scholarly journals The Thermal Error Estimation of the Machine Tool Spindle Based on Machine Learning

Machines ◽  
2021 ◽  
Vol 9 (9) ◽  
pp. 184
Author(s):  
Yu-Cheng Chiu ◽  
Po-Hsun Wang ◽  
Yuh-Chung Hu
Keyword(s):  
Machine Learning ◽  
Machine Tool ◽  
Random Forests ◽  
Pearson Correlation ◽  
Gaussian Process Regression ◽  
Correlation Coefficients ◽  
Thermal Error ◽  
Error Modeling ◽  
Machining Process ◽  
Tool Manufacture

Thermal error is one of the main sources of machining error of machine tools. Being a key component of the machine tool, the spindle will generate a lot of heat in the machining process and thereby result in a thermal error of itself. Real-time measurement of thermal error will interrupt the machining process. Therefore, this paper presents a machine learning model to estimate the thermal error of the spindle from its feature temperature points. The authors adopt random forests and Gaussian process regression to model the thermal error of the spindle and Pearson correlation coefficients to select the feature temperature points. The result shows that random forests collocating with Pearson correlation coefficients is an efficient and accurate method for the thermal error modeling of the spindle. Its accuracy reaches to 90.49% based on only four feature temperature points—two points at the bearings and two points at the inner housing—and the spindle speed. If the accuracy requirement is not very onerous, one can select just the temperature points of the bearings, because the installation of temperature sensors at these positions is acceptable for the spindle or machine tool manufacture, while the other positions may interfere with the cooling pipeline of the spindle.

Evaluating yield strength of Ni-based superalloys via high throughput experiment and machine learning

2021 ◽  
pp. 2050015
Author(s):  
Feng Liu ◽  
Zexin Wang ◽  
Zi Wang ◽  
Zijun Qin ◽  
Zihang Li ◽  
...  
Keyword(s):  
Machine Learning ◽  
Yield Strength ◽  
High Throughput ◽  
Pearson Correlation ◽  
Gaussian Process Regression ◽  
Correlation Coefficients ◽  
High Entropy ◽  
Feature Importance ◽  
Key Factor ◽  
The Individual

Yield strength (YS) is a key factor during design and application of Ni-based superalloys with complex compositions, hence it is of great significance to evaluate the YS prior to manufacturing. In this work, alloy diffusion-multiple technology was employed as a high-throughput way to yield the hardness dataset. Based on the composition and other descriptors, Pearson correlation coefficients, stability selection and feature importance were used to select the efficient feature variables. Thereafter, six different machine learning models were applied to predict the YS. Finally, the individual and interaction effect of Co and Mo could be effectively detected by the Gaussian process regression (GPR) model. The optimum composition of Ni-based superalloys with the largest YS at room temperature was determined using the trained GPR model and genetic algorithm. This method can be extended to predict the YS in other multicomponent alloys, such as Ti alloys, Co-based alloys, and high entropy alloys.

Application of a Bayesian Network to Thermal Error Modeling and Analysis for Machine Tool

2010 ◽  
Vol 455 ◽  
pp. 616-620
Author(s):  
X. Li ◽  
Q. Lei ◽  
Z.H. Li
Keyword(s):  
Machine Tool ◽  
Bayesian Network ◽  
Error Compensation ◽  
Process Condition ◽  
Thermal Error ◽  
Error Modeling ◽  
Machining Process ◽  
Cnc Machine ◽  
Thermal Error Modeling ◽  
Thermal Error Compensation

CNC machine tool dynamic thermal error compensation has always been a hot issue to improving precision. This dissertation proposes a method of machine tool thermal error modeling during processing, based on Bayesian network theory, by describing the correlation between the various factors of generated the heat error, through the sample data, analyzed and simplified the intrinsic correlation between these various factors, established the basic thermal error compensation model, and used the network’s good characteristic of self-studying, combining the result of update collection data, continually modify the model to reflect the machining process condition changes. Finally, the experimental results show the feasibility of Bayesian network model, it was a stronger application for achieving the thermal error compensation.

Numerical Analysis of Thermal Error for a 4-Axises Horizontal Machining Center

2017 ◽  
Vol 868 ◽  
pp. 64-68
Author(s):  
Yu Bin Huang ◽  
Wei Sun ◽  
Qing Chao Sun ◽  
Yue Ma ◽  
Hong Fu Wang
Keyword(s):  
Machine Tool ◽  
Working Condition ◽  
Prediction Method ◽  
Thermal Error ◽  
Error Modeling ◽  
Model Verification ◽  
Design Stage ◽  
Thermal Errors ◽  
Machining Center ◽  
Machining Errors

Thermal deformations of machine tool are among the most significant error source of machining errors. Most of current thermal error modeling researches is about 3-axies machine tool, highly reliant on collected date, which could not predict thermal errors in design stage. In This paper, in order to estimate the thermal error of a 4-axise horizontal machining center. A thermal error prediction method in machine tool design stage is proposed. Thermal errors in workspace in different working condition are illustrated through numerical simulation and volumetric error model. Verification experiments shows the outcomes of this prediction method are basically correct.

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.

Thermal Error Modeling and Prediction of a Heavy Floor-Type Milling and Boring Machine Tool

2015 ◽  
Author(s):  
Fengchun Li ◽  
Tiemin Li ◽  
Haitong Wang
Keyword(s):  
Boundary Conditions ◽  
Machine Tool ◽  
Superposition Principle ◽  
Engineering Application ◽  
Thermal Error ◽  
Error Modeling ◽  
Simulation Data ◽  
Thermal Error Modeling ◽  
Fea Model ◽  
Modeling And Prediction

Thermal error modeling and prediction of a heavy floor-type milling and boring machine tool was studied in this paper. An FEA model and a thermal network of the machine tool’s ram was established. The influence of boundary conditions on thermal error was studied to find out the boundary conditions that needn’t to be calculated precisely, reducing the time cost of the work. Superposition principle of heat sources was used in the FEA to get the simulation data of thermal error and temperature. A model based on the simulation data was established to predict the thermal error during the work process. An experiment was performed to verify the accuracy of the model. The result shows that the model accuracy is 87%. The method in this paper is expected to be used in engineering application.

Sign in / Sign up

Export Citation Format

Share Document