Y. Kang, C.-W. Chang, M.-H. Chu, Y.-P. Chang, and S.-Y. Chien (Taiwan)
: Thermal deformation, Hybrid model, ARMA, Neural network, Machine tools
Two hybrid models consisted of ARMA model and the FNN (feed-forward neural network) are proposed to increase the prediction accuracy and reduce the learning time for prediction of the thermal deformation in machine tools. The ARMA model is used to preprocess the measured temperatures and thermal deformations, and its outputs are treated as the inputs of the FNN. The input variables of the FNN can be reduced , and the hybrid models can describe the relationships between the variations of temperature and the thermal deformations. This proposed models are compared with the conventional ARMA model and the FNN model. The experiment results show the hybrid models can obtain the better prediction accuracy under the same learning iterations.
Important Links:
Go Back
