Improved Hybrid Differential Evolution for NLP/MINLP Engineering Optimization Problems
In this paper, an improved hybrid differential evolution algorithm (IHDE) is proposed for nonlinear and mixed-integer nonlinear programming models (NLPs and MINLPs) in engineering optimization fields. In order to improve the global searching ability and convergence speed, IHDE takes full advantage of differential information and global statistical information extracted respectively by differential evolution algorithm (DE) and the annealing mechanism-embedded estimation of distribution algorithm (EDA), and adopts the feasibility rules to handle constraints. Simulation and comparison based on three bench-marks and a practical scheduling of crude oil blending problem demonstrate the efficiency, accuracy and robustness of IHDE. Moreover, the key parameters of IHDE are also analyzed.
Differential Evolution Estimation of Distribution Hybrid Evolution Mixed-Coding Feasibility Rules
Bai Liang Wang Junyan Jiang Yongheng Huang Dexian
Department of Automation, Tsinghua Univ., Beijing 100084, China National Laboratory for Information Marvell Technology (Shanghai) Ltd, Keyuan Rd, Pudong Dist, Shanghai 201203, China
国内会议
厦门
英文
1-6
2012-08-01（万方平台首次上网日期，不代表论文的发表时间）