一种基于梯度信息的多目标优化算法

doi:10.3969/j.issn.0438-1157.2013.12.020

化工学报 ›› 2013, Vol. 64 ›› Issue (12): 4401-4409.DOI: 10.3969/j.issn.0438-1157.2013.12.020

一种基于梯度信息的多目标优化算法

祁荣宾^1,2, 刘趁霞^1,2, 钟伟明^1,2, 钱枫^1,2

1. 化工过程先进控制和优化技术教育部重点实验室, 上海 200237;
2. 华东理工大学信息科学与工程学院, 上海 200237

收稿日期:2013-05-31 修回日期:2013-07-20 出版日期:2013-12-05 发布日期:2013-12-05
通讯作者: 祁荣宾
作者简介:祁荣宾（1974- ），女，博士，副研究员。
基金资助:
国家重点基础研究发展计划项目（2012CB720500）；国家自然科学基金项目（U1162202，61174118，61222303，21206037）；国家高技术研究发展计划项目（2013AA040701）；中央高校基本科研业务费专项基金；上海市重点学科建设项目（B504）。

A multi-objective optimization algorithm based on gradient information

QI Rongbin^1,2, LIU Chenxia^1,2, ZHONG Weiming^1,2, QIAN Feng^1,2

1. Key Laboratory of Advanced Control and Optimization for Chemical Processes, Ministry of Education, Shanghai 200237, China;
2. School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China

Received:2013-05-31 Revised:2013-07-20 Online:2013-12-05 Published:2013-12-05
Supported by:
supported by the National Basic Research Program of China (2012CB720500),the National Natural Science Foundation of China (U1162202，61174118，61222303，21206037),the High-tech Research and Development Program of China (2013AA040701),the Fundamental Research Funds for the Central Universities and Shanghai Leading Academic Discipline Project (B504).

摘要/Abstract

摘要： 传统的多目标进化算法多是基于Pareto最优概念的类随机搜索算法，求解速度较慢，特别是针对动态多目标优化问题。就此提出了一种新的基于梯度信息的多目标寻优算法（hybrid optimization algorithm based on single and multi-objective gradient information，HSMGOA），该算法首先利用种群中每个个体对各目标的负梯度方向，以有效保证种群个体能沿单个目标函数值减小的方向加快搜索；同时为避免由于多目标问题之间的冲突性而导致其他目标函数的显著增大，将多个目标的梯度信息方向整合为一个方向进行协同搜索；并且还提出了一种新的选择置点法，以加快算法初始寻优速度并提供优良的初始种群。通过对ZDT系列测试函数的仿真可以看出，HSMGOA在较少的运行次数下，其性能远远优于NSGA2算法。最后将HSMGOA与NSGA2混合以解决补料分批生化反应过程的动态多目标优化问题，并将取得的Pareto最优解集与NSGA2、MOPSO比较可知，该混合算法在解决该化工问题时表现出了更好的性能。

关键词: 多目标, 优化算法, 梯度信息, 选择置点法, 补料分批生化反应器, 动态优化

Abstract: Most of the basic multi-objective evolutionary algorithm is one kind of similar random search algorithm based on the concept of Pareto optimization,which with the slowly speed,especially for dynamic multi-objective problems.Accordingly,the hybrid optimization algorithm based on single and multi-objective gradient information (HSMGOA) is proposed.The algorithm confirms the direction of variation on each individual by using the gradient information.Firstly,the negative gradient direction information of each target in the population is calculated,those operation guarantees the individual species moving to the optimization declining direction for each of the single objective value effectively.Due to the conflict between each objective of multi-objective problem,it may cause the increase of the other objective function value if only considering the fall direction of one target.Therefore,this article also joins in the random weighted integration method,which fusing the gradient direction information of multiple goals to one search direction.Also,based on the traditional crowding distance selection method,this paper proposes a new select scatter point method to further speed up the optimization algorithm and provide the best initial population.Through the simulation of ZDT series test function and the analysis results with the NSGA2,it can be seen that the performance of the proposed algorithm is much better than the NSGA2 algorithm with less run times.It also shows that this algorithm has faster convergence.Finally a new algorithm was proposed by mixing the algorithm with NSGA2,and it is applied to dynamic multi-objective optimization of fed-batch bioreactor,the preferable Pareto optimal solution set is obtained.Compared with NSGA2 and MOPSO,the new algorithm shows better performance.

Key words: multi-objective, optimization algorithm, gradient information, selection and collocation method, fed-batch bioreactor, dynamic optimization

中图分类号:

TQ021.8

祁荣宾, 刘趁霞, 钟伟明, 钱枫. 一种基于梯度信息的多目标优化算法[J]. 化工学报, 2013, 64(12): 4401-4409.

