@inproceedings{4da8aeb054164c949a08a86124209ab8,
title = "Intelligent Manufacturing Monitoring and Surface Roughness Prediction System-A Case Study of Aluminum Parts Milling",
abstract = "The aim of this study is to create an economical automatic machining system to predict surface roughness during processing, which is an important quality criterion. Complex network accelerators and software acceleration are used to achieve real-time calculations. When the expected results are not obtained, the turning tool is changed or processing is halted. The system can maximize the processing efficiency. In this study, a deep neural network is used to predict the roughness of the plane, and sensors are installed at different positions to study the effects of different positions and numbers on accuracy. The accuracy obtained is 92.3%.",
keywords = "deep learning, intelligent systems, machine learning, neural network",
author = "Chen, {Po Yang} and Hsu, {Ya Wen} and Lee, {Ming Chan} and Perng, {Jau Woei}",
note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 International Automatic Control Conference, CACS 2020 ; Conference date: 04-11-2020 Through 07-11-2020",
year = "2020",
month = nov,
day = "4",
doi = "10.1109/CACS50047.2020.9289771",
language = "English",
series = "2020 International Automatic Control Conference, CACS 2020",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2020 International Automatic Control Conference, CACS 2020",
address = "美國",
}