Development of a thermal error compensation system for a CNC machine using a radial basis function neural network

Farias, Adalto de; Santos, Marcelo; Bordinassi, Ed Claudio

doi:10.1007/s40430-022-03812-4

Cited by 7 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After compensation, in the scenario of spindle speed variation, the spindle's axial thermal error exhibited a fluctuation range of −19.8 µm to 11.5 µm and of −11.9 µm to 7.7 µm in the scenario of spindle intermittent constant speed, which greatly reduced the error fluctuation range and improved the accuracy stability. de Farias et al [18] proposed an error compensation system grounded in the foundation of the radial basis function and carried out experiments on three-axis CNC machine equipment. In accordance with the obtained results, the thermal maximum error was reduced by 77.8% in a higher-temperature operating environment.…”

Section: Introductionmentioning

confidence: 99%

A Thermal Error Prediction Method of High-Speed Motorized Spindle Based on Pelican Optimization Algorithm and CNN-LSTM

Gao,

Xia,

Guo

2023

Applied Sciences

View full text Add to dashboard Cite

Given motorized spindles’ extensive periods of prolonged high-velocity operation, they are prone to temperature changes, which leads to the problem of thermal error, leading to diminished precision in machining operations. To address the thermal error issue in motorized spindles of computer numerical control (CNC) machine tools, this study proposes a pelican optimization algorithm (POA)-optimized convolutional neural network (CNN)–long short-term memory (LSTM) hybrid neural network model (POA-CNN-LSTMNN). Initially, the identification of temperature-sensitive locations in the spindle system is performed using a combination of hierarchical clustering, the K-medoids algorithm, and Pearson’s coefficient calculation. Subsequently, the temperature data from these identified points, along with real-time collected spindle thermal error data, are employed to construct the model. The Pelican optimization algorithm is used to enhance the model parameters to achieve the best performance. Finally, the proposed model is subjected to a comparative analysis with other thermal error prediction models. Drawing from the experimental findings, it is evident that the POA-CNN-LSTMNN model exhibits superior prediction performance.

show abstract

Section: Introductionmentioning

confidence: 99%

A Thermal Error Prediction Method of High-Speed Motorized Spindle Based on Pelican Optimization Algorithm and CNN-LSTM

Gao,

Xia,

Guo

2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…However, traditional methods mostly only predict short-term and medium-term aging, and when there are significant changes in the external environment, there will generally be significant deviations. Compared with traditional models, neural networks have better real-time prediction and persistence, and higher fault tolerance, which are more suitable for processing nonlinear system temperature prediction [24][25]. Therefore, the research is based on BPNN algorithm to predict the temperature information of CNC.…”

Section: Adaptive Tecmmentioning

confidence: 99%

Intelligent CNC control with improved adaptive thermal error compensation model

Shen,

Yang

2023

J. vibroeng.

View full text Add to dashboard Cite

The thermal errors (TE) of computer numerical control (CNC) in workshop production seriously reduces the productivity. Therefore, to improve the productivity of CNC and enhance production intelligence, an improved adaptive TE compensation model (TECM) is proposed. The model is based on an online temperature measurement system (OTMS), which improves the adaptive learning rate of back-propagation neural network (BPNN) for temperature prediction. Finally, the correlation value between temperature changes and TEs is used for thermal error compensation. The performance verification of the model shows that the proposed OTMS can achieve effective temperature acquisition and processing, and the prediction ability of the improved BPNN is significantly higher than that of other prediction algorithms. Finally, it is found in the test that the improved adaptive TECM can reduce the contour error of workpiece machining to within 0.02×10-3 mm, the machining accuracy of CNC is significantly improved. The above results show that using the improved adaptive TECM can promote the intelligent development of CNC and improve their machining accuracy, which is of great significance to the development of workshop manufacturing.

show abstract

Dynamic Thermal Compensation in CNC Machining: Modeling a Linear Kalman Filter for Enhanced Positional Accuracy

de Farias,

Brochado,

dos Santos

et al. 2024

Communications in Computer and Information Science

View full text Add to dashboard Cite

Development of a thermal error compensation system for a CNC machine using a radial basis function neural network

Cited by 7 publications

References 21 publications

A Thermal Error Prediction Method of High-Speed Motorized Spindle Based on Pelican Optimization Algorithm and CNN-LSTM

A Thermal Error Prediction Method of High-Speed Motorized Spindle Based on Pelican Optimization Algorithm and CNN-LSTM

Intelligent CNC control with improved adaptive thermal error compensation model

Dynamic Thermal Compensation in CNC Machining: Modeling a Linear Kalman Filter for Enhanced Positional Accuracy

Contact Info

Product

Resources

About