Uncertainty analysis of two-shaft gas turbine parameter of artificial neural network (ANN) approximated function using sequential perturbation method
This thesis deals with the finding of uncertainty for two-shaft gas turbine involving its parameter where Artificial Neural Network (ANN) approximated function in association with sequential perturbation method will be applied. Previously, in order for operators to increase the efficiency of two-sha...
| id |
ump-872 |
|---|---|
| recordtype |
eprints |
| spelling |
ump-8722017-04-10T01:43:42Z http://umpir.ump.edu.my/id/eprint/872/ Uncertainty analysis of two-shaft gas turbine parameter of artificial neural network (ANN) approximated function using sequential perturbation method Hilmi Asyraf, Razali TJ Mechanical engineering and machinery This thesis deals with the finding of uncertainty for two-shaft gas turbine involving its parameter where Artificial Neural Network (ANN) approximated function in association with sequential perturbation method will be applied. Previously, in order for operators to increase the efficiency of two-shaft gas turbine, experimental method was done where each variable input related with the output which is the thrust produced, Fn need to be change from time to time in order to attain the most possible outcome. Moreover, alot of expensive jigs required to perform this experiment as every parameter involved will be measured with their respective equipments hence as the parameter involved increases, the cost to operate the experiment will also increases. The approach in analysing uncertainty of two-shaft gas turbine parameter is multivariable nonlinear complex function with five inputs and output were randomly generated and their function was approximated via ANN using feed-forward and backpropagation network. Uncertainty outcome through sequential perturbation with ANN will then be compare with the uncertainty outcome using sequential perturbation analytically. Lastly, percentage error between both methods shall be compute so as to prove that uncertainty analysis using sequential perturbation with ANN can also be use rather than by any other method. Average percentage error between Newton approximation (analytical method) and sequential perturbation (numerical method) retrieved is 0.001%. Meanwhile, the average percentage error between actual thrust produced and approximated thrust produced possessed is 0.213%. These values mentioned is not the vital part of this study as their intention was to substantiate whether ANN approximated function can be apply in order to proceed with the crucial part of all which is the average percentage error between uncertainty value via sequential perturbation with ANN and Newton approximation analytically where the value acquired is 0.476%. From these results, it is proven that only a set of data with input and output is necessary for the sake of predicting the output’s uncertainty, UFn hence intensifies the efficiency of two-shaft gas turbine. 2009-11 Undergraduates Project Papers NonPeerReviewed application/pdf en http://umpir.ump.edu.my/id/eprint/872/1/Uncertainty%20analysis%20of%20two-shaft%20gas%20turbine%20parameter%20of%20artificial%20neural%20network%20%28ANN%29%20approximated%20function%20using%20sequential%20perturbation%20method%20%28Table%20of%20content%29.pdf application/pdf en http://umpir.ump.edu.my/id/eprint/872/2/Uncertainty%20analysis%20of%20two-shaft%20gas%20turbine%20parameter%20of%20artificial%20neural%20network%20%28ANN%29%20approximated%20function%20using%20sequential%20perturbation%20method%20%28Abstract%29.pdf application/pdf en http://umpir.ump.edu.my/id/eprint/872/3/Uncertainty%20analysis%20of%20two-shaft%20gas%20turbine%20parameter%20of%20artificial%20neural%20network%20%28ANN%29%20approximated%20function%20using%20sequential%20perturbation%20method%20%28Chapter%201%29.pdf application/pdf en http://umpir.ump.edu.my/id/eprint/872/5/Uncertainty%20analysis%20of%20two-shaft%20gas%20turbine%20parameter%20of%20artificial%20neural%20network%20%28ANN%29%20approximated%20function%20using%20sequential%20perturbation%20method%20%28References%29.pdf Hilmi Asyraf, Razali (2009) Uncertainty analysis of two-shaft gas turbine parameter of artificial neural network (ANN) approximated function using sequential perturbation method. Faculty of Mechanical Engineering, Universiti Malaysia Pahang. http://iportal.ump.edu.my/lib/item?id=chamo:45567&theme=UMP2 |
| repository_type |
Digital Repository |
| institution_category |
Local University |
| institution |
Universiti Malaysia Pahang |
| building |
UMP Institutional Repository |
| collection |
Online Access |
| language |
English English English English |
| topic |
TJ Mechanical engineering and machinery |
| spellingShingle |
