Correcting geometric deviations of CNC Machine-Tools: An approach with Artificial Neural Networks

Leite, Wanderson de Oliveira; Rubio, Juan Carlos Campos; Duduch, Jaime Gilberto; Almeida, Paulo

doi:10.1016/j.asoc.2015.07.014

Cited by 14 publications

(3 citation statements)

References 38 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some approaches use ML methods to estimate the surface roughness based on gathered sensor data or designed processing parameters in turning [25,26], drilling [27,28], laser cutting [29], and milling [30][31][32]. On the other hand, intelligent manufacturing systems with integrated AI algorithms can assist in process design to pre-compensate potential system errors, such as geometric deviation correction for CMC machines [33].…”

Section: Quality Prediction Based On Machine Learning Techniquesmentioning

confidence: 99%

Machine learning-enabled early prediction of dimensional accuracy for complex products of investment casting

Dong

Wang²,

Wang³

et al. 2023

Preprint

View full text Add to dashboard Cite

For the foundry industry, predicting the dimensional accuracy of investment precision castings is vital yet challenging. In order to reduce cost loss caused by out-of-tolerance phenomena, this work develops a data-driven framework for estimating and screening early products based on machine learning techniques. The hollow turbine blade is analyzed as a typical case for the proposed framework. Initially, a database was compiled from the same production line of wax patterns and corresponding castings. Feature engineering techniques were employed to choose the most important characteristics and simplify inputs, employing reject rate analysis and decision tree analysis. Random forest regressors (RFRs) were chosen as the fundamental models after a sensible selection of machine learning algorithms. To enhance the performance of RFRs, the results suggested that the thickness distribution of the source material is another crucial element in determining the dimensional correctness of castings. Ultimately, a hybrid metaheuristic strategy incorporating RFR and dung beetle optimization was developed. The results showed that the proposed prediction model could minimize the error by 22.4% compared to conventional models, making it an valuable tool for early dimensional quality evaluation and guiding wall thickness control for hollow turbine blades.

show abstract

Section: Quality Prediction Based On Machine Learning Techniquesmentioning

confidence: 99%

Machine learning-enabled early prediction of dimensional accuracy for complex products of investment casting

Dong

Wang²,

Wang³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Based on the theory of multi-body system (MBS), Kong et al [12] established a volumetric error model for ultra-precision machine tools. In addition, some scholars use neural network theory and stream of variation theory to analyze machine tool errors [13,14].…”

Section: Introductionmentioning

confidence: 99%

Effects of Machining Errors on Optical Performance of Optical Aspheric Components in Ultra-Precision Diamond Turning

Zhang

Lin

et al. 2020

Micromachines

View full text Add to dashboard Cite

Optical aspheric components are inevitably affected by various disturbances during their precision machining, which reduces the actual machining accuracy and affects the optical performance of components. In this paper, based on the theory of multi-body system, we established a machining error model for optical aspheric surface machined by fast tool servo turning and analyzed the effect of the geometric errors on the machining accuracy of optical aspheric surface. We used the method of ray tracing to analyze the effect of the surface form distortion caused by the machining error on the optical performance, and identified the main machining errors according to the optical performance. Finally, the aspheric surface was successfully applied to the design of optical lens components for an aerial camera. Our research has a certain guiding significance for the identification and compensation of machining errors of optical components.

show abstract

“…ANN is utilized for modelling and prediction purposes due to its advantages in nonlinear response and when time variability occurs. It covers the difficulty in inferring input/output mapping [4] and [5] and the search algorithms for optimization, based on genetic and evolution principles [6] to [8]. RSM is a reliable statistical tool for the mathematical modelling of engineering systems and for the optimization of different manufacturing processes.…”

Section: Introductionmentioning

confidence: 99%

Modelling and Prediction of Thrust Force and Torque in Drilling Operations of Al7075 Using ANN and RSM Methodologies

2018

SV-JME

View full text Add to dashboard Cite

Many developed approaches for the improvement of sustainability during machining operations; one of which is the optimized utilization of cutting tools. Increasing the efficient use of cutting tool results in better product quality and longer tool life. Drilling is one of the most popular manufacturing processes in the metal-cutting industry. It is usually carried out at the final steps of the production process. In this study, the effects of cutting parameters (cutting velocity, feed rate) and tool diameter on thrust force (Fz) and torque (Mz) are investigated in the drilling of an Al7075 workpiece using solid carbide tools. The full factorial experimental design is implemented in order to increase the confidence limit and reliability of the experimental data. Artificial neural networks (ANN) and response surface methodology (RSM) approaches are used to acquire mathematical models for both the thrust force (Fz) and torque (Mz) related to the drilling process. RSM-and ANN-based models are compared, and it is clearly determined that the proposed models are capable of predicting the thrust force (Fz) and torque (Mz). Nevertheless, the ANN models estimate in a more accurate way the outputs used in comparison to the RSM models.

show abstract

Correcting geometric deviations of CNC Machine-Tools: An approach with Artificial Neural Networks

Cited by 14 publications

References 38 publications

Machine learning-enabled early prediction of dimensional accuracy for complex products of investment casting

Machine learning-enabled early prediction of dimensional accuracy for complex products of investment casting

Effects of Machining Errors on Optical Performance of Optical Aspheric Components in Ultra-Precision Diamond Turning

Modelling and Prediction of Thrust Force and Torque in Drilling Operations of Al7075 Using ANN and RSM Methodologies

Contact Info

Product

Resources

About