Development of an adaptive surrogate model for production optimization

Golzari, Aliakbar; Sefat, Morteza Haghighat; Jamshidi, Saeid

doi:10.1016/j.petrol.2015.07.012

Cited by 93 publications

(34 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…60 The radial basis function (RBF) surrogate model was used instead of the simulation model to express the relationship between the design variables and the responses. 61,62 Uniformly, random sampling was carried out within the range of each design variable according to Hammersley Design. A total of 100 sample points were selected to fit the RBF surrogate model of each response.…”

Section: Surrogate Modelmentioning

confidence: 99%

Analysis and multi-objective optimization design of wheel based on aerodynamic performance

Wang

Zhang

et al. 2019

Advances in Mechanical Engineering

View full text Add to dashboard Cite

In the past studies, the influence of wheel structure design and optimization on the aerodynamic drag of car and heat transfer performance of brake disc was less studied. To study the influence mechanism, the finite element model for wheel aerodynamic analysis was established using computational fluid dynamic method and the correctness of the model was verified by the wind tunnel test data. The influence mechanism of the flow field on aerodynamic drag of car and wheel and heat transfer performance of brake disc was studied. The influence of wheel disc structure on aerodynamic drag coefficient of the car and average convective heat transfer coefficient of the brake discs was studied. The parametric model of the wheel under the computational fluid dynamic analysis was established using mesh morphing technology. A total of 100 and 10 sample points were extracted using the Hammersley Design and Optimal Latin Hypercube Design, respectively, to fit the radial basis function surrogate model and test the accuracy of the surrogate model. Based on the established surrogate model, taking the minimum of the wheel mass, the minimum of the aerodynamic drag coefficient of the car and the maximum of the average surface convective heat transfer coefficient of brake discs as objectives and design variables of wheel as constraints to ensure the wheel structural strength, the non-dominated sorting genetic algorithm was adopted to carry out multi-objective optimization design for the wheel. Pareto frontier was obtained and a compromise solution was selected as the optimization design result. After the optimization design, the wheel mass is reduced by 8.28%, the aerodynamic drag coefficient of the car is reduced by 3.17% and the average surface convective heat transfer coefficient of brake discs is increased by 9.31%.

show abstract

Section: Surrogate Modelmentioning

confidence: 99%

Analysis and multi-objective optimization design of wheel based on aerodynamic performance

Wang

Zhang

et al. 2019

Advances in Mechanical Engineering

View full text Add to dashboard Cite

show abstract

“…The simulators are not necessarily optimized for fast iterative computations. Lighter modeling approaches such as surrogate models [17][18][19] are therefore needed in practical online applications.…”

Section: Introductionmentioning

confidence: 99%

Towards online adaptation of digital twins

et al. 2020

View full text Add to dashboard Cite

Digital twins have gained a lot of attention in modern day industry, but practical challenges arise from the requirement of continuous and real-time data integration. The actual physical systems are also exposed to disturbances unknown to the real-time simulation. Therefore, adaptation is required to ensure reliable performance and to improve the usability of digital twins in monitoring and diagnostics. This study proposes a general approach to the real-time adaptation of digital twins based on a mechanism guided by evolutionary optimization. The mechanism evaluates the deviation between the measured state of the real system and the estimated state provided by the model under adaptation. The deviation is minimized by adapting the model input based on the differential evolution algorithm. To test the mechanism, the measured data were generated via simulations based on a physical model of the real system. The estimated data were generated by a surrogate model, namely a simplified version of the physical model. A case study is presented where the adaptation mechanism is applied on the digital twin of a marine thruster. Satisfactory accuracy was achieved in the optimization during continuous adaptation. However, further research is required on the algorithms and hardware to reach the real-time computation requirement.

show abstract

“…In recent years, kinds of surrogate model-based approaches, including Response Surface Method (RSM) [10], Neural Networks (NNs) [11], Support Vector Machine (SVM) [12], Kriging meta-model [13]- [15] and Radial Basis Function (RBF) [16], have been increasingly favored due to their significant efficiency in reliability analysis. The basic principle of these methods is to construct a surrogate model as an alternative to the implicit performance function, and then complete the reliability assessment.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Adaptive Reliability Analysis Method Based on Kriging and Weighted Average Misclassification Rate Improvement

et al. 2019

View full text Add to dashboard Cite

In the past few years, the Kriging model based on the adaptive design of experiments (DoE) has attracted extensive attention in analyzing the reliability of structures involving time-consuming simulations or complicated implicit performance function. Although varieties of sampling strategies have been proposed, they update DoE mainly by selecting the sample at which its corresponding learning function value is the maximum or minimum. However, there are usually two drawbacks. First, the training samples in DoE are easily clustered or overlapped. Second, the existing strategies usually only consider the improvement of prediction accuracy at the new training sample rather than the accuracy improvement of the region near the new training sample. Unfortunately, these two drawbacks can cause some unnecessary performance function evaluations. Therefore, an efficient adaptive sampling strategy and reliability analysis algorithm based on Kriging model, weighted average misclassification rate, sampling uniformity and gradient of prediction uncertainty are proposed. Furthermore, an improved stopping criterion based on the relative error estimation of failure probability is also developed to further reduce iteration. Subsequently, two explicit examples from the literature are analyzed to verify the effectiveness and superiority of the proposed method. Finally, a truss structure subjected to six external loads is investigated to illustrate the feasibility of the proposed reliability analysis method in engineering applications.

show abstract

Development of an adaptive surrogate model for production optimization

Cited by 93 publications

References 29 publications

Analysis and multi-objective optimization design of wheel based on aerodynamic performance

Analysis and multi-objective optimization design of wheel based on aerodynamic performance

Towards online adaptation of digital twins

An Efficient Adaptive Reliability Analysis Method Based on Kriging and Weighted Average Misclassification Rate Improvement

Contact Info

Product

Resources

About