Application of hybrid PSO and LS-SVR intelligent recognition of dual linear axis dynamic synchronization error characteristics

Authors:
Xiankun Lin;Bo Yuan;Shizhuo Han
Affiliations:
College of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, China;College of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, China;College of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, China
Venue:
IITA'09 Proceedings of the 3rd international conference on Intelligent information technology application
Year:
2009

Citing 4
Cited 0

The Behavior of Particles

EP '98 Proceedings of the 7th International Conference on Evolutionary Programming VII
Support Vector Regression and Classification Based Multi-View Face Detection and Recognition

FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
Machinery Fault Diagnosis Using Least Squares Support Vector Machine

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks, Part III
Load forecasting using fixed-size least squares support vector machines

IWANN'05 Proceedings of the 8th international conference on Artificial Neural Networks: computational Intelligence and Bioinspired Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

The synchronization error of feed axis has direct relation with contour error in interpolation motions. Recognition of synchronization error of dual linear motor driven axis with gantry frame has an important role in compensating the error to avoid the effect of contour precision. In the contribution, a combination of Particle Swarm Optimization (PSO) algorithm and Least Squares Support Vector Regression (LS-SVR) machine technique for intelligent recognition of dynamic synchronization error in dual linear axis feed process is presented. The 2d-time function of laser interferometer is applied in acquisition of the dynamic synchronization error data as recognition learning patterns. In recognition of various error characteristics during different process in the feed motion, dual important parameters of LSSVR, support vector number and error punishment factor, are tuned with PSO in an intelligent way. To demonstrate the procedure of the proposed approach, an illustration is discussed in detail. The result shows that the combination technique can decrease support number 38.5% and effectively recognize the characteristics with 9.04µm error under 40m/min feed rate motion condition.