APPLICATION OF ARTIFICIAL NEURAL NETWORKS FOR PREDICTING ROUGHNESS AT CLEANING AND GETTING POINT-Reference-Cited by-同舟云学术

APPLICATION OF ARTIFICIAL NEURAL NETWORKS FOR PREDICTING ROUGHNESS AT CLEANING AND GETTING POINT

Published:2019-07-21 Issue:7 Volume:4 Page:128-134
ISSN:2071-7318
Container-title:Bulletin of Belgorod State Technological University named after. V. G. Shukhov
language:en
Short-container-title:

Author:

Баранов Д.¹,Baranov Denis²,Дуюн Т.А.¹,Duyun T.A.²

Affiliation:

1. Белгородский государственный технологический университет им В.Г. Шухова

2. Belgorod State Technological University named after V.G. Shukhov

Abstract

A technique for the development of artificial neural networks to predict the roughness of the treated surface during finishing and semi-finishing turning is presented. The back-propagation network architecture was adopted, having an input, hidden and output layers, a sigmoidal activation function for the hidden layer and a linear one for the output layer. To form a training sample, empirical expressions in the form of power functions were used, training of networks was carried out according to the Levenberg-Marquardt algorithm, which has fast convergence. Technological modes (cutting speed and depth of cut, tool feed), cutting tool geometrical parameters (main and auxiliary angles in terms of the tool, radius at the tip of the tool, rake angle), physicomechanical properties of the material being processed, each the training sample is formed from thousands of source data combinations. Separate networks have been developed that predict roughness during finishing and semi-turning turning, as well as a combined network that takes into account both types of processing. Analysis of the accuracy of the networks showed good results, the relative error of calculations does not exceed 1%. The proposed neural network models can be used in technological preparation of production, as well as in systems of adaptive control of the cutting process.

Publisher

BSTU named after V.G. Shukhov

Subject

Psychiatry and Mental health,Neuropsychology and Physiological Psychology

Reference11 articles.

1. Дуюн Т.А., Гринек А.В. Математическое моделирование процессов механической обработки как средство управления технологическими параметрами на основе нейросетевых и нечетких моделей // Труды международной конференции «Современные направления и перспективы развития технологий обработки и обо-рудования в машиностроении», Севастополь – 2016, №3 (3). С. 28–33., Dujun T.A., Grinek A.V. Mathematical modeling of machining as control system instrument of technological parameters based on the fuzzy logic and neural networks [Matematicheskoe modelirovanie processov mekhanicheskoj obrabotki kak sredstvo upravleniya tekhnologicheskimi parametrami na osnove nejrosetevyh i nechetkih modelej]. Trudi mezhdunarodnoy konferencii «Sovremennie napravlenia i perspectivi razvitia tekhnologiy obrabotki i oborudovania v mashinostroenii», Sevastopol. 2016. No. 3. Pp. 28–33. (rus)

2. Кабалдин Ю.Г., Лаптев И.Л., Шатагин С.В., Серый С.В. Диагностика выходных пара-метров процесса резания в режиме реального времени на основе фрактального и вейвлетанализаов с использованием программно-аппаратных средств NationalInstruments и Nvidia CUDA // Вестник машиностроения. 2014. № 8. С. 80–82., Kabaldin U.G., Laptev I.L., Shatahin S.V., Seriy S.V. Diagnostics of the output parameters of the cutting process in real time based on fractal and wavelet analyzes using software and hardware NationalInstruments and Nvidia CUDA [Diagnostika vyhodnyh parametrov processa rezaniya v rezhime real'nogo vremeni na osnove fraktal'nogo i vejvletanalizaov s ispol'zovaniem programmno-apparatnyh sredstv NationalInstruments i Nvidia CUDA]. Bulletin of engineering. 2014. No. 8. Pp. 80–82. (rus)

3. Алтунин К.А., Соколов М.В. Применение нейронных сетей для моделирования процесса токарной обработки // Вестник ТГТУ. 2016. Том 22. №1. С. 122–133, Altunin K.A., Sokolov M.V. Application of Neural Networks to Modeling of the Turning Process [Primenenie nejronnyh setej dlya modelirovaniya processa tokarnoj obrabotki]. Transactions of the TSTU. 2016. No. 1. Pp.122–133. (rus)

4. Хоанг В.Ч., Сальников В.С. Моделирование температуры резания в условиях неопределенности с применением искусственной нейронной сети // В сб. Известия ТулГУ. Технические науки. 2014. Вып. 11. Ч. 2.С. 386–395., Hoang V.C., Salnikov V.S. Modelling of temperature of cutting in the conditions of uncertainty with application of the artificial neural network [Modelirovanie temperatury rezaniya v usloviyah neopredelennosti s primeneniem iskusstvennoj nejronnoj seti]. V sb. Izvestia TulGU. Tekhnicheskie nauki. 2014. No. 11. P. 2. Pp. 386-395. (rus)

5. Briceno J.F., El-Mounayri H., Mukhopadhyay S. Selecting an artificial neural network for efficient modeling and accurate simulation of the milling process // International Journal of Machine Tools and Manufacture. 2002. Vol. 42. №6. P. 663–674., Briceno J.F., El-Mounayri H., Mukhopadhyay S. Selecting an artificial neural network for efficient modeling and accurate simulation of the milling process. International Journal of Machine Tools and Manufacture. 2002. Vol. 42. No. 6. Pp. 663–674.

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Neural-Network Prediction of the Surface Roughness in Milling;Russian Engineering Research;2023-01