Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization Unit
Data-driven models are essential tools for the development of surrogate models that can be used for the design, operation, and optimization of industrial processes. One approach of developing surrogate models is through the use of input−output data obtained from a process simulator. To enh...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-05-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/12/10/1906 |
| _version_ | 1798043495901954048 |
|---|---|
| author | Mohamed Ibrahim Saad Al-Sobhi Rajib Mukherjee Ahmed AlNouss |
| author_facet | Mohamed Ibrahim Saad Al-Sobhi Rajib Mukherjee Ahmed AlNouss |
| author_sort | Mohamed Ibrahim |
| collection | DOAJ |
| description | Data-driven models are essential tools for the development of surrogate models that can be used for the design, operation, and optimization of industrial processes. One approach of developing surrogate models is through the use of input−output data obtained from a process simulator. To enhance the model robustness, proper sampling techniques are required to cover the entire domain of the process variables uniformly. In the present work, Monte Carlo with pseudo-random samples as well as Latin hypercube samples and quasi-Monte Carlo samples with Hammersley Sequence Sampling (HSS) are generated. The sampled data obtained from the process simulator are fitted to neural networks for generating a surrogate model. An illustrative case study is solved to predict the gas stabilization unit performance. From the developed surrogate models to predict process data, it can be concluded that of the different sampling methods, Latin hypercube sampling and HSS have better performance than the pseudo-random sampling method for designing the surrogate model. This argument is based on the maximum absolute value, standard deviation, and the confidence interval for the relative average error as obtained from different sampling techniques. |
| first_indexed | 2024-04-11T22:49:44Z |
| format | Article |
| id | doaj.art-6bcd30d95eed478086900da4e5556049 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-11T22:49:44Z |
| publishDate | 2019-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-6bcd30d95eed478086900da4e55560492022-12-22T03:58:37ZengMDPI AGEnergies1996-10732019-05-011210190610.3390/en12101906en12101906Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization UnitMohamed Ibrahim0Saad Al-Sobhi1Rajib Mukherjee2Ahmed AlNouss3Chemical Engineering Department, College of Engineering, Qatar University, Doha 2713, QatarChemical Engineering Department, College of Engineering, Qatar University, Doha 2713, QatarGas and Fuels Research Center, Texas A&M Engineering Experiment Station, College Station, TX 77843, USAChemical Engineering Department, College of Engineering, Qatar University, Doha 2713, QatarData-driven models are essential tools for the development of surrogate models that can be used for the design, operation, and optimization of industrial processes. One approach of developing surrogate models is through the use of input−output data obtained from a process simulator. To enhance the model robustness, proper sampling techniques are required to cover the entire domain of the process variables uniformly. In the present work, Monte Carlo with pseudo-random samples as well as Latin hypercube samples and quasi-Monte Carlo samples with Hammersley Sequence Sampling (HSS) are generated. The sampled data obtained from the process simulator are fitted to neural networks for generating a surrogate model. An illustrative case study is solved to predict the gas stabilization unit performance. From the developed surrogate models to predict process data, it can be concluded that of the different sampling methods, Latin hypercube sampling and HSS have better performance than the pseudo-random sampling method for designing the surrogate model. This argument is based on the maximum absolute value, standard deviation, and the confidence interval for the relative average error as obtained from different sampling techniques.https://www.mdpi.com/1996-1073/12/10/1906surrogate modelsampling techniquestabilization unitprocess simulationprocess systems engineering (PSE) |
| spellingShingle | Mohamed Ibrahim Saad Al-Sobhi Rajib Mukherjee Ahmed AlNouss Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization Unit Energies surrogate model sampling technique stabilization unit process simulation process systems engineering (PSE) |
| title | Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization Unit |
| title_full | Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization Unit |
| title_fullStr | Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization Unit |
| title_full_unstemmed | Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization Unit |
| title_short | Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization Unit |
| title_sort | impact of sampling technique on the performance of surrogate models generated with artificial neural network ann a case study for a natural gas stabilization unit |
| topic | surrogate model sampling technique stabilization unit process simulation process systems engineering (PSE) |
| url | https://www.mdpi.com/1996-1073/12/10/1906 |
| work_keys_str_mv | AT mohamedibrahim impactofsamplingtechniqueontheperformanceofsurrogatemodelsgeneratedwithartificialneuralnetworkannacasestudyforanaturalgasstabilizationunit AT saadalsobhi impactofsamplingtechniqueontheperformanceofsurrogatemodelsgeneratedwithartificialneuralnetworkannacasestudyforanaturalgasstabilizationunit AT rajibmukherjee impactofsamplingtechniqueontheperformanceofsurrogatemodelsgeneratedwithartificialneuralnetworkannacasestudyforanaturalgasstabilizationunit AT ahmedalnouss impactofsamplingtechniqueontheperformanceofsurrogatemodelsgeneratedwithartificialneuralnetworkannacasestudyforanaturalgasstabilizationunit |