A framework for modeling complex manufacturing processes using fuzzy neural networks is presented with a novel training algorithm. In this study, a hierarchical structure that consists of fuzzy basis function networks (FBFN) is proposed to construct comprehensive models of the complex processes. A new adaptive least-squares (ALS) algorithm, based on the least-squares method and genetic algorithm (GA), is proposed for autonomous learning and construction of FBFNs without any human intervention. Simulation studies are performed to demonstrate advantages of the proposed modeling framework with the training algorithm in modeling complex manufacturing processes. The proposed method is implemented for the surface grinding processes based on the hierarchical structure of FBFNs. Process models for surface roughness and residual stress are developed based on the available grinding model structures with a small number of experimental data to demonstrate the concept. The accuracy of developed models is validated through independent sets of grinding experiments.
Keywords:
grinding,
fuzzy neural nets,
learning (artificial intelligence),
radial basis function networks,
least squares approximations,
genetic algorithms,
hierarchical systems,
large-scale systems,
surface roughness,
internal stresses
Topics:
Algorithms,
Grinding,
Manufacturing,
Modeling,
Stress,
Surface roughness,
Simulation,
Genetic algorithms,
Errors
1.
Liao
, T. W.
, and Chen
, L. J.
, 1994
, “A Neural Network Approach for Grinding Processes: Modelling and Optimization
,” Int. J. Mach. Tools Manuf.
, 34
, pp. 919
–937
.2.
Midha
, P. S.
, Zhu
, C. B.
, and Trmal
, G. J.
, 1991
, “Optimum Selection of Grinding Parameters Using Process Modelling and Knowledge Based System Approach
,” J. Mater. Process. Technol.
, 28
, pp. 189
–198
.3.
Xiao, G., Malkin, S., and Danai, K., 1992, “Intelligent Control of Cylindrical Plunge Grinding,” Proceedings of the ACC, Chicago, IL, 24–26 June, pp. 391–398.
4.
Broomhead
, D. S.
, and Lowe
, D.
, 1988
, “Multivariable Functional Interpolation and Adaptive Networks
,” Complex Syst.
, 2
, pp. 321
–355
.5.
Koo, T.-K. J., 1996, “Construction of Fuzzy Linguistic Model,” in Proc. of the 35th Conf. on Decision and Control, Kobe, Japan, December, pp. 98–103.
6.
Nie
, J.
, and Linkens
, D. A.
, 1993
, “Learning Control Using Fuzzified Self-Organizing Radial Basis Function Networks
,” IEEE Trans. Fuzzy Syst.
, 1
, pp. 280
–287
.7.
Shimojima, K., Fukuda, T., and Hasegawa, Y., 1995, “RBF-Fuzzy System With GA Based Unsupervised/Supervised Learning Method,” in Proc. of 1995 IEEE Int. Conf. on Fuzzy Systems, Yokohama, Japan, 20–24 March, pp. 253–258.
8.
Wang, L. X., and Mendel, J. M., 1992a, “Back-Propagation Fuzzy Systems as Nonlinear Dynamic System Identifiers,” Proc. IEEE 1992 Int. Conf. Fuzzy Systems, San Diego, CA, pp. 1409–1418.
9.
Wang
, L. X.
, and Mendel
, J. M.
, 1992b
, “Fuzzy Basis Functions, Universal Approximation, and Orthogonal Least-Squares Learning
,” IEEE Trans. Neural Netw.
, 3
, pp. 807
–814
.10.
Glorennec, P. Y., 1994, “Learning Algorithms for Neuro-Fuzzy Networks,” in Fuzzy Control Systems, A. Kandel and G. Langholz, eds., CRC Press, Boca Raton, pp. 3–18.
11.
Jang
, J.-S. R.
, 1993
, “ANFIS: Adaptive-Network-Based Fuzzy Inference System
,” IEEE Trans. Syst. Man Cybern.
, 23
, pp. 665
–685
.12.
Elanayar, S. V. T., and Shin, Y. C., 1990, “Machining Condition Monitoring for Automation Using Neural Networks,” ASME Winter Annual. Mtg., PED-Vol. 44, pp. 85–95.
13.
Venk
, S.
, Govind
, R.
, and Merchant
, E.
, 1990
, “An Expert System Approach to Optimization of the Centerless Grinding Process
,” Ann. CIRP
, 39
, pp. 489
–492
.14.
To¨nshoff
, H. K.
, Peters
, J.
, Inasaki
, I.
, and Paul
, T.
, 1992
, “Modelling and Simulation of Grinding Processes
,” Ann. CIRP
, 41
, pp. 677
–688
.15.
Malkin, S., 1989, Grinding Technology: Theory and Application of Machining with Abrasives, Society of Manufacturing Engineers, Reading, MI.
