Some efficient approaches for multi-objective constrained optimization of computationally expensive black-box model problems
详细信息 查看全文
- 作者：F. Capitanescua ; florin.capitanescu@list.lu" class="auth_mail" title="E-mail the corresponding author ; A. Ahmadib ; E. Benettoa ; A. Marvugliaa ; L. Tiruta-Barnab
- 关键词：Multi-objective optimization ; Life cycle assessment ; Environmental engineering ; Expensive black-box model
- 刊名：Computers & Chemical Engineering
- 出版年：2015
- 出版时间：2 November 2015
- 年：2015
- 卷：82
- 期：Complete
- 页码：228-239
- 全文大小：873 K
文摘
- •
We propose new hybrid methods for expensive multiobjective optimization problems.
- •
The first method relies on a sensitivity-based MILP surrogate model.
- •
The second method relies on a functions’ curve fitting NLP surrogate model.
- •
The methods are applied to life cycle assessment-based optimization of water plants.
- •
The methods clearly outperform a state-of-the-art metaheuristic algorithm.