TJ Mechanical engineering and machinery Hilmi Asyraf, Razali Uncertainty analysis of two-shaft gas turbine parameter of artificial neural network (ANN) approximated function using sequential perturbation method |
| description |
This thesis deals with the finding of uncertainty for two-shaft gas turbine involving its parameter where Artificial Neural Network (ANN) approximated function in association with sequential perturbation method will be applied. Previously, in order for operators to increase the efficiency of two-shaft gas turbine, experimental method was done where each variable input related with the output which is the thrust produced, Fn need to be change from time to time in order to attain the most possible outcome. Moreover, alot of expensive jigs required to perform this experiment as every parameter involved will be measured with their respective equipments hence as the parameter involved increases, the cost to operate the experiment will also increases. The approach in analysing uncertainty of two-shaft gas turbine parameter is multivariable nonlinear complex function with five inputs and output were randomly generated and their function was approximated via ANN using feed-forward and backpropagation network. Uncertainty outcome through sequential perturbation with ANN will then be compare with the uncertainty outcome using sequential perturbation analytically. Lastly, percentage error between both methods shall be compute so as to prove that uncertainty analysis using sequential perturbation with ANN can also be use rather than by any other method. Average percentage error between Newton approximation (analytical method) and sequential perturbation (numerical method) retrieved is 0.001%. Meanwhile, the average percentage error between actual thrust produced and approximated thrust produced possessed is 0.213%. These values mentioned is not the vital part of this study as their intention was to substantiate whether ANN approximated function can be apply in order to proceed with the crucial part of all which is the average percentage error between uncertainty value via sequential perturbation with ANN and Newton approximation analytically where the value acquired is 0.476%. From these results, it is proven that only a set of data with input and output is necessary for the sake of predicting the output’s uncertainty, UFn hence intensifies the efficiency of two-shaft gas turbine. |
| format |
Undergraduates Project Papers |
| author |
Hilmi Asyraf, Razali |
| author_facet |
Hilmi Asyraf, Razali |
| author_sort |
Hilmi Asyraf, Razali |
| title |
Uncertainty analysis of two-shaft gas turbine parameter of artificial neural network (ANN) approximated function using sequential perturbation method |
| title_short |
Uncertainty analysis of two-shaft gas turbine parameter of artificial neural network (ANN) approximated function using sequential perturbation method |
| title_full |
Uncertainty analysis of two-shaft gas turbine parameter of artificial neural network (ANN) approximated function using sequential perturbation method |
| title_fullStr |
Uncertainty analysis of two-shaft gas turbine parameter of artificial neural network (ANN) approximated function using sequential perturbation method |
| title_full_unstemmed |
Uncertainty analysis of two-shaft gas turbine parameter of artificial neural network (ANN) approximated function using sequential perturbation method |
| title_sort |
uncertainty analysis of two-shaft gas turbine parameter of artificial neural network (ann) approximated function using sequential perturbation method |
| publishDate |
2009 |
| url |
http://umpir.ump.edu.my/id/eprint/872/ http://umpir.ump.edu.my/id/eprint/872/ http://umpir.ump.edu.my/id/eprint/872/1/Uncertainty%20analysis%20of%20two-shaft%20gas%20turbine%20parameter%20of%20artificial%20neural%20network%20%28ANN%29%20approximated%20function%20using%20sequential%20perturbation%20method%20%28Table%20of%20content%29.pdf http://umpir.ump.edu.my/id/eprint/872/2/Uncertainty%20analysis%20of%20two-shaft%20gas%20turbine%20parameter%20of%20artificial%20neural%20network%20%28ANN%29%20approximated%20function%20using%20sequential%20perturbation%20method%20%28Abstract%29.pdf http://umpir.ump.edu.my/id/eprint/872/3/Uncertainty%20analysis%20of%20two-shaft%20gas%20turbine%20parameter%20of%20artificial%20neural%20network%20%28ANN%29%20approximated%20function%20using%20sequential%20perturbation%20method%20%28Chapter%201%29.pdf http://umpir.ump.edu.my/id/eprint/872/5/Uncertainty%20analysis%20of%20two-shaft%20gas%20turbine%20parameter%20of%20artificial%20neural%20network%20%28ANN%29%20approximated%20function%20using%20sequential%20perturbation%20method%20%28References%29.pdf |
| first_indexed |
2023-09-18T21:53:31Z |
| last_indexed |
2023-09-18T21:53:31Z |
| _version_ |
1777413926656409600 |