Adaptive Kriging surrogate model for the optimization design of a dense non-aqueous phase liquid-contaminated groundwater remediation process

2014 ◽  
Vol 15 (2) ◽  
pp. 263-270 ◽  
Author(s):  
Haibo Chu ◽  
Wenxi Lu
Keyword(s):  
Simulation Model ◽  
Aqueous Phase ◽  
Surrogate Model ◽  
Optimization Design ◽  
Integrated Approach ◽  
Surrogate Models ◽  
Kriging Surrogate Model ◽  
The Common ◽  
Adaptive Kriging ◽  
Remediation Process

The optimization model needs to call the simulation model to calculate the response under different conditions for many times, and this is computationally expensive and time-consuming. To solve this problem, surrogate models can be used to yield insight into the functional relationship between the design variables and the responses, instead of simulation models in the optimization. In this paper, an integrated optimization method based on adaptive Kriging surrogate models was proposed and applied to the cost optimization of a surfactant enhanced aquifer remediation process for dense non-aqueous phase liquids (DNAPLs). First, the initial samples were created by Latin hypercube sampling, and then the responses corresponding to the initial samples were computed by a simulation model. The initial Kriging model was derived through these samples. Secondly, the adaptive Kriging surrogate model was proposed based on updating initial Kriging with new samples via infill sampling criteria. The results showed that it had improved the accuracy of the surrogate model, and the added samples had provided more information about the simulation model than the common samples. Even with the same number of samples, the adaptive Kriging surrogate model performed better than the common Kriging surrogate model, which was built only once. What's more, the integrated approach not only greatly reduced the computational burden, but also determined the actual optimal DNAPLs remediation strategy.

Optimization of Denser Nonaqueous Phase Liquids-contaminated groundwater remediation based on Kriging surrogate model

2013 ◽  
Vol 8 (2) ◽  
pp. 304-314 ◽  
Author(s):  
Wenxi Lu ◽  
Haibo Chu ◽  
Ying Zhao ◽  
Jiannan Luo
Keyword(s):  
Simulation Model ◽  
Optimization Model ◽  
Surrogate Model ◽  
Groundwater Remediation ◽  
Groundwater Resources ◽  
Optimal Strategies ◽  
Nonaqueous Phase Liquids ◽  
Kriging Surrogate Model ◽  
Aquifer Remediation ◽  
Remediation Process

Spillage of large amounts of Denser Nonaqueous Phase Liquids (DNAPLs) had resulted in serious pollution of groundwater resources throughout the world; a large number of studies had demonstrated surfactant-enhanced remediation is a more effective approach to remediate DNAPLs contaminations. In this paper, the remediation optimization process was carried out in three steps. Firstly, a water-oil-surfactant simulation model had been firstly established to simulate a surfactant enhanced aquifer remediation process. The Kriging surrogate model had been developed to get a similar input–output relationship with simulation model. In the final, a nonlinear optimization model was formulated for the minimum cost, and Kriging surrogate model had been embedded into the optimization model as a constrained condition. What is more, simulated annealing method was used to solve the optimization model and give the optimal Surfactant-Enhanced Aquifer Remediation strategy. The results showed Kriging surrogate model had reduced computational burden and make the optimization model easy to solve, and the optimal strategies gave an effective guide to contaminants remediation process.

scholarly journals Rapidly Tuning the PID Controller Based on the Regional Surrogate Model Technique in the UAV Formation

Entropy ◽  
2020 ◽  
Vol 22 (5) ◽  
pp. 527
Author(s):  
Binglin Wang ◽  
Xiaojun Duan ◽  
Liang Yan ◽  
Juan Deng ◽  
Jiangtao Chen
Keyword(s):  
Simulation Model ◽  
Surrogate Model ◽  
Linear Quadratic Regulator ◽  
Surrogate Models ◽  
Singular Points ◽  
Pid Controllers ◽  
Linear Quadratic ◽  
Order Of Magnitude ◽  
Pareto Fronts ◽  
Model Technique

The leader–follower structure is widely used in unmanned aerial vehicle formation. This paper adopts the proportional-integral-derivative (PID) and the linear quadratic regulator controllers to construct the leader–follower formation. Tuning the PID controllers is generally empirical; hence, various surrogate models have been introduced to identify more refined parameters with relatively lower cost. However, the construction of surrogate models faces the problem that the singular points may affect the accuracy, such that the global surrogate models may be invalid. Thus, to tune controllers quickly and accurately, the regional surrogate model technique (RSMT), based on analyzing the regional information entropy, is proposed. The proposed RSMT cooperates only with the successful samples to mitigate the effect of singular points along with a classifier screening failed samples. Implementing the RSMT with various kinds of surrogate models, this study evaluates the Pareto fronts of the original simulation model and the RSMT to compare their effectiveness. The results show that the RSMT can accurately reconstruct the simulation model. Compared with the global surrogate models, the RSMT reduces the run time of tuning PID controllers by one order of magnitude, and it improves the accuracy of surrogate models by dozens of orders of magnitude.

