Sage Journals: Discover world-class research

Abstract

A hybrid model, which is composed of an autoregressive moving-average (ARMA) filter and a feedforward neural network (FNN), is proposed to increase prediction accuracy and to reduce learning time for the estimation of thermal deformations in a machine tool. The ARMA filter is used to yield state variables which establish the relationship between the present and past states of thermal deformations for the reservation of the influences of past temperatures and deformation. Otherwise, the quantity of FNN inputs is very vast because of the data needed for the non-linear system. These state variables, which are estimated by past measured temperatures and past estimated deformation, serve as inputs of the FNN. The algorithms of this hybrid model are presented and verified by the experimental results; also, the prediction accuracy is compared with the ARMA and FNN independently for the same learning iterations.

Keywords

thermal deformation hybrid model autoregressive moving average neural network machine tools

References

Bryan

International status of thermal error research. Ann. CIRP, 1990, 39, 645–656.

Donmez

M. A.

Blomquist

R. J.

Hocken

R. J.

Liu

C. R.

Barash

M. M.

A general methodology for machine tool accuracy enhancement by error compensation. Precision Engng, 1986, 8(4), 187–195.

Chen

J. S.

Yuan

J. X.

S. M.

Realtime compensation for time-variant volumetric errors on a machining center. Trans. ASME, 1993, 115, 472–479.

Baker

Rao

B. K. N.

Hope

A. D.

Noroozi

Performance monitoring of a machining centre. In Proceedings of the IEEE Instrumentation and Measurement Technology Conference, Belgium, 4–6 June 1996, pp. 853–858 (IEEE, New York).

Lee

J. H.

Yang

S. H.

Fault diagnosis and recovery for a CNC machine tool thermal error compensation system. J. Mfg. Systems, 2001, 19(6), 428–434.

Zhang

A study of precompensation for thermal errors of NC machine tools. Int. J. Mach. Tools Mf., 1997, 37(12), 1715–1719.

Freeman

J. A.

Skapura

D. M.

Neural networks algorithms, applications, and programming techniques, 1992, (Addison-Wesley, New York).

Bebis

Georgiopoulos

Feed-forward neural network. IEEE Potentials, 1994, 13(4), 27–31.

Mou

A method of using neural networks and inverse kinematics for machine tools error estimation and correction. J. Mfg Sci. Engng, 1997, 119, 247–254.

10.

Vanherck

Dehaes

Nuttin

Compensation of thermal deformations in machine tools with neural nets. Computers Industry, 1997, 33, 119–125.

11.

Hattori

Noguchi

Ito

Suto

Inoue

Estimation of thermal deformation in machine tools using neural network technique. J. Mater. Processing Technol., 1996, 56, 765–772.

12.

Chen

J. S.

A study of thermally induced machine tool errors in real cutting conditions. Int. J. Mach. Tools Mf., 1996, 36(12), 1401–1411.

13.

Chen

J. S.

Fast calibration and modeling of thermally induced machine tool errors in real machining. Int. J. Mach. Tools Mf., 1997, 37(2), 159–169.

14.

Chen

J. S.

Chiou

Quick testing and modeling of thermally induced errors of CNC machine tools. Int. J. Mach. Tools Mf., 1995, 35(7), 1063–1074.

15.

Phak

H. J.

Lee

S. W.

Kwon

H. D.

Thermal error measurement and modeling techniques for the five-degree-of-freedom spindle drifts in computer numerically controlled machine tools. Proc. Instn Mech. Engrs, Part C: J. Mechanical Engineering Science, 2001, 215, 469–485.

Estimation of thermal deformation in machine tools using the hybrid autoregressive moving-average - neural network model

Abstract

Abstract

Keywords

References