Skip to main content

Advertisement

SpringerLink
Log in

Analysis and synthesis of laser forming process using neural networks and neuro-fuzzy inference system

  • Methodologies and Application
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

To apply laser forming process in reality, it is required to know the relationships between the deformed shape and scanning paths along with heating conditions. The deformation due to laser scanning depends on various factors, namely laser power, scan speed, spot diameter, scan position, number of scans, and many others. This article presents soft computing-based methods to predict deformations for a set of heating conditions, and also to determine the heating lines and heat conditions, in order to get a desired shape (i.e., inverse analysis). A novel attempt has been made in this paper to carry out analysis and synthesis (inverse analysis) of laser forming process using both genetic-neural network (GA-NN) and genetic adaptive neuro-fuzzy inference system (GA-ANFIS). During the analysis, laser power, scan speed, spot diameter, scan position and number of scans are taken as inputs and bending angle is considered as the output. A batch mode of training has been used for both the approaches with the help of some experimental data. The performances of the developed approaches have been tested on some real experimental data. Both the approaches are found to be effective to predict the bending angles and carry out the process synthesis successfully. GA-NN approach is found to perform better than the GA-ANFIS approach in predicting the bending angles, and both the approaches are able to provide comparable predictions in inverse analysis.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

References

  • Akbilgic O, Bozdogan H (2011) Predictive subset selection using regression trees and RBF neural networks hybridized with the genetic algorithm. Eur J Pure Appl Math 4(4):467–485

    MathSciNet  Google Scholar 

  • Carlone P, Palazzo GS, Pasquino R (2008) Inverse analysis of the laser forming process by computational modeling and methods. Comput Math Appl 55:2018–2032

    Article  MathSciNet  MATH  Google Scholar 

  • Casalino G, Ludovico AD (2002) Parameter selection by an artificial neural network for a laser bending process. IMechE Part B J Eng Manuf 216:1517–1520

    Article  Google Scholar 

  • Chen DJ, Xiang YB, Wu SC, Li MQ (2002) Application of fuzzy neural network to laser bending process of sheet metal. Mater Sci Technol 18:677–680

    Article  Google Scholar 

  • Cheng PJ, Lin SC (2000) Using neural networks to predict bending angle of sheet metal formed by laser. Int J Mach Tools Manuf 40:1185–1197

    Article  Google Scholar 

  • Cheng PJ, Lin SC (2001) An analytical model to estimate angle formed by laser. J Mater Process Technol 108:314–319

    Article  Google Scholar 

  • Cheng JG, Yao YL (2004) Process synthesis of laser forming by genetic algorithm. Int J Mach Tools Manuf 44:1619–1628

    Article  Google Scholar 

  • Dragos V, Dan V, Kovacevic R (2000) Prediction of the laser sheet bending using neural network. In: IEEE international symposium on circuits and systems, pp 686–689

  • Du Y, Wang X (2010) Improved BP network to predict bending angle in the laser bending process for sheet metal. In: International conference on intelligent system design and engineering application, Cairo, Egypt, pp 839–843

  • Gisario A, Barletta M, Conti C, Guarino S (2011) Springback control in sheet metal bending by laser-assisted bending: experimental analysis, empirical and neural network modeling. Opt Lasers Eng 49:1372–1383

    Article  Google Scholar 

  • Griffiths J, Edwardson SP, Dearden G, Watkins KG (2010) Finite element modeling of laser forming at macro and micro scales. Phys Procedia 5:371–380

    Article  Google Scholar 

  • Guarino S, Ucciardello N, Tagliaferri V (2007) An application of neural network solutions to modeling of diode laser assisted forming process of AA6082 thin sheets. Key Eng Mater 344:325–332

    Article  Google Scholar 

  • Herrera F, Lozano M, Verdegay JL (1995) Tuning fuzzy logic controllers by genetic algorithms. Int J Approx Reason 12:293–315

    Article  MathSciNet  Google Scholar 

  • Hu Z, Labudovic M, Wang H, Kovacevic R (2001) Computer simulation and experimental investigation of sheet metal bending using laser beam scanning. Int J Mach Tools Manuf 41:589–607

    Article  Google Scholar 

  • Hu J, Dang D, Shen H, Zhang Z (2012) A finite element model using multi-layered shell element in laser forming. Opt Laser Technol 44:1148–1155

    Article  Google Scholar 

  • Jang JSR (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern 23(3):665–685

    Article  Google Scholar 

  • Keller JM, Yager RR, Tahani H (1992) Neural nework implementation of fuzzy logic. Fuzzy Sets Syst 45(1):1–12

