Conditional Monitoring of Industrial Processes With Deep Neural Networks

Glen, Chosua and Schwung, Andreas and Rusyadi, Rusman (2019) Conditional Monitoring of Industrial Processes With Deep Neural Networks. Bachelor thesis, Swiss German University.

[img]
Preview
Text
Chosua Glen 11501047 TOC.pdf

Download (619kB) | Preview
[img] Text
Chosua Glen 11501047 1.pdf
Restricted to Registered users only

Download (44kB)
[img] Text
Chosua Glen 11501047 2.pdf
Restricted to Registered users only

Download (695kB)
[img] Text
Chosua Glen 11501047 3.pdf
Restricted to Registered users only

Download (1MB)
[img] Text
Chosua Glen 11501047 4.pdf
Restricted to Registered users only

Download (1MB)
[img] Text
Chosua Glen 11501047 5.pdf
Restricted to Registered users only

Download (237kB)
[img]
Preview
Text
Chosua Glen 11501047 Ref.pdf

Download (129kB) | Preview

Abstract

In this paper a condition monitoring an in industrial processes is made with deep learning algorithm, with data served from IEEE PHM Challenge of the bearings‟ degrading life. To provide the best many-to-many type of learning process, sequential type of deep learning is chosen such as Long-Short Term Memory (LSTM), Gated Recurrent Unit (GRU), Encoder-Decoder Model, and Sequence to Sequence Attention Model will be used to make Remaining Useful Life (RUL) prediction based on the actual RUL of the tested bearings with end-to-end approach. Comparison and discussion will be written in detail.

Item Type: Thesis (Bachelor)
Uncontrolled Keywords: Deep Learning ; Process Monitoring ; Sequential ; Regression ; Many to Many
Subjects: T Technology > TJ Mechanical engineering and machinery
Divisions: Faculty of Engineering and Information Technology > Department of Mechatronics Engineering
Depositing User: Adityatama Ratangga
Date Deposited: 19 May 2020 14:01
Last Modified: 19 May 2020 14:01
URI: http://repository.sgu.ac.id/id/eprint/642

Actions (login required)

View Item View Item