Application and Study of Fuzzy Neural Network Theory Based on Takagi-Sugeno Model to Thermal Error Modeling on NC Machine Tool

2013 ◽  
Vol 744 ◽  
pp. 147-152
Author(s):  
Zi Jian Liu ◽  
Zhi Min Yu ◽  
Si Ming Li ◽  
Yan Di Ai
Keyword(s):  
Neural Network ◽  
Machine Tool ◽  
Fuzzy Neural Network ◽  
Thermal Error ◽  
Error Modeling ◽  
Nc Machine Tool ◽  
Fuzzy Neural ◽  
Nc Machine ◽  
Sugeno Model ◽  
Takagi Sugeno

For the degree of thermal deformation nonlinear is high and difficult to predict, fuzzy neural network modeling (FNN) based on Takagi-Sugeno model was applied to the NC machine tool thermal error modeling thus the complete thermal error fuzzy neural network mathematical model on NC machine tool was established and network parameters initialization and learning method were discussed. Thermal error experiment was conducted on large NC gantry rail grinder spindle box system and two independent groups of spindle thermal error data were collected, one was used to establish thermal error fuzzy neural network prediction model and another one was used to verify the prediction accuracy of this model. The test results show that fuzzy neural network model has high prediction accuracy.

Research on Thermal Error Modeling of NC Machine Tool Based on BP Neural Networks

2009 ◽  
Vol 626-627 ◽  
pp. 135-140 ◽  
Author(s):  
Qian Jian Guo ◽  
X.N. Qi
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Machine Tool ◽  
Ant Colony Algorithm ◽  
Thermal Error ◽  
Error Modeling ◽  
Minimum Problem ◽  
Bp Neural Networks ◽  
Nc Machine Tool ◽  
Nc Machine

Through analysis of the thermal errors affected NC machine tool, a new prediction model based on BP neural networks is presented, and ant colony algorithm is applied to train the weights of neural network model. Finally, thermal error compensation experiment is implemented, and the thermal error is reduced from 35μm to 6μm. The result shows that the local minimum problem of BP neural network is overcome, and the model accuracy is improved.

The Thermal Error Prediction of NC Machine Tool Based on LS-SVM and Grey Theory

2009 ◽  
Vol 16-19 ◽  
pp. 410-414 ◽  
Author(s):  
Chang Long Zhao ◽  
Yi Qiang Wang ◽  
Xue Song Guan
Keyword(s):  
Support Vector Machine ◽  
Correlation Analysis ◽  
Prediction Model ◽  
Machine Tool ◽  
Least Squares ◽  
Thermal Error ◽  
Support Vector ◽  
Error Prediction ◽  
Nc Machine Tool ◽  
Nc Machine

In this paper, a hybrid method of correlation analysis based on the gray theory and the least squares support vector machine is proposed to model the thermal error of spindle of NC machine tool and predict the thermal error. The gray correlation analysis is used to optimize the measuring points of spindle. The optimum measuring points and the measured thermal error of spindle are regarded as the data to be trained to build the thermal error prediction model based on the least squares support vector machine (LS-SVM). The results show that the thermal error prediction model based on LS-SVM of NC machine tool has advantages of high precision and good generalization performance. The prediction model can be used in real-time compensation of NC machine tool and can prove the process precision and reduce cost.

Error Compensation on a NC-Machine Tool Based on Integrated Intelligent Computation

2011 ◽  
Vol 121-126 ◽  
pp. 1436-1442
Author(s):  
Huang Lin Zeng ◽  
Yong Sun ◽  
Xiao Hong Ren ◽  
Li Xin Liu
Keyword(s):  
Neural Network ◽  
Machine Tool ◽  
Error Compensation ◽  
Ant Colony Algorithm ◽  
Rough Set Theory ◽  
Dynamic Feedback ◽  
Standard Equipment ◽  
Nc Machine Tool ◽  
Nc Machine ◽  
Feedback Neural Network

This paper is a study of the application of integrated intelligent computation to solve the problems of error compensation for high-precision a NC machining system. The primary focus is on the development of integrated intelligent computation approach to get an error compensation system which is a dynamic feedback neural network embedded in a NC machine tool. Optimization of error measurement points of a NC machine tool is realized by way of application of error variable attribute reduction on rough set theory. A principal component analysis is used for data compression and feature extraction to reduce the input dimension of a dynamic feedback neural network and reduce training time of the network. Taking advantage of ant colony algorithm on training of a dynamic feedback neural network does the global search so that network can converge to get a global optimum. Positioning error caused in thermal deformation compensation capabilities were tested using industry standard equipment and procedures. The results obtained shows that this approach can effectively improve compensation precision and real time of error compensation on machine tools.

Sign in / Sign up

Export Citation Format

Share Document