Open AccessPREDICTION OF MACHINE TOOL ROUGHNESS BASED ON ANN
Author(s) -
Hanfeng Jiang
Publication year - 2021
Publication title -
journal of physics conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1920/1/012096
Subject(s) - artificial neural network , matlab , machining , surface roughness , computer science , process (computing) , software , surface finish , numerical control , surface (topology) , artificial intelligence , engineering drawing , machine learning , mechanical engineering , engineering , mathematics , geometry , materials science , operating system , composite material , programming language
This paper presents a method based on ANN to predict the surface roughness of parts in machining process. The mathematical simulation software MATLAB is used to establish the ANN model, and it is found that the error between the predicted value and the actual data is very small, between 6 % and 15 %. This method can combine artificial neural network with machinery, which is instructive for future research. This method has low operation threshold, does not need too complex geometric operation, only need a lot of data can get good results. Therefore, the ANN method can be used to predict and control the surface roughness of the workpiece.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom