the optimal decisions. The work presents a full-fledged evolutionary approach for optimization of the process.
Optimization of laser percussion drilling by using neural network For stainless steel 304
2000
This research is focused on laser percussion drilling optimization through integrating the neural network method with the Lonberg-Marcoitte(L-M). To begin with, optimum input parameters of the process were obtained in order to optimize every single output parameters (responses) ANN method was used to create an experimental model of the process based on the experimental results. Then optimum input parameters (peak
Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2013
Determination of optimal laser cutting parameter settings for obtaining high cut quality in CO 2 laser cutting process is of great importance. In this paper an attempt has been made to apply different optimization methods for determining of optimal values of laser power, cutting speed, assist gas pressure and focus position with the purpose of improving the cut quality characteristics obtained in the CO 2 laser cutting of stainless steel. The laser cutting experiment was planned and conducted according to the Taguchi's L 27 orthogonal array and the experimental data were used for developing mathematical models for surface roughness, kerf width and width of heat affected zone based on artificial neural networks (ANNs). Mathematical models of the cut quality characteristics were developed using single hidden layer ANN trained with Levenberg-Marquardt algorithm. This paper compares the quality of solutions obtained when optimizing ANN models using the real coded genetic algorithm (RCGA), simulated annealing (SA) and recently developed improved harmony search algorithm (IHSA). The computer code was written in MATLAB to integrate the ANN-based process models and the RCGA, SA and IHSA algorithms. For the purpose of comparison, some performance criteria were used. The merits and the limitations of the selected optimization methods were discussed.
This paper presents an investigation on single objective optimization for CO 2 laser cladding process considering clad height (H) and clad width (W) as performance characteristics. This optimization of multiple quality characteristics has been done using Genetic Algorithm (GA) approach. The aim of this work is to predict the performance characteristics (H and W) at optimized condition by applying back propagation method of artificial neural network (ANN). The essential input process parameters are identified as laser power, scan speed of work table and powder feed rate. In order to validate the predicted result, an experiment as confirmatory test is carried out at the optimized cladding condition. It is observed that the confirmatory experimental result is showing a good agreement with the predicted one. It has also been found that the optimum condition of the cladding parameters for multi performance characteristics varies with the different combinations of weighting factors.
Pareto optimisation of certain quality characteristics in laser cutting by ANN-GA approach
International Journal of Advanced Intelligence Paradigms, 2017
Determining the optimal laser cutting conditions for simultaneous improvement of multiple cut quality characteristics is of great importance. The aim of the present research is to simultaneously optimise three cut quality characteristics such as surface roughness, kerf taper angle and burr height in CO 2 laser cutting of stainless steel. The laser cutting experiment was conducted based on Taguchi's experimental design using L 27 experimental plan by varying four parameters such as laser power, cutting speed, assist gas pressure and focus position at three levels. Using the obtained experimental results three mathematical models for the prediction of cut quality characteristics were developed using artificial neural networks (ANNs). The developed response models for cut quality characteristics were taken as objective functions for the multi-objective optimisation based on the genetic algorithm. The obtained optimal solution sets were used to generate 2-D and 3-D Pareto fronts. The overall improvement of about 16% was registered in multiple cut quality characteristics.
Parametric Optimization of Nd:YAG Laser Beam Machining Process Using Artificial Bee Colony Algorithm
Journal of Industrial Engineering, 2013
Nd:YAG laser beam machining (LBM) process has a great potential to manufacture intricate shaped microproducts with its unique characteristics. In practical applications, such as drilling, grooving, cutting, or scribing, the optimal combination of Nd:YAG LBM process parameters needs to be sought out to provide the desired machining performance. Several mathematical techniques, like Taguchi method, desirability function, grey relational analysis, and genetic algorithm, have already been applied for parametric optimization of Nd:YAG LBM processes, but in most of the cases, suboptimal or near optimal solutions have been reached. This paper focuses on the application of artificial bee colony (ABC) algorithm to determine the optimal Nd:YAG LBM process parameters while considering both single and multiobjective optimization of the responses. A comparative study with other population-based algorithms, like genetic algorithm, particle swarm optimization, and ant colony optimization algorithm...