An approach to indirect real-time predictions with amazon machine learning
Manufacturing all around the world is going through a phenomenon known as industry 4.0 where digital transformations are taking place across the manufacturing value chain. Concepts such as the industrial internet of things and machine learning have become a norm in the industry. The biggest challeng...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/75522 |
| _version_ | 1826122894080475136 |
|---|---|
| author | Lee, Daryl Wei Qiang |
| author2 | Tegoeh Tjahjowidodo |
| author_facet | Tegoeh Tjahjowidodo Lee, Daryl Wei Qiang |
| author_sort | Lee, Daryl Wei Qiang |
| collection | NTU |
| description | Manufacturing all around the world is going through a phenomenon known as industry 4.0 where digital transformations are taking place across the manufacturing value chain. Concepts such as the industrial internet of things and machine learning have become a norm in the industry. The biggest challenges currently faced by organizations in achieving the goals of industry 4.0 include the issues of interoperability, analytical complications, and cyber-security risks amongst many others. In this project, we will develop an approach to create an indirect real-time prediction system using amazon machine learning. The system will be tested on a deburring (abrasive grinding) process as a case study. The proposed approach will enable users to utilize machine learning techniques provided on the AML platform to create a machine learning model and subsequently generate predictions and display them visually in a dynamic chart. |
| first_indexed | 2024-10-01T05:55:42Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/75522 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:55:42Z |
| publishDate | 2018 |
| record_format | dspace |
| spelling | ntu-10356/755222023-03-04T18:35:51Z An approach to indirect real-time predictions with amazon machine learning Lee, Daryl Wei Qiang Tegoeh Tjahjowidodo School of Mechanical and Aerospace Engineering DRNTU::Engineering::Mechanical engineering Manufacturing all around the world is going through a phenomenon known as industry 4.0 where digital transformations are taking place across the manufacturing value chain. Concepts such as the industrial internet of things and machine learning have become a norm in the industry. The biggest challenges currently faced by organizations in achieving the goals of industry 4.0 include the issues of interoperability, analytical complications, and cyber-security risks amongst many others. In this project, we will develop an approach to create an indirect real-time prediction system using amazon machine learning. The system will be tested on a deburring (abrasive grinding) process as a case study. The proposed approach will enable users to utilize machine learning techniques provided on the AML platform to create a machine learning model and subsequently generate predictions and display them visually in a dynamic chart. Bachelor of Engineering (Mechanical Engineering) 2018-06-01T04:25:28Z 2018-06-01T04:25:28Z 2018 Final Year Project (FYP) http://hdl.handle.net/10356/75522 en Nanyang Technological University 74 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Mechanical engineering Lee, Daryl Wei Qiang An approach to indirect real-time predictions with amazon machine learning |
| title | An approach to indirect real-time predictions with amazon machine learning |
| title_full | An approach to indirect real-time predictions with amazon machine learning |
| title_fullStr | An approach to indirect real-time predictions with amazon machine learning |
| title_full_unstemmed | An approach to indirect real-time predictions with amazon machine learning |
| title_short | An approach to indirect real-time predictions with amazon machine learning |
| title_sort | approach to indirect real time predictions with amazon machine learning |
| topic | DRNTU::Engineering::Mechanical engineering |
| url | http://hdl.handle.net/10356/75522 |
| work_keys_str_mv | AT leedarylweiqiang anapproachtoindirectrealtimepredictionswithamazonmachinelearning AT leedarylweiqiang approachtoindirectrealtimepredictionswithamazonmachinelearning |