Cite Article

Cause and Effect Prediction in Manufacturing Process Using an Improved Neural Networks

Choose citation format

BibTeX

@article{IJASEIT2384,
   author = {Nazri M. Nawi and Noorhamreeza Abdul Hamid and Noor Azah Samsudin and Zawati Harun and Mohd Firdaus Ab Aziz and Azizul Azhar Ramli},
   title = {Cause and Effect Prediction in Manufacturing Process Using an Improved Neural Networks},
   journal = {International Journal on Advanced Science, Engineering and Information Technology},
   volume = {7},
   number = {6},
   year = {2017},
   pages = {2027--2034},
   keywords = {backpropagation algorithm; hypersurface method; activation function; Lagrange interpolation; search direction},
   abstract = {

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 multi-dimensional 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. 

},    issn = {2088-5334},    publisher = {INSIGHT - Indonesian Society for Knowledge and Human Development},    url = {http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=2384},    doi = {10.18517/ijaseit.7.6.2384} }

EndNote

%A Nawi, Nazri M.
%A Abdul Hamid, Noorhamreeza
%A Samsudin, Noor Azah
%A Harun, Zawati
%A Ab Aziz, Mohd Firdaus
%A Ramli, Azizul Azhar
%D 2017
%T Cause and Effect Prediction in Manufacturing Process Using an Improved Neural Networks
%B 2017
%9 backpropagation algorithm; hypersurface method; activation function; Lagrange interpolation; search direction
%! Cause and Effect Prediction in Manufacturing Process Using an Improved Neural Networks
%K backpropagation algorithm; hypersurface method; activation function; Lagrange interpolation; search direction
%X 

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 multi-dimensional 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. 

%U http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=2384 %R doi:10.18517/ijaseit.7.6.2384 %J International Journal on Advanced Science, Engineering and Information Technology %V 7 %N 6 %@ 2088-5334

IEEE

Nazri M. Nawi,Noorhamreeza Abdul Hamid,Noor Azah Samsudin,Zawati Harun,Mohd Firdaus Ab Aziz and Azizul Azhar Ramli,"Cause and Effect Prediction in Manufacturing Process Using an Improved Neural Networks," International Journal on Advanced Science, Engineering and Information Technology, vol. 7, no. 6, pp. 2027-2034, 2017. [Online]. Available: http://dx.doi.org/10.18517/ijaseit.7.6.2384.

RefMan/ProCite (RIS)

TY  - JOUR
AU  - Nawi, Nazri M.
AU  - Abdul Hamid, Noorhamreeza
AU  - Samsudin, Noor Azah
AU  - Harun, Zawati
AU  - Ab Aziz, Mohd Firdaus
AU  - Ramli, Azizul Azhar
PY  - 2017
TI  - Cause and Effect Prediction in Manufacturing Process Using an Improved Neural Networks
JF  - International Journal on Advanced Science, Engineering and Information Technology; Vol. 7 (2017) No. 6
Y2  - 2017
SP  - 2027
EP  - 2034
SN  - 2088-5334
PB  - INSIGHT - Indonesian Society for Knowledge and Human Development
KW  - backpropagation algorithm; hypersurface method; activation function; Lagrange interpolation; search direction
N2  - 

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 multi-dimensional 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. 

UR - http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=2384 DO - 10.18517/ijaseit.7.6.2384

RefWorks

RT Journal Article
ID 2384
A1 Nawi, Nazri M.
A1 Abdul Hamid, Noorhamreeza
A1 Samsudin, Noor Azah
A1 Harun, Zawati
A1 Ab Aziz, Mohd Firdaus
A1 Ramli, Azizul Azhar
T1 Cause and Effect Prediction in Manufacturing Process Using an Improved Neural Networks
JF International Journal on Advanced Science, Engineering and Information Technology
VO 7
IS 6
YR 2017
SP 2027
OP 2034
SN 2088-5334
PB INSIGHT - Indonesian Society for Knowledge and Human Development
K1 backpropagation algorithm; hypersurface method; activation function; Lagrange interpolation; search direction
AB 

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 multi-dimensional 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. 

LK http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=2384 DO - 10.18517/ijaseit.7.6.2384