An RBF neural network approach to geometric error compensation with displacement measurements only

Abstract A novel radial basis function (RBF) neural network-based geometric error compensation method with displacement measurements only is proposed in this paper. The individual geometric error components are formulated mathematically based on laser interferometer calibration with displacement measurements only and modeled using RBF neural network for error compensation in motion controller. Only 4 and 15 displacement measurements are required to identify the error components for XY and XYZ table, respectively. The experiment results on two XY tables illustrate the effectiveness of the proposed method. The overall errors can be reduced significantly after compensation, and different data intervals can be selected to reduce calibration time but maintain a high level of accuracy. The proposed methodology can be extended to other types of precision machine and is more suitable for precision machines requiring a relative low level of accuracy, but fast calibration like those used for acceptance testing and periodic checking.

[1]  Li Zhuang,et al.  Integrated geometric error modeling, identification and compensation of CNC machine tools , 2012 .

[2]  Lee Tong Heng,et al.  Precision Motion Control: Design and Implementation , 2008 .

[3]  Steven D. Phillips,et al.  Results of the NIST National Ball Plate Round Robin , 1997, Journal of Research of the National Institute of Standards and Technology.

[4]  C. R. Liu,et al.  A Contribution to the Analysis and Compensation of the Geometric Error of a Machining Center , 1986 .

[5]  Jianzhong Fu,et al.  Numerical solution of simultaneous equations based geometric error compensation for CNC machine tools with workpiece model reconstruction , 2016 .

[6]  Mariano Artés,et al.  A New Methodology for Vibration Error Compensation of Optical Encoders , 2012, Sensors.

[7]  Juntao Fei,et al.  Robust adaptive neural sliding mode control of MEMS triaxial gyroscope with angular velocity estimation , 2012, Neural Computing and Applications.

[8]  Samaneh Hamedi,et al.  Efficient performance of neural networks for nonlinearity error modeling of three-longitudinal-mode interferometer in nano-metrology system , 2012 .

[9]  B. Lu,et al.  A Displacement Method for Machine Geometry Calibration , 1988 .

[10]  Reza Shahnazi,et al.  PSO-RBF Based control Schema for Adaptive Active Queue Management in TCP Networks , 2017 .

[11]  Y. Lin,et al.  Modelling of Five-Axis Machine Tool Metrology Models Using the Matrix Summation Approach , 2003 .

[12]  Shuang Ding,et al.  Identification of different geometric error models and definitions for the rotary axis of five-axis machine tools , 2016 .

[13]  Kok Kiong Tan,et al.  An RBF neural network approach towards precision motion system with selective sensor fusion , 2016, Neurocomputing.

[14]  Lakhmi C. Jain,et al.  Radial Basis Function Networks 2: New Advances in Design , 2001 .

[15]  Kaiguo Fan,et al.  Unified error model based spatial error compensation for four types of CNC machining center: Part II-unified model based spatial error compensation , 2014 .

[16]  S. Sartori,et al.  Geometric Error Measurement and Compensation of Machines , 1995 .

[17]  P. Pedone,et al.  Low-cost interferometric compensation of geometrical errors , 2009 .

[18]  Jorge Santolaria,et al.  Identification strategy of error parameter in volumetric error compensation of machine tool based on laser tracker measurements , 2012 .

[19]  James D. Keeler,et al.  Layered Neural Networks with Gaussian Hidden Units as Universal Approximations , 1990, Neural Computation.

[20]  Sonko Osawa,et al.  Geometric calibration of a coordinate measuring machine using a laser tracking system , 2005 .

[21]  Alexander Friz,et al.  Three-dimensional metrology in MEMS applications , 2002, SPIE Advanced Lithography.

[22]  Kok Kiong Tan,et al.  Adaptive Friction Compensation With a Dynamical Friction Model , 2011, IEEE/ASME Transactions on Mechatronics.

[23]  Xin Chen,et al.  Disturbance attenuation for nonlinear switched descriptor systems based on neural network , 2012, Neural Computing and Applications.

[24]  Kok Kiong Tan,et al.  Adaptive robust control for servo manipulators , 2003, Neural Computing & Applications.

[25]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[26]  Xuesong Mei,et al.  Geometric error modeling and compensation for large-scale grinding machine tools with multi-axes , 2013 .

[27]  Jun Ni,et al.  A displacement measurement approach for machine geometric error assessment , 2001 .

[28]  Fuad E. Alsaadi,et al.  A new approach to non-fragile state estimation for continuous neural networks with time-delays , 2016, Neurocomputing.