回归分类协同昂贵约束多目标优化算法

胡晓敏; 王炳海; 黄佳玟; 龚超富; 李敏

doi:10.12052/gdutxb.240032

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

回归分类协同昂贵约束多目标优化算法

计算机科学与技术 | 更新时间：2026-05-27

- 回归分类协同昂贵约束多目标优化算法
- Regression Classification Collaborative Expensive Constrained Multi-objective Optimisation Algorithm
- 广东工业大学学报 2024年41卷第6期页码：69-79
- 作者机构：
  
  广东工业大学计算机学院,广东,广州,510006
- 作者简介：
  
  胡晓敏(1983–)，女，副教授，博士，主要研究方向为昂贵多约束优化、计算智能、数据挖掘，E-mail：xmhu@ieee.org
  李敏(1978–)，女，博士，主要研究方向为人工智能、计算智能、深度学习，E-mail：lmjsj@gdut.edu.cn
- 基金信息：
  
  国家自然科学基金资助项目(62272108)
- DOI：10.12052/gdutxb.240032
  中图分类号： TP301.6
- 纸质出版：2024
- 稿件说明：
移动端阅览
胡晓敏, 王炳海, 黄佳玟, 龚超富, 李敏. 回归分类协同昂贵约束多目标优化算法[J]. 广东工业大学学报, 2024, 41(6): 69-79.

Hu Xiao-min, Wang Bing-hai, Huang Jia-wen, et al. Regression Classification Collaborative Expensive Constrained Multi-objective Optimisation Algorithm[J]. 2024, 41(6): 69-79.
胡晓敏, 王炳海, 黄佳玟, 龚超富, 李敏. 回归分类协同昂贵约束多目标优化算法[J]. 广东工业大学学报, 2024, 41(6): 69-79. DOI： 10.12052/gdutxb.240032.

Hu Xiao-min, Wang Bing-hai, Huang Jia-wen, et al. Regression Classification Collaborative Expensive Constrained Multi-objective Optimisation Algorithm[J]. 2024, 41(6): 69-79. DOI： 10.12052/gdutxb.240032.

摘要

现有基于代理模型的昂贵约束多目标优化算法存在两个问题，即使用回归模型拟合约束时带来的误差影响算法的搜索方向，以及目标函数存在不可拟合的情况时，回归模型拟合效果差。为解决这两个问题，提出一种分类模型与回归模型协同的昂贵约束多目标进化优化算法。该方法使用分类模型对搜索空间进行粗略划分，指导算法快速进入可行区域，减弱约束拟合误差的影响。使用回归模型在可行区域内优化目标函数。两种模型协同工作，分类模型提供概括的搜索方向，回归模型进行精细建模。这种模型的融合，既考虑了约束误差对算法的影响，也综合了目标函数的可拟合性问题，能更全面准确地描绘复杂问题的特征，从而提高算法的求解效率和效果，为进一步提升基于代理模型的昂贵约束多目标优化提供了一种协同建模的有效途径。

Abstract

The existing expensive constrained multi-objective optimization algorithms based on surrogate models face two main issues. Firstly

the use of regression models to fit constraints introduces errors that affect the algorithm's search direction. Secondly

when the objective function is non-fittable

the performance of the regression model for fitting is poor. To address these issues

a collaborative expensive constrained multi-objective evolutionary optimization algorithm is proposed

which combines a classification model with a regression model. This method employs the classification model to roughly divide the search space

guiding the algorithm to quickly enter the feasible region and reducing the impact of constraint fitting errors. The regression model is then used to optimize the objective function within the feasible region. The collaboration of the two models allows the classification model to provide a general search direction while the regression model performs detailed modeling. This fusion of models not only considers the impact of constraint errors on the algorithm but also comprehensively addresses the fittability of the objective function

enabling a more comprehensive and accurate depiction of the characteristics of complex problems. As a result

it enhances the efficiency and effectiveness of the algorithm

providing an effective approach for further improving expensive constrained multi-objective optimization based on surrogate models.

关键词

Keywords

references

JIN Y. A comprehensive survey of fitness approximation in evolutionary computation[J]. Soft Computing, 2005, 9(1): 3-12.

JIN Y. Surrogate-assisted evolutionary computation: recent advances and future challenges[J]. Swarm and Evolutionary Computation, 2011, 1(2): 61-70.

BOX G E P, DRAPER N R. Empirical model- building and response surfaces[M]. New York: John Wiley Sons, 1987.

BROOMHEAD D S, LOWE D. Radial basis functions, multi-variable functional interpolation and adaptive networks[J]. Royal Signals and Radar Establishment Malvern, 1988: 1-34.

KRIGE D G. A statistical approach to some basic mine valuation problems on the witwatersrand[J]. Journal of the Southern African Institute of Mining and Metallurgy, 1951, 52(6): 119-139.

