scholarly journals An Unsupervised Regularization and Dropout based Deep Neural Network and Its Application for Thermal Error Prediction

2020 ◽  
Vol 10 (8) ◽  
pp. 2870
Author(s):  
Yang Tian ◽  
Guangyuan Pan
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Machine Tool ◽  
Deep Neural Network ◽  
Thermal Error ◽  
Error Modeling ◽  
Error Prediction ◽  
Learning Technology ◽  
Heavy Duty ◽  
Self Organizing

Due to the large size of the heavy duty machine tool-foundation systems, space temperature difference is high related to thermal error, which affects to system’s accuracy greatly. The recent highly focused deep learning technology could be an alternative in thermal error prediction. In this paper, a thermal prediction model based on a self-organizing deep neural network (DNN) is developed to facilitate accurate-based training for thermal error modeling of heavy-duty machine tool-foundation systems. The proposed model is improved in two ways. Firstly, a dropout self-organizing mechanism for unsupervised training is developed to prevent co-adaptation of the feature detectors. In addition, a regularization enhanced transfer function is proposed to further reduce the less important weights of the process and improve the network feature extraction capability and generalization ability. Furthermore, temperature sensors are used to acquire temperature data from the heavy-duty machine tool and concrete foundation. In this way, sample data of thermal error predictive model are repeatedly collected from the same locations at different times. Finally, accuracy of the thermal error prediction model was validated by thermal error experiments, thus laying the foundation for subsequent studies on thermal error compensation.

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.

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.

scholarly journals Research on Thermal Error Modeling of Motorized Spindle Based on BP Neural Network Optimized by Beetle Antennae Search Algorithm

Machines ◽  
2021 ◽  
Vol 9 (11) ◽  
pp. 286
Author(s):  
Zhaolong Li ◽  
Bo Zhu ◽  
Ye Dai ◽  
Wenming Zhu ◽  
Qinghai Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Bp Neural Network ◽  
High Speed ◽  
Search Algorithm ◽  
Thermal Error ◽  
Error Prediction ◽  
Machining Accuracy ◽  
Motorized Spindle ◽  
Thermal Error Model

High-speed motorized spindle heating will produce thermal error, which is an important factor affecting the machining accuracy of machine tools. The thermal error model of high-speed motorized spindles can compensate for thermal error and improve machining accuracy effectively. In order to confirm the high precision thermal error model, Beetle antennae search algorithm (BAS) is proposed to optimize the thermal error prediction model of motorized spindle based on BP neural network. Through the thermal characteristic experiment, the A02 motorized spindle is used as the research object to obtain the temperature and axial thermal drift data of the motorized spindle at different speeds. Using fuzzy clustering and grey relational analysis to screen temperature-sensitive points. Beetle antennae search algorithm (BAS) is used to optimize the weights and thresholds of the BP neural network. Finally, the BAS-BP thermal error prediction model is established. Compared with BP and GA-BP models, the results show that BAS-BP has higher prediction accuracy than BP and GA-BP models at different speeds. Therefore, the BAS-BP model is suitable for prediction and compensation of spindle thermal error.

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.

Study on the Application of the Combined Prediction Modeling Method to Thermal Error Modeling on NC Machine Tools

2007 ◽  
Vol 329 ◽  
pp. 779-784 ◽  
Author(s):  
Y.X. Li ◽  
Jian Guo Yang ◽  
Yu Yao Li ◽  
H.T. Zhang ◽  
G. Turyagyenda
Keyword(s):  
Prediction Model ◽  
Machine Tool ◽  
Thermal Error ◽  
Error Modeling ◽  
Primary Data ◽  
Analysis Model ◽  
Grey System ◽  
Trend Prediction ◽  
Thermal Error Modeling ◽  
Thermal Errors

Due to the complexity of machine tool thermal errors affected by various factors, a new combining prediction model, based on the theory of gery system GM (1,1) model, is applied to the trend prediction of machine tool thermal errors. The degree of smoothness of primary data sequence is first improved by function transform method and sequentially grey system GM (1,1) model is established; second, time series analysis model is established by remnant sequence of GM (1,1) model to amend the precision of grey system GM (1,1) model. Thus, the precision of combining prediction model is further improved. Through the prediction study on thermal error modeling in a spot NC turning center, testing results showed that combining prediction model can highly improve machine tool’s prediction precision and make it more effective for real-time compensation of machine tool thermal error.

Application of Partial Least Squares Neural Network in Thermal Error Modeling for CNC Machine Tool

2008 ◽  
Vol 392-394 ◽  
pp. 30-34 ◽  
Author(s):  
J.H. Shen ◽  
Jian Guo Yang
Keyword(s):  
Neural Network ◽  
Machine Tool ◽  
Least Squares ◽  
Partial Least Squares ◽  
Thermal Error ◽  
Error Modeling ◽  
Neural Network Modeling ◽  
Cnc Machine Tool ◽  
Cnc Machine ◽  
Thermal Error Modeling

This paper presents a partial least squares neural network modeling method for CNC machine tool thermal errors. This method uses the neural network learning rule to obtain the PLS parameters instead of the traditional linear method in partial least squares regression so as to overcome the multicollinearity and nonlinearity problem in thermal error modeling. The basic principle and architecture of PLSNN is described and the new method is applied on the thermal error modeling for a CNC turning center. After model validation with two groups of new testing data and performance comparison with other five different modeling methods, PLSNN performs better than the others with better robustness.

Sign in / Sign up

Export Citation Format

Share Document