Systems Engineering and Electronics ›› 2018, Vol. 40 ›› Issue (1): 198-208.doi: 10.3969/j.issn.1001-506X.2018.01.29

Previous Articles     Next Articles

Clustering-based multi-objective estimation of distribution algorithm and its application

ZHANG Xiujie1, GAO Xiaoxia2, ZHANG Hu2, ZHAO Jie1   

  1. 1. School of Mechanical and Electrical Engineering, Harbin Institute of Technology, Harbin 150001, China; 2. School of Astronautics, Harbin Institute of Technology, Harbin 150001, China
  • Online:2018-01-08 Published:2018-01-08

PDF (PC)

Abstract:

In order to improve the deficiencies, that is, insufficiently considering the regularity property, inappropriately handling abnormal solutions, easily losing population diversity, and the excessive computational cost of constructing the optimal probabilistic model, which exist in the process of using common multi-objective estimation of distribution algorithms to solve multi-objective optimization problems, this paper proposes a clustering-based multi-objective estimation of distribution algorithm (CEDA). At each generation, CEDA adopts an agglomerative hierarchical clustering algorithm to find the neighborhood structure of population, and based on the structure, CEDA builds a multivariate Gaussian model for each solution to approximate population structure and to sample new solutions. In order to reduce the computational cost of modelling, neighboring solutions share the same covariance matrix to construct Gaussian models. The comparison experiments based on benchmark instances indicate that CEDA is able to solve complicated multi-objective optimization problems. Practical application based on optimization design of the gear reducer shows CEDA also has favorable practicability and superiority.

[an error occurred while processing this directive]