z-logo
open-access-imgOpen Access
Study on straightness prediction of centerless grinding of slender rod based on PCA and Markov
Author(s) -
Xin-Chun Chen,
Peng Ding,
Can Wang,
Ning Yan
Publication year - 2020
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 - 10.1088/1742-6596/1633/1/012157
Subject(s) - grinding , machining , mechanical engineering , cylinder , piston (optics) , rod , markov chain , computer science , engineering , machine learning , medicine , physics , alternative medicine , pathology , wavefront , optics
In order to optimize the processing parameters of slender rods and achieve high-precision machining, a method of straightness prediction of centerless grinding based on PCA and Markov is proposed. A straightness measuring device for slender rod is developed to collect data. The accumulated straightness data is divided into typical processing conditions. The parameters that affect the straightness of centerless grinding of slender rod are analyzed based on PCA. According to the correlation between the parameters and the degree of influence on the straightness, the construction of the processing conditions is further simplified. On this basis, the straightness prediction model based on PCA and Markov is established to predict the processing conditions of centerless grinding of slender rods. Taking the centerless grinding of the piston rod of a hydraulic cylinder as an example, the machining experimental research is conducted. The predictive value is compared with the actual measured value, and the result shows that the average error rate is 3.94%, which indicates the effectiveness of the prediction method and meets the needs of actual production. This study provided technical support for parameters optimization of centerless grinding of slender rods parameter optimization and high-precision machining.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.
Having issues? You can contact us here