Application of Kriging Surrogate Model in Performance Parameters Optimization of Excavator Cab Shock Absorbers

2015 ◽  
Vol 741 ◽  
pp. 393-396 ◽  
Author(s):  
Lei Liu ◽  
Yi Qi Zhou ◽  
Yong Zhen Mi ◽  
Dan Lu
Keyword(s):  
Surrogate Model ◽  
Optimization Design ◽  
Parameters Optimization ◽  
Engineering Optimization ◽  
Performance Parameters ◽  
Kriging Surrogate Model ◽  
Nsga Ii ◽  
Fem Model ◽  
Functional Relationships ◽  
Shock Absorbers

The surrogate model has been extensively applied in engineering optimization design recently. Based on surrogate model, the complicated functional relationships between variables and responses can be precisely described. In this paper, the Kriging surrogate model are adopted to simulate the relationships between the sound pressure level (SPL) peaks at the drivers right ear (DRE) and the performance parameters of excavator cab shock absorbers with the FEM model, followed by the optimization design been accomplished with algorithm NSGA-II. The results indicate that the SPL peaks and the overall SPL can both be decreased through optimizing the performance parameters with Kriging surrogate model.

Using Kriging Surrogate Models to Predict the Vibration Responses of a Submerged Riser

2020 ◽  
Author(s):  
Marcelo Damasceno ◽  
Hélio Ribeiro Neto ◽  
Tatiane Costa ◽  
Aldemir Cavalini Júnior ◽  
Ludimar Aguiar ◽  
...  
Keyword(s):  
Surrogate Model ◽  
High Performance ◽  
Computational Cost ◽  
Offshore Structures ◽  
Surrogate Models ◽  
Computational Time ◽  
Kriging Surrogate Model ◽  
Efficient Manner ◽  
Modeling Tools ◽  
Fluid Structure

Abstract Fluid-structure interaction modeling tools based on computational fluid dynamics (CFD) produce interesting results that can be used in the design of submerged structures. However, the computational cost of simulations associated with the design of submerged offshore structures is high. There are no high-performance platforms devoted to the analysis and optimization of these structures using CFD techniques. In this context, this work aims to present a computational tool dedicated to the construction of Kriging surrogate models in order to represent the time domain force responses of submerged risers. The force responses obtained from high-cost computational simulations are used as outputs for training and validated the surrogate models. In this case, different excitations are applied in the riser aiming at evaluating the representativeness of the obtained Kriging surrogate model. A similar investigation is performed by changing the number of samples and the total time used for training purposes. The present methodology can be used to perform the dynamic analysis in different submerged structures with a low computational cost. Instead of solving the motion equation associated with the fluid-structure system, a Kriging surrogate model is used. A significant reduction in computational time is expected, which allows the realization of different analyses and optimization procedures in a fast and efficient manner for the design of this type of structure.

A Computational Efficient Method to Assess the Sensitivity of Finite-Element Models: An Illustration With the Hemipelvis

2016 ◽  
Vol 138 (12) ◽  
Author(s):  
Dermot O'Rourke ◽  
Saulo Martelli ◽  
Murk Bottema ◽  
Mark Taylor
Keyword(s):  
Finite Element ◽  
Factorial Design ◽  
Surrogate Model ◽  
Computational Cost ◽  
Bone Geometry ◽  
Surrogate Models ◽  
Full Factorial Design ◽  
Fe Model ◽  
Kriging Surrogate Model ◽  
Full Factorial