16.
Steffens
, K.
, 1983
, “Closed Loop Simulation of Grinding
,” Ann. CIRP
, 32/1
, pp. 255
–259
.17.
Kruszynski
, B.
, 1991
, “An Attempt to Predict Residual Stresses in Grinding of Metals With the Aid of a New Grinding Parameter
,” Ann. CIRP
, 40/1
, pp. 335
–337
.18.
Li
, Y. Y.
, and Chen
, Y.
, 1989
, “Simulation of Surface Grinding Process
,” Trans. ASME
, 111
, pp. 46
–53
.19.
Rowe
, W. B.
, Pettit
, J. A.
, Boyle
, A.
, and Moruzzi
, J. L.
, 1988
, “Avoidance of Thermal Damage in Grinding and Prediction of the Damage Threshold
,” Ann. CIRP
, 37/1
, pp. 327
–330
.20.
Lindsay
, R. P.
, 1983
, “The Effect of Wheel Wear Rate on the Grinding Performance of Three Wheel Grades
,” Ann. CIRP
, 32/1
, pp. 247
–249
.21.
Malkin
, S.
, 1976
, “Selection of Operating Parameters in Surface Grinding of Steels
,” Trans. ASME, J. Eng. Ind.
, 98
, pp. 56
–62
.22.
Peters, J., Snoeys, R., and Maris, M., 1978, “Residual Stresses in Grinding,” AGARD Conference Preceedings No. 256, pp. 2-1–2-15.
23.
Snoeys
, R.
, Maris
, M.
, and Peters
, J.
, 1978
, “Thermally Induced Damage in Grinding
,” Ann. CIRP
, 27/2
, pp. 571
–581
.24.
Snoeys
, R.
, and Peters
, J.
, 1974
, “The Significance of Chip Thickness in Grinding
,” Ann. CIRP
, 23/2
, pp. 227
–237
.25.
Rowe
, W. B.
, Yan
, L.
, Inasaki
, I.
, and Malkin
, S.
, 1994
, “Application of Artificial Intelligence in Grinding
,” Ann. CIRP
, 43/2
, pp. 521
–531
.26.
Vishnupad, P. S., and Shin, Y. C., 1998, “Intelligent Optimization of Grinding Processes Using Fuzzy Logic,” Proceedings of the Institutions of Mechanical Engineers, Part B, Journal of Engineering Manufacture, Vol. 212, No. B8, pp. 647–660.
27.
Ko´czy
, L. T.
, Hirota
, K.
, and Muresan
, L.
, 1999
, “Interpolation in Hierarchical Fuzzy Rule Bases
,” Int. J. Fuzzy Syst.
, 1
, pp. 77
–84
.28.
Chen
, S.
, Cowan
, C. F. N.
, and Grand
, P. M.
, 1991
, “Orthogonal Least Squares Learning Algorithm for Radial Basis Function Networks
,” IEEE Trans. Neural Netw.
, 2
, pp. 302
–309
.29.
Hohensohn, J., and Mendel, J. M., 1994, “Two-Pass Orthogonal Least-Squares Algorithm to Train and Reduce Fuzzy Logic Systems,” Proc. of the 3rd IEEE Conf. on Fuzzy Systems, Orlando, FL, pp. 696–700.
30.
Goldberg, D. E., 1989, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, Reading, MA.
31.
Michalewicz, Z., 1996, Genetic Algorithms+Data Structures=Evolution Programs, 3rd ed., Springer-Verlag, Reading, Berlin.
32.
Chen, S., Wu, Y., and Alkadhimi, K., 1995, “A Two-Layer Learning Method for Radial Basis Function Networks Using Combined Genetic and Regularized OLS Algorithms,” Genetic Algorithms in Engineering Systems: Innovations and Applications, IEE Conf. Publication No. 414, pp. 245–249.
33.
Lin, C.-T., and Lee, C. S. G., 1996, Neural Fuzzy Systems: A Neuro-Fuzzy Synergism to Intelligent Systems, PTR Prentice–Hall, Reading, NJ.
34.
Demuth, H., and Beale, M., 1994, Neural Network Toolbox User’s Guide, MA, The MathWorks, Inc.
35.
Kovach, J., 1987, “Improved Grinding of Ceramic Components,” AFWAL-TR-87-4137, 1–5 June, Dayton, OH, Vol. 7, pp. 72–100.
36.
Shin
, Y. C.
, and Vishnupad
, P.
, 1996
, “Neuro-Fuzzy Control of Complex Manufacturing Processes
,” Int. J. Prod. Res.
, 34
, pp. 3291
–3309
.Copyright © 2004
by ASME
You do not currently have access to this content.