ZURADA J. Introduction to artificial neural systems[M]. St. Paul: West Publishing Co. , 1992.

CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20: 273-297.

LIM D, JIN Y, ONG Y S, et al . Generalizing surrogate-assisted evolutionary computation[J ] . IEEE Transactions on Evolutionary Computation, 2009, 14(3): 329-355.

KNOWLES J. ParEGO: a hybrid algorithm with on-line landscape approximation for expensive multiobjective optimization problems[J]. IEEE Transactions on Evolutionary Computation, 2006, 10(1): 50-66.

ZHANG Q, LIU W, TSANG E, et al . Expensive multiobjective optimization by MOEA/D with Gaussian process model[J ] . IEEE Transactions on Evolutionary Computation, 2009, 14(3): 456-474.

SEAH C W, ONG Y S, TSANG I W, et al . Pareto rank learning in multi-objective evolutionary algorithms[C ] //2012 IEEE Congress on Evolutionary Computation. Brisbane, QLD: IEEE, 2012: 1-8.

CHUGH T, JIN Y, MIETTINEN K, et al . A surro gate-assisted reference vector guided evolutionary algorithm for computationally expensive many-objective optimization[J ] . IEEE Transactions on Evolutionary Computation, 2018, 22(1): 129-142.

CAI X Y, MA Z Y, ZHANG F, et al . Adaptive multitask with multipopulation-based cooperative search for expensive multiobjective optimization problems[J ] . Chinese Journal of Computers, 2021, 44(9): 1934-1948.

JIANG P, CHENG Y, YI J, et al . An efficient constrained global optimization algorithm with a clustering-assisted multiobjective infill criterion using Gaussian process regression for expensive problems[J ] . Information Sciences, 2021, 569: 728-745.

CHEN J H, QIU M J, TANG J J, et al . A hybrid algorithm based on improved differential evolution and particle swarm optimization for power system optimal power flow calculation[J ] . Journal of Guangdong University of Technology, 2017, 34(5): 22-28

GU Q, WANG Q, LI X, et al . A surrogate-assisted multi-objective particle swarm optimization of expensive constrained combinatorial optimization problems[J ] . Knowledge-Based Systems, 2021, 223: 107049.

WANG H, JIN Y. A random forest-assisted evolutionary algorithm for data-driven constrained multiobjective combinatorial optimi-zation of trauma systems[J]. IEEE Transactions on Cybernetics, 2020, 50(2): 536-549.

CHUGH T, SINDHYA K, MIETTINEN K, et al . On constraint handling in surrogate-assisted evolutionary many-objective optimization[C ] //Parallel Problem Solving from Nature-PPSN XIV: 14th International Conference. Edinburgh, UK: Springer International Publishing, 2016: 214-224.

YANG Q, CHEN W N, DENG J D, et al . A level-based learning swarm optimizer for large-scale optimization[J ] . IEEE Transactions on Evolutionary Computation, 2018, 22(4): 578-594.

HU X M, LONG Z T, LI M. A multi-objective recommendation algorithm based on user stratification[J]. Journal of Guangdong University of Technology, 2023, 40(1): 10-18.

CHENG R, JIN Y, OLHOFER M, et al . A reference vector guided evolutionary algorithm for many-objective optimization[J ] . IEEE Transactions on Evolutionary Computation, 2016, 20(5): 773-791.

CHENG R, JIN Y, NARUKAWA K, et al . A multiobjective evolutionary algorithm using gaussian process-based inverse modeling[J ] . IEEE Transactions on Evolutionary Computation, 2015, 19(6): 838-856.

WEI F F, CHEN W N, YANG Q, et al . A classifier-assisted level-based learning swarm optimizer for expensive optimization[J ] . IEEE Transactions on Evolutionary Computation, 2021, 25(2): 219-233.

MA Z, WANG Y. Evolutionary constrained multiobjective optimization: test suite construction and performance comparisons[J]. IEEE Transactions on Evolutionary Computation, 2019, 23(6): 972-986.

COELLO C A C, CORTéS N C. Solving multiobjective optimization problems using an artificial immune system[J]. Genetic Programming and Evolvable Machines, 2005, 6: 163-190.

DATTA R, REGIS R G. A surrogate-assisted evolution strategy for constrained multi-objective optimization[J]. Expert Systems with Applications, 2016, 57: 270-284.

TIAN Y, CHENG R, ZHANG X, et al . PlatEMO: a matlab platform for evolutionary multi-objective optimization[J ] . IEEE Computational Intelligence Magazine, 2017, 12(4): 73-87.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

6061铝合金铣削工艺参数多目标优化

基于动态模糊混沌粒子群算法的含电动汽车微电网多目标优化调度研究

MOEA/D聚合函数的二次泛化及其优化性能分析

求解多目标背包问题的改进人工鱼群算法

带有时间窗的虚拟场站接驳补货车辆路径问题