Thermal Error Modeling and Compensating of Motorized Spindle Based on Improved Neural Network

2010 ◽  
Vol 129-131 ◽  
pp. 556-560 ◽  
Author(s):  
Chun Li Lei ◽  
Zhi Yuan Rui
Keyword(s):  
Neural Network ◽  
High Speed ◽  
Thermal Deformation ◽  
Influence Factors ◽  
Thermal Error ◽  
Error Modeling ◽  
Motorized Spindle ◽  
Key Factor ◽  
Manufacturing Accuracy ◽  
Thermal Error Model

In a lot of factors, thermal deformation of motorized high-speed spindle is a key factor affecting the manufacturing accuracy of machine tool. In order to reduce the thermal errors, the reasons and influence factors are analyzed. A thermal error model, that considers the effect of thermodynamics and speed on the thermal deformation, is proposed by using genetic algorithm-based radial basis function neural network. The improved neural network has been trained and tested, then a thermal error compensation system based on this model is established to compensate thermal deformation. The experiment results show that there is a 79% decrease in motorized spindle errors and this model has high accuracy.

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.

scholarly journals Thermal Error Prediction of Ball Screws Based on PSO-LSTM

2021 ◽  
Author(s):  
Xiangsheng Gao ◽  
Yueyang Guo ◽  
Dzonu Ambrose Hanson ◽  
Zhihao Liu ◽  
Min Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
High Speed ◽  
Thermal Characteristic ◽  
Thermal Error ◽  
Error Model ◽  
Cnc Machine Tools ◽  
Error Prediction ◽  
Model Based ◽  
Thermal Error Model

Abstract Thermal error of ball screws seriously affects the machining precision of CNC machine tools especially in high speed and precision machining. Compensation technology is one of the most effective methods to address the thermal issue, and the effect of compensation depends on the accuracy and robustness of the thermal error model. Traditional modeling approaches have major challenges in time-series thermal error prediction. In this paper, a novel thermal error model based on Long Short-Term Memory (LSTM) neural network and Particle Swarm Optimization (PSO) algorithm is proposed. A data-driven model based on LSTM neural network is established according to the time-series collected data. The hyperparameters of LSTM neural network are optimized by PSO and then a PSO-LSTM model is established to precisely predict the thermal error of ball screws. In order to verify the effectiveness and robustness of the proposed model, two thermal characteristic experiments based on step and random speed are conducted on a self-designed test bench. The results show that the PSO-LSTM model has higher accuracy compared with the RBF model and BP model with high robustness. The proposed method can be implemented to predict the thermal error of ball screws, and provide a foundation for thermal error compensation.

Novel thermal error modeling method for machining centers

2014 ◽  
Vol 229 (8) ◽  
pp. 1500-1508 ◽  
Author(s):  
Xiaolong Zhu ◽  
Sitong Xiang ◽  
Jianguo Yang
Keyword(s):  
Neural Network ◽  
Vector Quantization ◽  
Thermal Deformation ◽  
Clustering Algorithm ◽  
Thermal Error ◽  
Network Clustering ◽  
Elman Neural Network ◽  
Machining Center ◽  
Adaptive Vector Quantization ◽  
Thermal Error Model

Thermal deformation is one of the main contributors to machining errors in machine tools. In this paper, a novel approach to build an effective thermal error model for a machining center is proposed. Adaptive vector quantization network clustering algorithm is conducted to identify the temperature variables, and then one temperature variable is selected from each cluster to represent the same cluster. Furthermore, a non-linear model based on output-hidden feedback Elman neural network is adopted to establish the relationship between thermal error and temperature variables. The output-hidden feedback Elman network is adopted to predict the thermal deformation of the machining center. Back propagation (BP) neural network is introduced for comparison. A verification experiment on the machining center is carried out to validate the efficiency of the newly proposed method. Experimental verification shows that the adaptive vector quantization network clustering algorithm and output-hidden feedback Elman neural network is an accurate and effective method.

