PRINCIPLES OF DEVELOPING EXPRESS METHODS FOR EVALUATING THE SURFACE QUALITY OF PARTS
Authors:
1.
Soloviev Rybinsk State Aviation Technical University
(kafedra "Matematicheskoe i programmnoe obespechenie elektronnyh vychislitel'nyh sredstv", zaveduyuschiy)
Rybinsk, Yaroslavl, Russian Federation
Rybinsk, Yaroslavl, Russian Federation
2.
Soloviev Rybinsk State Aviation Technical University
Type:
Сonference article
Published:
13.04.2020
Subject area:
UDK 62 Инженерное дело. Техника в целом. Транспорт
GRNTI 55.13 Технология машиностроения
GRNTI 55.13 Технология машиностроения
Language:
Russian
Keywords:
roughness, the Express-method; automation of the evaluation parameters, the quality of a surface; machine learning
Abstract (English):
An approach to solving the problem of estimating surface profile parameters based on machine learning is considered. The proposed principles of development of Express-methods for automated evaluation of the profile on various parameters. An example of implementing an Express method based on the developed classification model is considered
An approach to solving the problem of estimating surface profile parameters based on machine learning is considered. The proposed principles of development of Express-methods for automated evaluation of the profile on various parameters. An example of implementing an Express method based on the developed classification model is considered
Keywords:
roughness, the Express-method; automation of the evaluation parameters, the quality of a surface; machine learning
roughness, the Express-method; automation of the evaluation parameters, the quality of a surface; machine learning
1. Tabenkin A. N. Sherohovatost', volnistost', profil'. Mezhdunarodnyy opyt / A.N. Tabenkin, S.B. Tarasov, S.N. Stepanov. Pod red. kand. tehn. nauk N.A. Tabachnikovoy. – SPb.: Izd-vo Politehn. un-ta, 2007. – 136 s.
2. Husu A. P., Vitenberg Yu. R., Pal'mov V. A. Sherohovatost' poverhnostey (teoretiko-veroyatnostnyy podhod): «Nauka». – Moskva, 1975. – 343 s.
3. Palamar I. N. Probabilistic Graphical Model Based on Growing Neural Gas for Long Time Series Classification / I. N. Palamar, S. S. Yulin // Modern Applied Science. – Sanada (Toronto). – 2015. – V.9. – № 2. – S. 109 – 116.
