Smart Manufacturing: Engineering Simulations in the Cloud

Industry 4.0 (I4.0) is built upon the capabilities of Internet of Things technologies that facilitate the recollection and processing of data. Originally conceived to improve the performance of manufacturing facilities, the field of application for I4.0 has expanded to reach most industrial sectors. To make the best use of the capabilities of I4.0, machine architectures and design paradigms have had to evolve. This is particularly important as the development of certain advanced manufacturing technologies has been passed from large companies to their subsidiaries and suppliers from around the world. This work discusses how design methodologies, such as those based on functional analysis, can incorporate new functions to enhance the architecture of machines. In particular, the article discusses how connectivity facilitates the development of smart manufacturing capabilities through the incorporation of I4.0 principles and resources that in turn improve the computing capacity available to machine controls and edge devices. These concepts are applied to the development of an in-line metrology station for automotive components. The impact on the design of the machine, particularly on the conception of the control, is analyzed. The resulting machine architecture allows for measurement of critical features of all parts as they are processed at the manufacturing floor, a critical operation in smart factories. Finally, this article discusses how the I4.0 infrastructure can be used to collect and process data to obtain useful information about the process.

Download Full-text

Demystifying data and AI for manufacturing: case studies from a major computer maker

APSIPA Transactions on Signal and Information Processing ◽

10.1017/atsip.2021.3 ◽

2021 ◽

Vol 10 ◽

Author(s):

Yi-Chun Chen ◽

Bo-Huei He ◽

Shih-Sung Lin ◽

Jonathan Hans Soeseno ◽

Daniel Stanley Tan ◽

...

Keyword(s):

Training Data ◽

Smart Manufacturing ◽

Reliable System ◽

Process Innovations ◽

Optical Inspection ◽

Technical Details ◽

Automation Technology ◽

Electronic Parts ◽

Traditional Approaches ◽

Inspection Machine

In this article, we discuss the backgrounds and technical details about several smart manufacturing projects in a tier-one electronics manufacturing facility. We devise a process to manage logistic forecast and inventory preparation for electronic parts using historical data and a recurrent neural network to achieve significant improvement over current methods. We present a system for automatically qualifying laptop software for mass production through computer vision and automation technology. The result is a reliable system that can save hundreds of man-years in the qualification process. Finally, we create a deep learning-based algorithm for visual inspection of product appearances, which requires significantly less defect training data compared to traditional approaches. For production needs, we design an automatic optical inspection machine suitable for our algorithm and process. We also discuss the issues for data collection and enabling smart manufacturing projects in a factory setting, where the projects operate on a delicate balance between process innovations and cost-saving measures.

Download Full-text