Effects of Latin hypercube sampling on surrogate modeling and optimization

Afzal, Arshad; Kim, Kwang‐Yong; Seo, Jung Hun

doi:10.5293/ijfms.2017.10.3.240

“…The sampling plan is available in the supplementary material. It is suggested that for up to 10 variables, a sampling size of 10-15 times the number of variables should suffice [17,18]. In the present study, the 10 variables are sampled by 200 unique combinations of the variables.…”

Section: Sampling and Surrogate Modelingmentioning

confidence: 97%

Applied Process Simulation-Driven Oil and Gas Separation Plant Optimization Using Surrogate Modeling and Evolutionary Algorithms

Andreasen¹

2020

View full text Add to dashboard Cite

In this article, the optimization of a realistic oil and gas separation plant has been studied. Using Latin Hypercube Sampling (LHS) and rigorous process simulations, surrogate models using Kriging have been established for selected model responses. The surrogate models are used in combination with an evolutionary algorithm for optimizing the operating profit, mainly by maximizing the recoverable oil production. A total of 10 variables representing pressure and temperature at various key places in the separation plant are optimized to maximize the operational profit. The optimization is bounded in the variables and a constraint function is included to ensure that the optimal solution allows export of oil with a Reid Vapor Pressure (RVP) < 12 psia. The main finding is that, while a high pressure is preferred in the first separation stage, apparently a unique optimal setting for the pressure in downstream separators does not appear to exist. In the second stage separator, apparently different, yet more or less equally optimal, settings are revealed. In the third and final separation stage a correlation between the separator pressure and the applied inlet temperature exists, where different combinations of pressure and temperature yields equally optimal results.

show abstract

“…A Latin-Hypercube sampling plan [14] is generated by the pyKriging package [15] for Python. It is suggested that for up to 10 variables an initial sample size of 15 should suffice [16]. In the present study a sample size of 20 is applied i.e.…”

Section: Design Of Computer Experiments and Surrogate Modelingmentioning

confidence: 99%

Applied Process Simulation-Driven Oil and Gas Separation Plant Optimization using Surrogate Modeling and Evolutionary Algorithms

Andreasen

¹

2019

Preprint

View full text Add to dashboard Cite

In this article the optimization of a realistic oil and gas separation plant has been studied. Two different fluids are investigated and compared in terms of the optimization potential. Using Design of Computer Experiment (DACE) via Latin Hypercube Sampling (LHS) and rigorous process simulations, surrogate models using Kriging have been established for selected model responses. The surrogate models are used in combination with a variety of different evolutionary algorithms for optimizing the operating profit, mainly by maximizing the recoverable oil production. A total of 10 variables representing pressure and temperature various key places in the separation plant are optimized to maximize the operational profit. The optimization is bounded in the variables and a constraint function is included to ensure that the optimal solution allows export of oil with an RVP < 12 psia. The main finding is that, while a high pressure is preferred in the first separation stage, apparently a single optimal setting for the pressure in downstream separators does not appear to exist. In the second stage separator apparently two different, yet equally optimal, settings are revealed. In the third and final separation stage a correlation between the separator pressure and the applied inlet temperature exists, where different combinations of pressure and temperature yields equally optimal results.<br>

show abstract

“…A Latin-Hypercube sampling plan [14] is generated by the pyKriging package [15] for Python. It is suggested that for up to 10 variables an initial sample size of 15 should suffice [16]. In the present study a sample size of 20 is applied i.e.…”

Section: Design Of Computer Experiments and Surrogate Modelingmentioning

confidence: 99%

Applied Process Simulation-Driven Oil and Gas Separation Plant Optimization using Surrogate Modeling and Evolutionary Algorithms

Andreasen

¹

2019

Preprint

0

View full text Add to dashboard Cite

In this article the optimization of a realistic oil and gas separation plant has been studied. Two different fluids are investigated and compared in terms of the optimization potential. Using Design of Computer Experiment (DACE) via Latin Hypercube Sampling (LHS) and rigorous process simulations, surrogate models using Kriging have been established for selected model responses. The surrogate models are used in combination with a variety of different evolutionary algorithms for optimizing the operating profit, mainly by maximizing the recoverable oil production. A total of 10 variables representing pressure and temperature various key places in the separation plant are optimized to maximize the operational profit. The optimization is bounded in the variables and a constraint function is included to ensure that the optimal solution allows export of oil with an RVP < 12 psia. The main finding is that, while a high pressure is preferred in the first separation stage, apparently a single optimal setting for the pressure in downstream separators does not appear to exist. In the second stage separator apparently two different, yet equally optimal, settings are revealed. In the third and final separation stage a correlation between the separator pressure and the applied inlet temperature exists, where different combinations of pressure and temperature yields equally optimal results.

show abstract

Effects of Latin hypercube sampling on surrogate modeling and optimization

Cited by 42 publications

References 29 publications

Applied Process Simulation-Driven Oil and Gas Separation Plant Optimization Using Surrogate Modeling and Evolutionary Algorithms

Applied Process Simulation-Driven Oil and Gas Separation Plant Optimization Using Surrogate Modeling and Evolutionary Algorithms

Applied Process Simulation-Driven Oil and Gas Separation Plant Optimization using Surrogate Modeling and Evolutionary Algorithms

Applied Process Simulation-Driven Oil and Gas Separation Plant Optimization using Surrogate Modeling and Evolutionary Algorithms

Contact Info

Product

Resources

About