Comparison of Forecasting Methods for Thermal Error on High-Speed Motorized Spindle

2011 ◽  
Vol 291-294 ◽  
pp. 2991-2994 ◽  
Author(s):  
Chun Li Lei ◽  
Zhi Yuan Rui ◽  
Jun Liu ◽  
Jing Fang Fang
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
High Speed ◽  
Operation Time ◽  
Thermal Error ◽  
Motorized Spindle ◽  
Curve Fit ◽  
Forecast Precision ◽  
Nc Machine

In order to reduce the thermal error of the motorized spindle and improve the manufacturing accuracy of NC machine tool, the thermal error forecasting models based on multivariate autoregressive (MVAR) method and genetic radial basis function (GARBF) neural network method are proposed, respectively. According to different representations of generation mechanism of motorized spindle thermal deformation, operation efficiency and curve fit precision of these two models are compared. The studied results show that under the same temperature rise variable conditions, MVAR model and GARBF neural network model have almost the same convergence and operation time and relative errors of two models are less than 3%. The results also show that the MVAR model has higher forecast precision in the prediction former stages; in contrast, the GARBF neural network model has higher forecast precision in the latter stages.

Research on Thermal Error Modeling of YK3610 Hobbing Machine

2012 ◽  
Vol 426 ◽  
pp. 293-296
Author(s):  
Qian Jian Guo ◽  
Jian Guo Yang
Keyword(s):  
Neural Network ◽  
Error Compensation ◽  
Back Propagation ◽  
Thermal Error ◽  
Back Propagation Neural Network ◽  
Error Modeling ◽  
Daily Production ◽  
Machine Error ◽  
Thermal Error Modeling ◽  
Thermal Error Model

Thermal error modeling. Neural network. Gear hobbing machine. Error compensation. Abstract. Four key thermal sources of YK3610 hobbing machine were selected in this paper, and a thermal error model based on the four temperature variables was proposed by using back propagation neural network. A thermal error compensation system was developed based on the proposed model, and which has been applied to the YK3610 hobbing machine in daily production. The result shows that the prediction accuracy of thermal deformation in the YK3610 hobbing machine has been improved.

FEA of Thermal Characteristic of Motorized Spindle Based on ANSYS Workbench

2013 ◽  
Vol 437 ◽  
pp. 36-41
Author(s):  
Kai Kang Chen ◽  
Fu Ping Li ◽  
Yong Sheng Zhao
Keyword(s):  
High Speed ◽  
Thermal Deformation ◽  
Thermal Characteristic ◽  
Thermal Error ◽  
Machining Accuracy ◽  
Motorized Spindle ◽  
Thermal Boundary Conditions ◽  
Steady State Temperature ◽  
Transient Thermal ◽  
Ansys Workbench

Thermal deformation of high-speed motorized spindle has an important effect on improving the machining accuracy. In this paper the thermal boundary conditions of thermal deformation, including the heat generation of the motor and bearing and heat transfer coefficient, are calculated to simulate the steady-state temperature field distribution, transient thermal analysis and thermal deformation in ANSYS Workbench. They provide theoretically the data for the thermal error compensation of the spindle system.

Thermal Error Modeling Based on Genetic Algorithm and BP Neural Network of High-Speed Spindle System

2015 ◽  
Author(s):  
Chi Ma ◽  
Liang Zhao ◽  
Hu Shi ◽  
Xuesong Mei ◽  
Jun Yang
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Correlation Analysis ◽  
Bp Neural Network ◽  
High Speed ◽  
Thermal Error ◽  
Error Modeling ◽  
Bp Network ◽  
Error Models ◽  
Hidden Layer

In order to improve the prediction accuracy of the thermal error models, grey cluster grouping and correlation analysis were proposed to optimize and select the heat-sensitive points to improve the performances of the thermal error model and minimize the independent variables to reduce modeling cost. Subsequently, the neural network with back propagation (BP) algorithm was proposed to construct the strongly nonlinear mapping relationship between spindle thermal errors and typical temperature variables. However, the shortcomings of the BP network restricted the accuracy, robustness and convergence of thermal error models. Then, a genetic algorithm (GA), which regarded the reciprocal of the absolute value sum of the differences between the predicted and desired outputs as the number of nodes in the hidden layer, was proposed to optimize the structure and initial values of the network. And the number of the nodes in the hidden layer can be determined by performing such operations of GAs. Moreover, the reciprocal of the sum square of the difference between the predicted and expected outputs of individuals is regarded as the fitness function and the weights and thresholds of the BP neural network are optimized by setting the control parameters of GAs. Then, the elongation and thermal tilt angle models of high-speed spindles were proposed based on BP and GA-BP networks and the fitting and prediction abilities were compared. The results showed that the grey cluster grouping and correlation analysis could depress the multicollinearity among temperature variables and improve the stability and accuracy of the thermal error models. Moreover, although the traditional BP network had better fitting ability, its convergence and generality were far worse than the GA-BP model and it is more suitable to use the GA-BP neural network as the thermal error modeling method in the compensation system.

