Inverse analysis and multi-objective optimization of single-point incremental forming of AA5083 aluminum alloy sheet

This paper presents soft computing-based modeling and multi-objective optimization of process parameters in single-point incremental forming (SPIF) of aluminum alloy sheet in order to obtain desired deformed shape with optimal formability satisfying multiple objectives. Response surface methodology and adaptive neuro-fuzzy inference system (ANFIS)-based models were developed to predict the responses based on the experimental data collected according to central composite design of experiments considering tool diameter, feed rate and step height as inputs, and outputs, namely forming wall angle, deformed sheet thickness and surface roughness. Inverse analyses were also performed to determine the set of input parameters to achieve desired outputs. Two different algorithms, namely back-propagation and hybrid, were employed to train the ANFIS in batch mode with the help of experimental data. The performances of the developed models were tested through real experimental data and also cross-validation methods. ANFIS trained by hybrid algorithm was found to be slightly better than that trained by the back-propagation algorithm in terms of prediction accuracy. Desirability function and a non-dominated sorting genetic algorithm were utilized for performing multi-objective optimization in SPIF, and the obtained optimal results were found satisfactory compared to the experimental data. The proposed approach could provide a reliable guidance for selection of suitable parameters in SPIF to achieve desired formed parts.

[1]  Gnanavelbabu A,et al.  Numerical Analysis on Formability of AZ61A Magnesium Alloy by Incremental Forming , 2014 .

[2]  Hamed Sohrabpoor,et al.  Selection of laser bending process parameters for maximal deformation angle through neural network and teaching–learning-based optimization algorithm , 2015, Soft Comput..

[3]  M. R. Nejati,et al.  Input value prediction of parameters in laser bending using Fuzzy and PSO , 2017, Soft Computing.

[4]  Jack Jeswiet,et al.  Single point incremental forming , 2008 .

[5]  Reza Teimouri,et al.  Erratum to: Application of soft computing techniques for modeling and analysis of MRR and taper in laser machining process as well as weld strength and weld width in laser welding process , 2015, Soft Comput..

[6]  C. Raju,et al.  Strain distribution and failure mode in single point incremental forming (SPIF) of multiple commercially pure aluminum sheets , 2017 .

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

[8]  Laith Mohammad Abualigah,et al.  Feature Selection and Enhanced Krill Herd Algorithm for Text Document Clustering , 2018, Studies in Computational Intelligence.

[9]  Zahra Zojaji,et al.  Optimization of finite element model of laser forming in circular path using genetic algorithms and ANFIS , 2016, Soft Comput..

[10]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[11]  Aldo Attanasio,et al.  On forces, formability and geometrical error in metal incremental sheet forming , 2011 .

[12]  Angshuman Baruah,et al.  Optimization of AA5052 in incremental sheet forming using grey relational analysis , 2017 .

[13]  E Hagan,et al.  Forming parameters for incremental forming of aluminium alloy sheet metal , 2002 .

[14]  Niels Bay,et al.  Theory of single point incremental forming , 2008 .

[15]  Laith Mohammad Abualigah,et al.  Hybrid clustering analysis using improved krill herd algorithm , 2018, Applied Intelligence.

[16]  Yang Yang,et al.  Multi-objective process parameters optimization of hot-wire laser welding using ensemble of metamodels and NSGA-II , 2018, Robotics and Computer-Integrated Manufacturing.

[17]  Anirban Bhattacharya,et al.  Formability and Surface Finish Studies in Single Point Incremental Forming , 2011 .

[18]  S. P. Regalla,et al.  Experimental and numerical studies on formability of extra-deep drawing steel in incremental sheet metal forming , 2014 .

[19]  V. S. Senthil Kumar,et al.  Modeling of Incremental Forming Process Parameters of Al 3003 (O) by Response Surface Methodology , 2014 .

[20]  Laith Mohammad Abualigah,et al.  Unsupervised text feature selection technique based on hybrid particle swarm optimization algorithm with genetic operators for the text clustering , 2017, The Journal of Supercomputing.

[21]  A. K. Nath,et al.  Analysis and synthesis of laser forming process using neural networks and neuro-fuzzy inference system , 2013, Soft Comput..

[22]  Srinivasa Prakash Regalla,et al.  Modeling and optimization of surface roughness in single point incremental forming process , 2015 .

[23]  J. Jeswiet,et al.  Observations on Heat Generated in Single Point Incremental Forming , 2017 .

[24]  Laith Mohammad Abualigah,et al.  A new feature selection method to improve the document clustering using particle swarm optimization algorithm , 2017, J. Comput. Sci..

[25]  H. G. Menghari,et al.  Optimization of two-point incremental forming process of AA1050 through response surface methodology , 2018, Measurement.

[26]  Laith Mohammad Abualigah,et al.  APPLYING GENETIC ALGORITHMS TO INFORMATION RETRIEVAL USING VECTOR SPACE MODEL , 2015 .