Application of Multi-Objective optimization algorithm and Artificial Neural Networks at machining process

Since, experimentally investigation of machining processes is difficult and costly, the problem becomes more difficult if the aim is simultaneously optimization of the machining outputs. This paper presents a novel hybrid method based on the Artificial Neural networks (ANNs), Multi-Objective Optimization (MOO) and Finite Element Method (FEM) for evaluation of thermo-mechanical loads during turning process. After calibrating controllable parameters of simulation by comparison between FE results and experimental results of literature, the results of FE simulation were employed for training neural networks by Genetic algorithm. Finally, the functions implemented by neural networks were considered as objective functions of Non-Dominated Genetic Algorithm (NSGA-II) and optimal non-dominated solution set were determined at the different states of thermo-mechanical loads. Comparison between obtained results of NSGA-II and predicted results of FE simulation showed that, developed hybrid technique of FEM-ANN-MOO in this study provides a robust framework for manufacturing processes.

[1]  Giuseppina Ambrogio,et al.  A hybrid finite element method–artificial neural network approach for predicting residual stresses and the optimal cutting conditions during hard turning of AISI 52100 bearing steel , 2008 .

[2]  Tuğrul Özel,et al.  Prediction of flank wear by using back propagation neural network modeling when cutting hardened H-13 steel with chamfered and honed CBN tools , 2002 .

[3]  J. Paulo Davim,et al.  Optimization of machining parameters of Al/SiC-MMC with ANOVA and ANN analysis , 2009 .

[4]  Kalyanmoy Deb,et al.  Muiltiobjective Optimization Using Nondominated Sorting in Genetic Algorithms , 1994, Evolutionary Computation.

[5]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[6]  David K. Aspinwall,et al.  Modelling of temperature and forces when orthogonally machining hardened steel , 1999 .

[7]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[8]  Li-Ning Xing,et al.  An efficient search method for multi-objective flexible job shop scheduling problems , 2009, J. Intell. Manuf..

[9]  Kalyanmoy Deb,et al.  A Tutorial on Evolutionary Multi-Objective Optimization (EMO) , 2005, Practical Approaches to Multi-Objective Optimization.

[10]  Ibrahim N. Tansel,et al.  Taguchi Method-GONNS integration: Complete procedure covering from experimental design to complex optimization , 2011, Expert Syst. Appl..

[11]  Marco Laumanns,et al.  A Tutorial on Evolutionary Multiobjective Optimization , 2004, Metaheuristics for Multiobjective Optimisation.

[12]  Joaquim Ciurana,et al.  Surface roughness monitoring application based on artificial neural networks for ball-end milling operations , 2011, J. Intell. Manuf..

[13]  Habibollah Haron,et al.  Application of GA to optimize cutting conditions for minimizing surface roughness in end milling machining process , 2010, Expert Syst. Appl..

[14]  Rubens Maciel Filho,et al.  Hybrid training approach for artificial neural networks using genetic algorithms for rate of reaction estimation: Application to industrial methanol oxidation to formaldehyde on silver catalyst , 2010 .