Articles | Volume 14, issue 1
https://doi.org/10.5194/ms-14-15-2023
https://doi.org/10.5194/ms-14-15-2023
Short communication
 | 
16 Jan 2023
Short communication |  | 16 Jan 2023

Short communication: Part contour error prediction based on LSTM neural network

Yun Zhang, Guangshun Liang, Cong Cao, Yun Zhang, and Yan Li

Viewed

Total article views: 1,041 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
864 157 20 1,041 21 17
  • HTML: 864
  • PDF: 157
  • XML: 20
  • Total: 1,041
  • BibTeX: 21
  • EndNote: 17
Views and downloads (calculated since 16 Jan 2023)
Cumulative views and downloads (calculated since 16 Jan 2023)

Viewed (geographical distribution)

Total article views: 1,005 (including HTML, PDF, and XML) Thereof 1,005 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 02 Jul 2024
Download
Short summary
A contour error prediction model based on LSTM (long short-term memory) is established. By inputting power, vibration signal, and temperature values, the contour error of parts can be predicted to adjust the feed speed in real time. In this way, we can obtain not only higher machining accuracy, but also higher machining efficiency and reduce the scrap rate. The model is compared with other models, and the optimal model is selected to obtain the optimal prediction effect.