    Article  MathSciNet  MATH  Google Scholar 

  • Khashei M, Bijari M (2010) An artificial neural network (p, d, q) model for time series forecasting. Expert Syst Appl 37:479–489

    Article  Google Scholar 

  • Kuo HC, Wu LJ (2002) Automation of heat bending in shipbuilding. Comput Ind 48:127–142

    Article  Google Scholar 

  • Kyrsanidi AK, Kermanidis TB, Pantelakis SG (2000) An analytical model for the prediction of distortions caused by the laser forming process. J Mater Process Technol 104:94–102

    Article  Google Scholar 

  • Liu C, Yao YL (2002) Optimal and robust design of the laser forming process. J Manuf Processes 4:52–66

    Article  Google Scholar 

  • Maji K, Pratihar DK (2010) Forward and reverse mappings of electrical discharge machining process using adaptive network-based fuzzy inference system. Expert Syst Appl 37:8566–8574

    Article  Google Scholar 

  • Maji K, Pratihar DK, Nath AK (2012) Experimental investigations, modeling and optimization of multi-scan laser forming of AISI 304 stainless steel sheet. Int J Adv Manuf Technol (under review)

  • Martino FD, Loia V, Sessa S (2010) Fuzzy transforms method and attribute dependency in data analysis. Inf Sci 180:493–505

    Article  MATH  Google Scholar 

  • Martino FD, Loia V, Sessa S (2011) Fuzzy transforms method in prediction data analysis. Fuzzy Sets Syst 180:146–163

    Article  MATH  Google Scholar 

  • Montgomery DC (2001) Design and analysis of experiments. Wiley, New York

    Google Scholar 

  • Nasrabadi E, Hashemi SM (2008) Robust fuzzy regression analysis using neural networks. Int J Uncertain Fuzziness Knowl Based Syst 16(4):579–598

    Article  MathSciNet  MATH  Google Scholar 

  • Nguyen TT, Yang YS, Bae KY, Choi SN (2009) Prediction of deformations of steel plate by artificial neural network in forming process with induction heating. J Mech Sci Technol 23:1211–1221

    Article  Google Scholar 

  • Pratihar DK (2008) Soft computing. Narosa Publishing House, New Delhi

    Google Scholar 

  • Pratihar DK, Deb K, Ghosh A (1999) A genetic-fuzzy approach for mobile robot navigation among moving obstacles. Int J Approx Reason 20:145–172

    Article  MATH  Google Scholar 

  • Shen H, Vollertsen F (2009) Modeling of laser forming—a review. Comput Mater Sci 46:834–840

    Article  Google Scholar 

  • Shen H, Shi Y, Yao Z, Hu J (2006a) An analytical model for estimating deformation in laser forming. Comput Mater Sci 37:593–598

    Article  Google Scholar 

  • Shen H, Shi YJ, Yao ZQ, Hu J (2006b) Fuzzy logic model for bending angle in laser forming. Mater Sci Technol 22:981–986

    Article  Google Scholar 

  • Vollertsen F (1994) An analytical model for laser bending. Lasers Eng 2:261–276

    Google Scholar 

  • Vollertsen F, Geiger M, Li WM (1993) FDM-and FEM simulation of laser forming: a comparative study. In: Proceedings of the fourth international conference on technology of plasticity, pp 1793–1798

  • Wang X, Xu W, Chen H, Wang J (2008) Parameter prediction in laser bending of aluminum alloy sheet. Front Mech Eng China 3(3):293–298

    Article  MathSciNet  Google Scholar 

  • Whitley D, Starkweather T, Bogart C (1990) Genetic algorithms and neural networks: optimizing connections and connectivity. Parallel Comput 14:347–361

    Article  Google Scholar 

  • Wu S, Ji Z (2002) FEM simulation of the deformation field during the laser forming of sheet metal. J Mater Process Technol 121:269–272

    Article  Google Scholar 

  • Zhang L, Michaleris P (2004) Investigation of Lagrangian and Eulerian finite element methods for modeling the laser forming process. Finite Element Anal Des 40:383–405

    Article  Google Scholar 

  • Zhang P, Guo B, Shan DB, Ji Z (2007) FE simulation of laser curve bending of sheet metals. J Mater Process Technol 184:157–162

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Mechanical Engineering, Indian Institute of Technology, Kharagpur, Kharagpur, 721 302, India

    Kuntal Maji, D. K. Pratihar & A. K. Nath

Authors
  1. Kuntal Maji
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. D. K. Pratihar
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. A. K. Nath
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to D. K. Pratihar.

Additional information

Communicated by Y. Jin.

Appendices

Appendix A: Experimental data collected according to CCD to develop the model of bending angle

SL. no.

