A multiobjective optimization based framework to balance the global exploration and local exploitation in expensive optimization

Feng, Zhiwei; Zhang, Qingbin; Zhang, Qingfu; Qian, Ting; Yang, Tao; Ma, Yang

doi:10.1007/s10898-014-0210-2

Cited by 62 publications

(26 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The aggregation method combines the objective functions into a scalar objective function that is used in a SOO context, thus producing one single compromise solution. To obtain an approximation to the , the SOO method must be run as many times as the desired number of points using different sets of weights vector [ 16 ].…”

Section: Multi-objective Optimization Approachmentioning

confidence: 99%

“…Multi-objective evolutionary algorithms based on decomposition (recognized in the scientific literature as MOEA/D) decompose a MOO problem into a number of scalar optimization subproblems (using a weight-dependent scalar aggregation function) and optimize them simultaneously [ 14 – 16 ]. The subproblems are simultaneously solved by handling a population of solutions that comprise the best solutions found so far for each subproblem.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Single Screw Extrusion Optimization Using the Tchebycheff Scalarization Method

Rocha

Matos

Costa

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The optimal design of a single screw extrusion (SSE) is a very difficult task since it deals with several conflicting performance indices. Past research to find the optimal SSE design has been successfully conducted by optimization procedures, in particular by multi-objective optimization. Problems with two or more objectives have been addressed by multi-objective evolutionary algorithms that search for the whole set of promising solutions in a single run. Our approach has been guided by the bi-objective optimization problems, using a methodology based on the weighted Tchebycheff scalarization function. The numerical results show that the proposed methodology is able to produce satisfactory results with physical meaning.

show abstract

Section: Multi-objective Optimization Approachmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Single Screw Extrusion Optimization Using the Tchebycheff Scalarization Method

Rocha

Matos

Costa

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Hence, in this paper, the above process is carried out iteratively. In each iteration, to balance the global exploration and local exploitation (Zhou et al 2007;Feng et al 2015), two new points, including the optimum of Eq. (29) and the point at which the samples are most sparse in the design space, are evaluated with the FEM and then added to the training sample set to gradually improve the three surrogate models until the optimization converges.…”

Section: T C C H a B W T C C H A B T C C H A B S T C C Hmentioning

confidence: 99%

An efficient space division–based width optimization method for RBF network using fuzzy clustering algorithms

Zhang

Gong

Fang

et al. 2019

Struct Multidisc Optim

View full text Add to dashboard Cite

The Radial Basis Function (RBF) network is one of the most widely used surrogate models in multidisciplinary design optimization. However, one of the challenges of applying the RBF network to engineering problems is how to efficiently optimize its width parameters. In this work, a novel space-division-based width optimization (SDWO) method is proposed to decompose the complex multivariable width optimization into several small-scale single-variable width optimizations. The SDWO method consists of two main steps. First, a two-stage fuzzy clustering algorithm is carried out to group the samples and divide the input space into several overlapping local regions, and the overlapping degree is controlled by a dimensionless expansion factor. Second, in each local region, one small-scale local RBF network (LRBFN) is constructed by solving a single-variable optimization problem when the LRBFN is needed for prediction. All these LRBFNs are independent of each other and can be constructed in parallel. The proposed method is efficient and particularly suitable for large sample sets. Test results of four sample sets verify that the proposed SDWO method has better performance than the conventional width optimization method in terms of both training efficiency and approximation accuracy. An inter-stage structure optimization is carried out, which demonstrates the efficiency of the proposed method in practical engineering applications.

show abstract

“…The bi-objective optimization problem (20) minimizes the predicted objective function value and maximizes the distance to the previously evaluated solutions. For this problem, we can employ well-developed multi-objective evolutionary algorithms (MOEAs), such as non-dominated sorting genetic algorithm -II (NSGA-II) [44] and the multiobjective evolutionary algorithm based on decomposition (MOEA/D) [45]- [47], to get the non-dominated front (NF) and corresponding non-dominated set (NS). In this paper, we choose NSGA-II since the magnitudes of these two objectives are different.…”

Section: ) Batch Infill Sampling Criterionmentioning

confidence: 99%

Optimal Design of Passive Control of Space Tethered-Net Capture System

Chen

Zhang

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

The space tethered-net is an important tool for space debris capture. But its rebound movement limits its effective working distance. To solve this issue, a passive control method using ''Energy dissipation band (EDB)'' is proposed in this paper. A semi-spring damper model of the EDB is first built and verified by the tests, and then the strengths of the bands are optimized with Radial Basis Function assisted optimization method with Batch infill Sampling criterion (RBFBS). Simulation results show that this passive control method can significantly increase the effective work distance of the space tethered-net, and RBFBS algorithm is able to optimize the strengths of the EDBs effectively and efficiently. This paper provides a new idea for the optimal design of the space tethered-net, which can be applied to the future flexible capture tasks.

show abstract

A multiobjective optimization based framework to balance the global exploration and local exploitation in expensive optimization

Cited by 62 publications

References 19 publications

Single Screw Extrusion Optimization Using the Tchebycheff Scalarization Method

Single Screw Extrusion Optimization Using the Tchebycheff Scalarization Method

An efficient space division–based width optimization method for RBF network using fuzzy clustering algorithms

Optimal Design of Passive Control of Space Tethered-Net Capture System

Contact Info

Product

Resources

About