Experimental Optimization of Nimonic 263 Laser Cutting Using a Particle Swarm Approach (original) (raw)
Related papers
Materials Today: Proceedings, 2018
This experimental work describes the utilization of a hybrid approach of regression modeling and particle swarm optimization (PSO) for optimizing the process parameters during the laser cutting of the Inconel-718 sheet. The experiments have been performed by using four machining parameters such as assist gas pressure, standoff distance, cutting speed and laser power. The kerf width and kerf taper are used as an output quality characteristic. The experiments have been performed by using well planned orthogonal array L 27 .The second order regression models have been developed for kerf width and kerf taper by using the experimental data. The developed second order regression models have been utilized in optimization by particle swarm optimization. The comparison of the experimental result with optimum results confirms that the individual improvement in output quality characteristics kerf width and kerf taper is approximate 10% and 57%, respectively. The overall improvement of 46% has been observed during the optimization. Finally, the effects of different process parameters on different performances have also been discussed. The parametric effect analysis shows that minimum kerf taper may be obtained at lowest values of laser power and middle values of standoff distance.
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.
Infrared Physics & Technology, 2018
The Inconel-718 is one of the most demanding advanced engineering materials because of its superior quality. The conventional machining techniques are facing many problems to cut intricate profiles on these materials due to its minimum thermal conductivity, minimum elastic property and maximum chemical affinity at magnified temperature. The laser beam cutting is one of the advanced cutting method that may be used to achieve the geometrical accuracy with more precision by the suitable management of input process parameters. In this research work, the experimental investigation during the pulsed Nd:YAG laser cutting of Inconel-718 has been carried out. The experiments have been conducted by using the well planned orthogonal array L 27. The experimentally measured values of different quality characteristics have been used for developing the second order regression models of bottom kerf deviation (KD), bottom kerf width (KW) and kerf taper (KT). The developed models of different quality characteristics have been utilized as a quality function for single-objective optimization by using particle swarm optimization (PSO) method. The optimum results obtained by the proposed hybrid methodology have been compared with experimental results. The comparison of optimized results with the experimental results shows that an individual improvement of 75%, 12.67% and 33.70% in bottom kerf deviation, bottom kerf width, and kerf taper has been observed. The parametric effects of different most significant input process parameters on quality characteristics have also been discussed.
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.
International Journal of Manufacturing, Materials, and Mechanical Engineering
In the present study, a novel technique, namely, evolutionary non-dominated sorting genetic algorithm-II (NSGA-II) was used in conjunction with developed artificial neural network (ANN) model to select optimal process parameters for achieving the better process performance in LBC. First, ANN with backpropagation algorithm was used to model the LBC of nickel based superalloy sheets. The input process parameters taken were oxygen pressure, pulse width, pulse frequency and cutting speed. The performance characteristics of interest in nickel based superalloy thin sheet cutting are average kerf taper and surface roughness. The ANN model was trained and tested using the experimental data obtained through experimentation on pulsed Nd-YAG laser beam machining system. The 4-10-11-2 backpropagation architecture was found more accurate and generalized for given problem with good prediction capability. The results show that the developed modelling and optimization tool is effective for process ...
2020
The conventional process of Machining of Nitinol alloy leads to extensive wear on the tool and deprived surface quality. Wire electro discharge machining (WEDM) is widely accepted for machining this alloy involving various input factors, namely, P, (pulse-on-duration), Q, (pulse-off-duration), C, (maximum-current), and V, (voltage). The factor’s effect on MRR (metal removal rate) and SR (surface roughness) responses and multi-response optimization of the WEDM process by employing PSO (particle swarm optimization) method are studied. The relationship model between factors and response characteristics were generated by ANOVA and optimized by response surface methodology has shown more significant factors (A and C). Though the effect of WEDM process factors on SR and MRR are contradictory when studied individually. MRPSO method was employed to get the best optimum condition for minimizing SR and maximizing MRR. MRPSO results improved the responses for vast combination of optimal setting...
Particle swarm optimization of a neural network model in a machining process
Sadhana, 2014
The optimization of architecture and weights of feed forward neural networks is a complex task of great importance in problems of supervised learning. In this work we analyze the use of the Particle Swarm Optimization algorithm for the optimization of neural network architectures and weights aiming better generalization performances through the creation of a compromise between low architectural complexity and low training errors. For evaluating these algorithms we apply them to benchmark classification problems of the medical field. The results showed that a PSO-PSO based approach represents a valid alternative to optimize weights and architectures of MLP neural networks.
The International Journal of Advanced Manufacturing Technology, 2010
Empirical models for machining time and surface roughness are described for exploring optimized machining parameters in turning operation. CNC turning machine was employed to conduct experiments on brass, aluminum, copper, and mild steel. Particle swarm optimization (PSO) has been used to find the optimal machining parameters for minimizing machining time subjected to desired surface roughness. Physical constraints for both experiment and theoretical approach are cutting speed, feed, depth of cut, and surface roughness. It is observed that the machining time and surface roughness based on PSO are nearly same as that of the values obtained based on confirmation experiments; hence, it is found that PSO is capable of selecting appropriate machining parameters for turning operation.
Journal of Engineering Science and Technology Review, 2014
The identification of laser cutting conditions for satisfying different requirements such as improving cut quality characteristics and material removal rate is of great importance. In this paper, an attempt has been made to develop mathematical models in order to relate laser cutting parameters such as the laser power, cutting speed, assist gas pressure and focus position, and cut quality characteristics such as the surface roughness, kerf width and width of heat affected zone (HAZ). A laser cutting experiment was planned as per Taguchi's L27 orthogonal array with three levels for each of laser cutting parameters considered. 3 mm thick AISI 304 stainless steel was used as workpiece material. Mathematical models were developed using a single hidden layer artificial neural network (ANN) trained with the Levenberg-Marquardt algorithm. On the basis of the developed ANN models the effects of the laser cutting parameters on the cut quality characteristics were presented. It was observed that laser cutting parameters variously affect cut quality characteristics. Also, for the range of operating conditions considered in the experiment, laser cut quality operating diagrams were shown. From these operating diagrams one can see the values of cut quality characteristics that can be achieved and subsequently select laser cutting parameter values. Furthermore, the analysis includes correlations between cut quality characteristics and material removal rate. To this aim, six trade-off operating diagrams for improving multiple responses at the same time were given.