Input parameters

Output: bending angle (°)

p (W)

v (mm/s)

d (mm)

r

n

A 1

A 2

A 3

1

225

250.0

0.500

0.25

5

4.81

5.34

5.07

2

275

250.0

0.500

0.25

5

6.71

6.61

6.82

3

225

283.0

0.500

0.25

5

4.06

4.52

3.76

4

275

283.0

0.500

0.25

5

4.56

4.20

5.00

5

225

250.0

0.750

0.25

5

3.97

3.74

3.55

6

275

250.0

0.750

0.25

5

5.69

5.85

6.04

7

225

283.0

0.750

0.25

5

2.14

1.95

2.18

8

275

283.0

0.750

0.25

5

6.45

6.29

6.68

9

225

250.0

0.500

0.75

5

4.12

4.21

4.19

10

275

250.0

0.500

0.75

5

4.41

4.73

4.56

11

225

283.0

0.500

0.75

5

2.22

2.27

2.17

12

275

283.0

0.500

0.75

5

5.05

4.95

5.00

13

225

250.0

0.750

0.75

5

3.56

3.63

3.73

14

275

250.0

0.750

0.75

5

6.12

6.23

5.94

15

225

283.0

0.750

0.75

5

1.74

1.58

1.66

16

275

283.0

0.750

0.75

5

3.89

4.08

4.20

17

225

250.0

0.500

0.25

15

11.30

11.50

11.06

18

275

250.0

0.500

0.25

15

15.21

14.47

14.83

19

225

283.0

0.500

0.25

15

8.58

8.65

8.79

20

275

283.0

0.500

0.25

15

13.00

12.40

12.80

21

225

250.0

0.750

0.25

15

8.07

8.28

7.90

22

275

250.0

0.750

0.25

15

15.47

15.28

15.40

23

225

283.0

0.750

0.25

15

7.16

7.21

7.26

24

275

283.0

0.750

0.25

15

12.24

12.47

11.93

25

225

250.0

0.500

0.75

15

11.70

11.06

11.25

26

275

250.0

0.500

0.75

15

14.20

14.34

14.47

27

225

283.0

0.500

0.75

15

9.48

9.54

9.36

28

275

283.0

0.500

0.75

15

12.53

12.46

12.5

29

225

250.0

0.750

0.75

15

7.98

8.09

8.28

30

275

250.0

0.750

0.75

15

15.20

15.28

15.10

31

225

283.0

0.750

0.75

15

6.46

6.30

6.38

32

275

283.0

0.750

0.75

15

12.25

12.31

12.37

33

225

266.5

0.625

0.50

10

6.33

6.45

6.21

34

275

266.5

0.625

0.50

10

11.13

10.84

10.95

35

250

250.0

0.625

0.50

10

8.87

8.95

9.04

36

250

283.0

0.625

0.50

10

8.67

8.84

8.56

37

250

266.5

0.500

0.50

10

9.30

8.78

9.02

38

250

266.5

0.750

0.50

10

7.44

7.75

8.35

39

250

266.5

0.625

0.25

10

8.88

9.00

8.60

40

250

266.5

0625

0.75

10

9.25

8.78

8.97

41

250

266.5

0.625

0.50

5

4.60

4.85

5.08

42

250

266.5

0.625

0.50

15

13.67

13.80

13.56

43

250

266.5

0.625

0.50

10

9.24

9.13

9.19

Appendix B: Data collected for testing the models of bending angle

 

SL. no.

Input parameters

Output: bending angle

p (W)

v (mm/s)

d (mm)

r

n

A (°)

1

230

258.33

0.550

0.30

6

5.93

2

270

275.00

0.700

0.60

6

5.82

3

240

275.00

0.550

0.40

8

6.37

4

260

258.33

0.700

0.70

14

11.85

5

240

258.33

0.700

0.70

8

5.72

6

230

275.00

0.550

0.40

6

5.91

7

270

258.33

0.550

0.60

8

8.18

8

240

275.00

0.700

0.30

14

8.93

9

270

275.00

0.700

0.30

6

6.95

10

260

258.33

0.550

0.40

8

8.29

11

230

258.33

0.550

0.70

12

8.70

12

240

275.00

0.700

0.60

14

8.41

13

230

258.33

0.550

0.30

12

8.61

14

260

258.33

0.700

0.40

6

6.08

15

270

275.00

0.550

0.60

12

10.48

Rights and permissions

Reprints and permissions

About this article

Cite this article

Maji, K., Pratihar, D.K. & Nath, A.K. Analysis and synthesis of laser forming process using neural networks and neuro-fuzzy inference system. Soft Comput 17, 849–865 (2013). https://doi.org/10.1007/s00500-012-0949-7

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-012-0949-7

Keywords

Search

Navigation