Development of a graph convolutional network-based surface quality monitoring approach
Many traditional quality monitoring approaches faced issues such as a huge number of uncontrollable parameters which leads to prediction inaccuracy. Other forms of modern monitoring system utilize Deep Learning (DL) models such Artificial Neural Networks (ANNs) and Convolutional Neural Networks (CNN...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/157257 |
| _version_ | 1826128146675531776 |
|---|---|
| author | Peh, Gerald Zong Xian |
| author2 | Chen Chun-Hsien |
| author_facet | Chen Chun-Hsien Peh, Gerald Zong Xian |
| author_sort | Peh, Gerald Zong Xian |
| collection | NTU |
| description | Many traditional quality monitoring approaches faced issues such as a huge number of uncontrollable parameters which leads to prediction inaccuracy. Other forms of modern monitoring system utilize Deep Learning (DL) models such Artificial Neural Networks (ANNs) and Convolutional Neural Networks (CNN). However, such models are unable to mine complex relations between each signal. To counter this issue, this study would introduce Graph Convolutional Networks (GCNs) to prediction of surface quality where it takes graph-structured data as an input instead of the usual Euclidean structured data. Such models can learn complex relationships which allows better feature representation of each sampled data. However, most GCNs have certain limitations such as a fixed kernel size which prevents learning of relationship from multi-hop neighborhood domains.
Therefore, this project would implement a Multi-Hop Graph Convolutional Network (MHGCN) model to observe whether fused features from different receptive fields would provide better prediction results. The data samples are converted into weighted graphs to establish different importance between each sample relations. Also, the proposed model would utilize an attention mechanism to mine relationships among different hop domains and select the important ones. Simple averaging ensemble learning would be implemented to combine multiple learners and improve learning process.
To verify the effectiveness of the proposed MHGCN model, it is compared with other DL and GCN models and the results shows that the MHGCN model with attention mechanism has the best performance. |
| first_indexed | 2024-10-01T07:20:10Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/157257 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:20:10Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1572572022-05-11T13:27:13Z Development of a graph convolutional network-based surface quality monitoring approach Peh, Gerald Zong Xian Chen Chun-Hsien School of Mechanical and Aerospace Engineering MCHchen@ntu.edu.sg Engineering::Mechanical engineering Many traditional quality monitoring approaches faced issues such as a huge number of uncontrollable parameters which leads to prediction inaccuracy. Other forms of modern monitoring system utilize Deep Learning (DL) models such Artificial Neural Networks (ANNs) and Convolutional Neural Networks (CNN). However, such models are unable to mine complex relations between each signal. To counter this issue, this study would introduce Graph Convolutional Networks (GCNs) to prediction of surface quality where it takes graph-structured data as an input instead of the usual Euclidean structured data. Such models can learn complex relationships which allows better feature representation of each sampled data. However, most GCNs have certain limitations such as a fixed kernel size which prevents learning of relationship from multi-hop neighborhood domains. Therefore, this project would implement a Multi-Hop Graph Convolutional Network (MHGCN) model to observe whether fused features from different receptive fields would provide better prediction results. The data samples are converted into weighted graphs to establish different importance between each sample relations. Also, the proposed model would utilize an attention mechanism to mine relationships among different hop domains and select the important ones. Simple averaging ensemble learning would be implemented to combine multiple learners and improve learning process. To verify the effectiveness of the proposed MHGCN model, it is compared with other DL and GCN models and the results shows that the MHGCN model with attention mechanism has the best performance. Bachelor of Engineering (Mechanical Engineering) 2022-05-11T13:27:13Z 2022-05-11T13:27:13Z 2022 Final Year Project (FYP) Peh, G. Z. X. (2022). Development of a graph convolutional network-based surface quality monitoring approach. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/157257 https://hdl.handle.net/10356/157257 en B049 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Mechanical engineering Peh, Gerald Zong Xian Development of a graph convolutional network-based surface quality monitoring approach |
| title | Development of a graph convolutional network-based surface quality monitoring approach |
| title_full | Development of a graph convolutional network-based surface quality monitoring approach |
| title_fullStr | Development of a graph convolutional network-based surface quality monitoring approach |
| title_full_unstemmed | Development of a graph convolutional network-based surface quality monitoring approach |
| title_short | Development of a graph convolutional network-based surface quality monitoring approach |
| title_sort | development of a graph convolutional network based surface quality monitoring approach |
| topic | Engineering::Mechanical engineering |
| url | https://hdl.handle.net/10356/157257 |
| work_keys_str_mv | AT pehgeraldzongxian developmentofagraphconvolutionalnetworkbasedsurfacequalitymonitoringapproach |