Assessing the sensitivity of a finite-element (FE) model to uncertainties in geometric parameters and material properties is a fundamental step in understanding the reliability of model predictions. However, the computational cost of individual simulations and the large number of required models limits comprehensive quantification of model sensitivity. To quickly assess the sensitivity of an FE model, we built linear and Kriging surrogate models of an FE model of the intact hemipelvis. The percentage of the total sum of squares (%TSS) was used to determine the most influential input parameters and their possible interactions on the median, 95th percentile and maximum equivalent strains. We assessed the surrogate models by comparing their predictions to those of a full factorial design of FE simulations. The Kriging surrogate model accurately predicted all output metrics based on a training set of 30 analyses (R2 = 0.99). There was good agreement between the Kriging surrogate model and the full factorial design in determining the most influential input parameters and interactions. For the median, 95th percentile and maximum equivalent strain, the bone geometry (60%, 52%, and 76%, respectively) was the most influential input parameter. The interactions between bone geometry and cancellous bone modulus (13%) and bone geometry and cortical bone thickness (7%) were also influential terms on the output metrics. This study demonstrates a method with a low time and computational cost to quantify the sensitivity of an FE model. It can be applied to FE models in computational orthopaedic biomechanics in order to understand the reliability of predictions.

scholarly journals Uncertainty Analysis in the Optimization Process of Groundwater Exploitation Scheme Based on SVR Method—A Case Study of Hetao Plain

2018 ◽  
Author(s):  
Yongkai An ◽  
Wenxi Lu ◽  
Xueman Yan
Keyword(s):  
Uncertainty Analysis ◽  
Simulation Model ◽  
Optimization Model ◽  
Surrogate Model ◽  
Surrogate Models ◽  
Groundwater Table ◽  
Pumping Rate ◽  
Groundwater Exploitation ◽  
Computational Load ◽  
Hetao Plain

This paper introduces a surrogate model to reduce the huge computational load in the process of simulation-optimization and uncertainty analysis. First, the groundwater numerical simulation model was established, calibrated and verified in the northeast of Hetao Plain. Second, two surrogate models of simulation model were established using support vector regression (SVR) method, one (surrogate model A, SMA) was used to describe the corresponding relationship between the pumping rate and average groundwater table drawdown, and another (surrogate model B, SMB) was used to express the corresponding relationship between the hydrogeological parameter values and average groundwater table drawdown. Third, an optimization model was established to search an optimal groundwater exploitation scheme using the maximum total pumping rate as objective function and the limitative average groundwater table drawdown as constraint condition, the SMA was invoked by the optimization model for obtaining the optimal groundwater exploitation scheme. Finally, the SMB was invoked in the process of uncertainty analysis for assessing the reliability of optimal groundwater exploitation scheme. Results show that the relative error and root mean square error between simulation model and the two surrogate models are both less than 5%, which is a high approximation accuracy. The SVR surrogate model developed in this study could not only considerably reduce the computational load, but also maintain high computational accuracy. The optimal total pumping rate is 7947 m3/d and the reliability of optimal scheme is 40.21%. This can thus provide an effective method for identifying an optimal groundwater exploitation scheme and assessing the reliability of scheme quickly and accurately.

Aerodynamic optimization design of single-layer spherical domes using kriging surrogate model

2021 ◽  
pp. 136943322199248
Author(s):  
Ye Qiu ◽  
Haiyun He ◽  
Chen Xu ◽  
Bingbing San
Keyword(s):  
Surrogate Model ◽  
Optimization Design ◽  
Stokes Equations ◽  
Single Layer ◽  
Vertical Displacement ◽  
Aerodynamic Performance ◽  
Geometric Parameters ◽  
Kriging Surrogate Model ◽  
Aerodynamic Optimization ◽  
Element Analysis

This paper aims to provide an aerodynamic optimization procedure to improve the aerodynamic performance of single-layer spherical domes, by coupling the kriging surrogate model with computational fluid dynamics (CFD) and finite element analysis (FEA). Firstly, a series of wind tunnel tests on the mean pressures and wind-induced behavior of a single-layer spherical latticed shell, were carried out to investigate the effect of dome geometric parameters. Then, the Reynolds-averaged Navier-Stokes equations and RSM turbulence model were utilized for simulating the wind loads on spherical domes, and the numerical results are validated with experimental data. On this basis, the single-objective aerodynamic optimization of spherical domes based on ordinary kriging surrogates has been carried out to find out the optimal geometric parameters (rise/span and wall-height/span ratios). The objectives were minimizing the highest mean suction and the maximum vertical displacement, respectively. The optimization results showed that the optimal design of spherical domes exhibits a reasonable aerodynamic performance improvement compared with the near optimal solutions. In addition, the highest mean suction and the maximum vertical displacement can be reduced by decreasing the wall-height of the dome, and a good trade-off between the two objectives can be achieved by selecting suitable dome geometric parameters.

Sign in / Sign up

Export Citation Format

Share Document