Cause and effect prediction in manufacturing process using an improved neural networks
The limitations of the existing Knowledge Hyper-surface method in learning cause and effect relationships in the manufacturing process is explored. A new approach to enhance the performance of the current Knowledge Hyper-surface method has been proposed by constructing midpoints between each primary...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
INSIGHT - Indonesian Society for Knowledge and Human Development
2017
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/3333/ http://eprints.uthm.edu.my/3333/1/AJ%202018%20%28342%29.pdf |
| _version_ | 1848887991883268096 |
|---|---|
| author | Mohd Nawi, Nazri Abdul Hamid, Noorhamreeza Samsudin, Noor Azah Harun, Zawati Ab Aziz, Mohd Firdaus Ramli, Azizul Azhar |
| author_facet | Mohd Nawi, Nazri Abdul Hamid, Noorhamreeza Samsudin, Noor Azah Harun, Zawati Ab Aziz, Mohd Firdaus Ramli, Azizul Azhar |
| author_sort | Mohd Nawi, Nazri |
| building | UTHM Institutional Repository |
| collection | Online Access |
| description | The limitations of the existing Knowledge Hyper-surface method in learning cause and effect relationships in the manufacturing process is explored. A new approach to enhance the performance of the current Knowledge Hyper-surface method has been proposed by constructing midpoints between each primary weight along each dimension by using a quadratic Lagrange interpolation polynomial. The new secondary-weight values, generated due to the addition of midpoints, were also represented as a linear combination of the corresponding primary/axial weight values. An improved neural networks in learning from examples have also been proposed where both of the proposed algorithms able to constrain the shape of the surface in two-dimensional and multidimensional cases and produced more realistic and acceptable results as compared to the previous version. The ability of the proposed approach to models the exponential increase/decrease in the belief values by using high-ordered polynomials without introducing 'over-fitting' effects was investigated. The performance of the proposed method in modelling the exponential increase/decrease in belief values was carried out on real cases taken from real casting data. The computed graphical results of the proposed methods were compared with the current Knowledge Hyper-surface and neural-network methods. As a result, the proposed methods correctly predict the sensitivity of process-parameter variations with the occurrence of a defect and very important area of research in a robust design methodology. |
| first_indexed | 2025-11-15T20:03:11Z |
| format | Article |
| id | uthm-3333 |
| institution | Universiti Tun Hussein Onn Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T20:03:11Z |
| publishDate | 2017 |
| publisher | INSIGHT - Indonesian Society for Knowledge and Human Development |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | uthm-33332021-11-16T07:36:24Z http://eprints.uthm.edu.my/3333/ Cause and effect prediction in manufacturing process using an improved neural networks Mohd Nawi, Nazri Abdul Hamid, Noorhamreeza Samsudin, Noor Azah Harun, Zawati Ab Aziz, Mohd Firdaus Ramli, Azizul Azhar TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television TS155-194 Production management. Operations management The limitations of the existing Knowledge Hyper-surface method in learning cause and effect relationships in the manufacturing process is explored. A new approach to enhance the performance of the current Knowledge Hyper-surface method has been proposed by constructing midpoints between each primary weight along each dimension by using a quadratic Lagrange interpolation polynomial. The new secondary-weight values, generated due to the addition of midpoints, were also represented as a linear combination of the corresponding primary/axial weight values. An improved neural networks in learning from examples have also been proposed where both of the proposed algorithms able to constrain the shape of the surface in two-dimensional and multidimensional cases and produced more realistic and acceptable results as compared to the previous version. The ability of the proposed approach to models the exponential increase/decrease in the belief values by using high-ordered polynomials without introducing 'over-fitting' effects was investigated. The performance of the proposed method in modelling the exponential increase/decrease in belief values was carried out on real cases taken from real casting data. The computed graphical results of the proposed methods were compared with the current Knowledge Hyper-surface and neural-network methods. As a result, the proposed methods correctly predict the sensitivity of process-parameter variations with the occurrence of a defect and very important area of research in a robust design methodology. INSIGHT - Indonesian Society for Knowledge and Human Development 2017 Article PeerReviewed text en http://eprints.uthm.edu.my/3333/1/AJ%202018%20%28342%29.pdf Mohd Nawi, Nazri and Abdul Hamid, Noorhamreeza and Samsudin, Noor Azah and Harun, Zawati and Ab Aziz, Mohd Firdaus and Ramli, Azizul Azhar (2017) Cause and effect prediction in manufacturing process using an improved neural networks. International Journal on Advanced Science Engineering Information Technology, 7 (6). pp. 2027-2034. ISSN 2088-5334 |
| spellingShingle | TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television TS155-194 Production management. Operations management Mohd Nawi, Nazri Abdul Hamid, Noorhamreeza Samsudin, Noor Azah Harun, Zawati Ab Aziz, Mohd Firdaus Ramli, Azizul Azhar Cause and effect prediction in manufacturing process using an improved neural networks |
| title | Cause and effect prediction in manufacturing process using
an improved neural networks |
| title_full | Cause and effect prediction in manufacturing process using
an improved neural networks |
| title_fullStr | Cause and effect prediction in manufacturing process using
an improved neural networks |
| title_full_unstemmed | Cause and effect prediction in manufacturing process using
an improved neural networks |
| title_short | Cause and effect prediction in manufacturing process using
an improved neural networks |
| title_sort | cause and effect prediction in manufacturing process using
an improved neural networks |
| topic | TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television TS155-194 Production management. Operations management |
| url | http://eprints.uthm.edu.my/3333/ http://eprints.uthm.edu.my/3333/1/AJ%202018%20%28342%29.pdf |