Optimization of Measuring Points for High-Speed Motorized Spindle Thermal Error

2012 ◽  
Vol 538-541 ◽  
pp. 2113-2116
Author(s):  
Wei Dong Gou ◽  
Xin Wei Ye ◽  
Chun Li Lei ◽  
Zhi Yuan Rui
Keyword(s):  
High Speed ◽  
Thermal Deformation ◽  
Thermal Error ◽  
Coefficient Of Determination ◽  
Motorized Spindle ◽  
Temperature Field Distribution ◽  
Measuring Point ◽  
Temperature Measuring ◽  
Key Points ◽  
Fuzzy Clustering Method

According to the location and number of temperature measuring points of the motorized spindle thermal error, a new method for optimizing the locations of thermal key points is proposed. Firstly, temperature measuring points are divided into groups by using fuzzy clustering method. Secondly, grey correlation model is adopted to analyze emphasis of each measuring point to thermal deformation in temperature field distribution of motorized spindle. Finally, temperature measuring points have been optimally selected based on modified coefficient of determination. Comparing to the conclusion of the existed literature, the results show that this method is feasibility and validity. The method can reduce the temperature variables and modeling time, and supply the theoretic support for the engineering experience.

Thermal error modeling and compensation for a high-speed motorized spindle

2014 ◽  
Vol 77 (5-8) ◽  
pp. 1005-1017 ◽  
Author(s):  
Jun Yang ◽  
Hu Shi ◽  
Bin Feng ◽  
Liang Zhao ◽  
Chi Ma ◽  
...  
Keyword(s):  
High Speed ◽  
Thermal Error ◽  
Error Modeling ◽  
Motorized Spindle ◽  
Thermal Error Modeling

Temperature Rise Prediction of Oil-Air Lubricated Angular Contact Ball Bearings Using Artificial Neural Network

2019 ◽  
Vol 12 (3) ◽  
pp. 248-261
Author(s):  
Baomin Wang ◽  
Xiao Chang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Temperature Rise ◽  
High Speed ◽  
Ball Bearing ◽  
Influence Factors ◽  
Ball Bearings ◽  
Ann Model ◽  
Angular Contact Ball Bearing ◽  
Artificial Neural

Background: Angular contact ball bearing is an important component of many high-speed rotating mechanical systems. Oil-air lubrication makes it possible for angular contact ball bearing to operate at high speed. So the lubrication state of angular contact ball bearing directly affects the performance of the mechanical systems. However, as bearing rotation speed increases, the temperature rise is still the dominant limiting factor for improving the performance and service life of angular contact ball bearings. Therefore, it is very necessary to predict the temperature rise of angular contact ball bearings lubricated with oil-air. Objective: The purpose of this study is to provide an overview of temperature calculation of bearing from many studies and patents, and propose a new prediction method for temperature rise of angular contact ball bearing. Methods: Based on the artificial neural network and genetic algorithm, a new prediction methodology for bearings temperature rise was proposed which capitalizes on the notion that the temperature rise of oil-air lubricated angular contact ball bearing is generally coupling. The influence factors of temperature rise in high-speed angular contact ball bearings were analyzed through grey relational analysis, and the key influence factors are determined. Combined with Genetic Algorithm (GA), the Artificial Neural Network (ANN) model based on these key influence factors was built up, two groups of experimental data were used to train and validate the ANN model. Results: Compared with the ANN model, the ANN-GA model has shorter training time, higher accuracy and better stability, the output of ANN-GA model shows a good agreement with the experimental data, above 92% of bearing temperature rise under varying conditions can be predicted using the ANNGA model. Conclusion: A new method was proposed to predict the temperature rise of oil-air lubricated angular contact ball bearings based on the artificial neural network and genetic algorithm. The results show that the prediction model has good accuracy, stability and robustness.

Sign in / Sign up

Export Citation Format

Share Document