.png){kind=icon}
Return
Surface Reconstruction Using Geometric Features and Machining Process
.png){kind=icon}
PRE
AI
DOI：10.1109/TIM.2024.3353870.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Coordinate measuring machines (CMMs) are frequently used in precise measurement applications and play a crucial role in profile error assessment. One widely adopted method for enhancing profile error evaluation efficiency is the reconstruction of dense errors after sparse CMM sampling. However, Nyquist's sampling theorem restricts the accuracy of reconstruction from CMM sampling, thus posing significant challenges for improving reconstruction accuracy. In this article, we present a method for reconstructing surfaces by fusing data from multiple features, circumventing the limitations of the sampling theorem. We constructed a machining simulation dataset with multiple features and used it to learn reconstruction strategies. Moreover, we devised a multifeature data fusion model (MfDFM) that adds high-frequency geometric information to measurement data, resulting in highly accurate surface reconstruction. A spatial attention mechanism is presented to improve reconstruction performance at full sample rates. Thorough experimentation on real workpieces confirms the efficacy of both our dataset and the proposed reconstruction method.
Keywords:
Machining
Surface reconstruction
Solid modeling
Servomotors
Measurement uncertainty
Image reconstruction
Reconstruction algorithms
Measurement
neural networks
profile error
surface reconstruction
Journal
IF:
5.9
Papers:
2.0W
Citations:
5.8W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSave
Dimensional and geometrical errors of three-axis CNC milling machines in a virtual machining system
OAAI
OAAIShareSave
View more