Malaysian Government Officials Induced in Public Procurement Fraud through the Lens of Fraud Diamond Analysis
At a Glance
Section titled āAt a Glanceā| Metadata | Details |
|---|---|
| Publication Date | 2022-10-01 |
| Journal | Asian Journal of Accounting and Governance |
| Authors | Norziaton Ismail Khan, Hamzah Bakar |
| Citations | 5 |
Abstract
Section titled āAbstractāReservoir simulation softwares are used as an important tool in oil and gas industries to \npredict the responses of the reservoir. Due the large number of grid blocks and hetero \ngeneity in the reservoir model, large number of simulations are required to narrow down \nthe risk in reservoir productivity. To mitigate this problem, Surrogate Reservoir Model \n(SRM) is considered as a potential solution to reduce simulation time. The SRM is \nused to predict the average reservoir pressure, production rate and bottom-hole flowing \npressure (BHFP) based on the time complexity. The main objective of this research is \nto develop dynamic well Surrogate Reservoir Model (SRM), that mines the output data \nfrom a conventional reservoir simulator. Key input parameters e,g. porosity, perme \nability are identified from reservoir model using principal component analysis (PCA) \ntechnique. Two supervised Artificial Neural Network (ANN), i.e. backpropagation neu \nral network (BPNN) and radial basis neural network (RBNN) is used to build SRM for \nsystem prediction. Mean Square Error (MSE) is used to calculate the error between the \ntarget and predicted output in order to select the SRM with minimum error value. The \nRBNN is shown to be the more effective in the development of SRM.