Artificial neural networks have been shown to have a lot of potential as a means of integrating multi-sensor signals for real-time monitoring of machining processes. However, many questions still remain to be answered on how to optimize the training parameters during the training phase to optimize their subsequent performance, especially in view of the fact that the few published articles have made conflicting recommendations. This paper presents a systematic evaluation of the individual effects of training parameters — learning rate, momentum rate, number of hidden layer nodes, transfer function and learning rule-on the performance of back-propagation networks used for predicting quality characteristics of end-milled parts. Multi-sensor signatures (acoustic emission, spindle vibration, cutting force components and machining time) acquired during circular end-milling of 4140 steel and the corresponding measured quality characteristics (surface roughness and bore tolerance) were used to train the networks. The network is part of a proposed intelligent machining monitoring and diagnostic system for quality assurance of machined parts. The network performances were evaluated using four different criteria: maximum error, rms error, mean error and number of training cycles. One of the results obtained shows that the hyperbolic tangent transfer function gives a better performance than the sigmoid and sine functions respectively. Optimum combinations of training parameters have been observed. The effects of various combinations of training parameters are presented.
Similar content being viewed by others
References
Adetona, O. (1994) Multi-sensor integration using neural networks for predicting quality characteristics of end-milled parts: effect of training parameters and learning rules, M.S. Thesis, University of Missouri-Rolla, April.
Altintas, Y., Yellowley, I. and Tlusty, J. (1985) The detection of tool breakage in milling, Sensors and Controls for Manufacturing, WAM of the ASME, Florida, pp. 101–110, November 17–22, 1985.
Chryssolouris, G. and Domroese, M. (1988) Sensor integration for tool wear estimation in machining, Sensors and Controls for Manufacturing, ASME WAM, Chicago, Illinois, pp. 115–128, November 27–December 2, 1988.
Colwell, L.U. (1975) Cutting temperature versus tool wear Annals of the CIRP, 24(1), 73–76.
Dayhof, T. (1990) Neural Network Architectures An Introduction, Van Nostrand Reinhold.
De Filippi, A. and Ippolito, R. (1969) Adaptive control in turning: cutting forces and tool wear relationship for P10, P20, P30 carbides. Annals of the CIRP, 17, 337–385.
Dornfeld, D.A. (1991) Monitoring of the machining process by means of acoustic emission sensors, Acoustic Emission: Current Practice and Future Directions, ASTM STP 1077.
Eberhart, R.C. and Dobbins, R.W. (1990) Neural Network PC Tools: A Practical Guide, Academic Press, San Diego, CA.
Elanayar, S., Young, V.T., Shin, C. and Kumara, S. (1991) Machining condition monitoring for automation using neural networks, in Monitoring and Control for Manufacturing Processes, ASME Winter Annual Meeting, Dallas, Texas, pp. 85–100.
Ertekin, Y.M. (1993) Extended multi-sensor data characterization and prediction of surface roughness and bore tolerance in circular end milling, M.S. Thesis, University of Missouri-Rolla, May.
Freeman, J.A. and Skapura, D.M. (1991) Neural Networks: Algorithms, Applications, and Programming Techniques, Addison-Wesley, Reading, MA.
Kim, S. and Klamecki, B.E. (1990) Milling cutter wear monitoring using spindle shaft vibration, in Monitoring and Control for Manufacturing Processes, WAM of ASME, Dallas, Texas, 44, pp. 57–75, November 25–30.
Lan, M.S. and Dornfeld, D.A. (1982) Experimental studies of tool wear via acoustic emission analysis, in Proceedings of the 10th NAMRC, SME, pp. 305–311.
Lan, M.-S. and Yngve, N. (1986) In-process detection of tool breakage in milling. Journal of Engineering for Industry, 108, 191.
Lee, L.C., Lee, K.S. and Gran, C.S. (1989) On the correlation between dynamic cutting force and tool wear. International Journal of Machine Tools Manufacturing, 29(3), 295–303.
Lippmann, R.P. (1987) An introduction to computing with neural nets. IEEE ASSP Magazine, 4–22, April.
Liu, M. and Liang, Y.S. (1990) Monitoring of peripheral milling using acoustic emission. Transactions of NAMRI, SME, 120–127.
Liu, T.I. and Ko, E.J. (1991) On-line artificial neural networks, in ASME WAM, Dallas, Texas, pp. 1091–1110.
Masory, O. (1991) Monitoring machining processes using multi-sensor readings fused by artificial neural networks. Journal of Materials Processing Technology, 28 231–240.
Mehta, N.K., Pandy, P.C. and Chakravarti, G. (1983) An investigation of tool wear and the vibration spectrum in milling. Wear, 91, 219–234.
Micheletti, G.F., Koenig, W. and Victor, H.R. (1976) In-process tool wear sensors for cutting operation. Annals of CIRP, 25, 483–496.
Moriwaki, T. (1980) Detection of cutting tool fracture by acoustic emission measurements. Annals of CIRP, 29(1).
Okafor, A.C. (1993) Artificial neural networks: theory and applications in manufacturing, in Lean Manufacturing in the Automotive Industries, Proceedings of 26th International Symposium on Automotive Technology and Automation, Aachen, Germany, pp. 383–390.
Okafor, A.C. and Chyou, Y.J. (1988) A comparative investigation for on-line end-mill wear and breakage detection for unmanned machining, in Sensors and Controls for Manufacturing, WAM of the ASME, Chicago, Illinois, pp.105–114, November 27–December 2.
Okafor, A.C., Marcus, M.S. and Tipirneni, R. (1991) Multiple sensor integration via neural networks for estimating surface roughness and bore tolerance in circular end milling: part 1—time domain, Condition Monitoring and Diagnostic Technology Journal, 2(2), pp. 49–57.
Okafor, A.C., Ertekin, Y.M. and Arora, S. (1993) Intelligent machining monitoring and diagnostic system for quality assurance based on multi-sensor integration, in Proceedings of the 1993 NSF Design and Manufacturing Systems Conference, 2, pp. 1631–1638.
Rangwala, S. and Dornfeld, D.A. (1987) Integration of sensors via neural networks for detection of tool wear state, in Intelligent and Integrated Analysis and Synthesis, ASME Winter Annual Meeting, Boston, MA, pp. 109–120, December 12–13.
Rumelhart, D.E. and McClelland, J.L. (1989) Parallel Distributed Processing, Vol. 1, MIT Press, Cambridge, MA.
Tlusty, J. and Andrew, G.C. (1983) A critical review on sensors for unmanned manufacturing. Annals of CIRP, 32(2), 563–572.
Week, M. (1986) Development and application of a flexible, modular monitoring and diagnostic systems. Computers in Industry, 7, 45–51.
Wright, P.K. and Bourne, D.A. (1988) Manufacturing IntelliGence, Addison-Wesley, Reading, MA.
Yee, K.W. and Evans L. (1985) Drill-up an alternative for on-line determination of end-mill wear, in Proceedings 13th NAMR Conference, May 19–22, pp. 304–309.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Chukwujekwu Okafor, A., Adetona, O. Predicting quality characteristics of end-milled parts based on multi-sensor integration using neural networks: individual effects of learning parameters and rules. J Intell Manuf 6, 389–400 (1995). https://doi.org/10.1007/BF00124065
Issue Date:
DOI: https://doi.org/10.1007/BF00124065