QI Rongbin, LIU Chenxia, ZHONG Weiming, QIAN Feng. A multi-objective optimization algorithm based on gradient information[J]. CIESC Journal, 2013, 64(12): 4401-4409.

参考文献 20

[1]	Deb K, Pratap A, Agarwal S, Meyarivan T.A fast and elitist multi-objective genetic algorithm:NSGA-Ⅱ[J].IEEE Transactions on Evolutionary Computation, 2002, 6 (2):182-197
[2]	Laumanns M, Thiele L, Deb K, Zitzler E.Combining convergence and diversity in evolutionary multi-objective optimization[J].Evolutionary Computation, 2002, 10 (3):263-282
[3]	Brockhoff D, Zitzler E.Are all objectives necessary on dimensionality reduction in evolutionary multi-objective optimization//Thomas P R, Hans-Georg B, Edmund B, Merelo-Guervó s Juan J, Darrell Whitley L, Xin Yao. Parallel Problem Solving from Nature-PPSN IX[C].Berlin:Springer Berlin Heidelberg, 2006:533-542
[4]	Hernandez-Diaz A G, Santana-Quintero L V, Coello C A, Molina J.Pareto-adaptive-dominance[J].Evolutionary Computation, 2007, 15 (4):533-542
[5]	Deb K, Saxena D K.On finding Pareto-optimal solutions through dimensionality reduction for certain large-dimensional multi-objective optimization problems[R].Kanpur:Kanpur Genetic Algorithms Laboratory, 2005
[6]	Lahanas M, Baltas D, Giannouli S.Global convergence analysis of fast multi-objective gradient based dose optimization algorithms for high-dose-rate brachytherapy[J].Phys.Med.Biol., 2003, 48 (5):599-617
[7]	Salomon R.Evolutionary algorithm and gradient search:similarities and differences[J].IEEE Transactions on Evolutionary Computation, 1998, 2 (2):45-55
[8]	Goh C K, Ong Y S, Tan K C, Teoh E J.An investigation on evolutionary gradient search for multi-objective optimization// Evolutionary Computation[C].Hong Kong, 2008:3741-3746
[9]	Smaili A A, Diab N A, Atallah N A.Optimum synthesis of mechanisms using tabu-gradient search algorithm[J].Journal of Mechanical Design, 2004, 127 (5):917-923
[10]	Shukla P K.On gradient based local search methods in unconstrained evolutionary multi-objective optimization//Evolutionary Multi-Criterion Optimization[C].Berlin:Springer Berlin Heidelberg, 2007:96-110
[11]	Ren Ziyan, Pham Minh-Trien, Song Minho, Kim Dong-Hun, Koh Chang Seop.A robust global optimization algorithm of electromagnetic devices utilizing gradient index and multi-objective optimization method[J].IEEE Transactions on Magnetics, 2011, 47 (5):1254-1257
[12]	Yu G, Chai T, Luo X.Multi-objective production planning optimization using hybrid evolutionary algorithms for mineral processing[J].IEEE Transactions on Evolutionary Computation, 2011, 15 (4):487-514
[13]	Qian W, Wang Y.A new multi-objective evolutionary algorithm based on weighted gradient//2012 Eighth International Conference on Natural Computation (ICNC)[C].IEEE, 2012:808-811
[14]	Coello C, Pultdo G T, Lechuga M S.Handing multiple objectives with particle swarm optimization[J].IEEE Transactions on Evolutionary Computation, 2001, 8 (3):256-279
[15]	Schott J R.Fault tolerant design using single and multi-criteria genetic algorithm optimization[D].MA, Cambridge:Massachusetts Institute of Technology, 1995
[16]	Zitzler E, Deb K, Thiele L.Comparison of multi-objective evolutionary algorithms empirical results[J].Evolutionary Computation, 2000, 8 (2):173-195
[17]	Sarkar D, Modak J M.Optimisation of fed-batch bioreactors using genetic algorithms[J].Chemical Engineering Science, 2003, 58 (11):2283-2296
[18]	Sarkar D, Modak J M.Pareto-optimal solutions for multi-objective optimization of fed-batch bioreactors using non-dominated sorting genetic algorithm[J].Chemical Engineering Science, 2005, 60 (2):481-492
[19]	He Yijun (贺益君), Yu Huanjun (俞欢军), Cheng Biao (成飚), Chen Dezhao (陈德钊).Multi-objective particle swarm optimization approach to solution of fed-batch bioreactor dynamic multi-objective optimization[J].Journal of Chemical Industry and Engineering (China) (化工学报), 2007, 58 (5):1262-1270
[20]	Spall J C.Implementation of the simultaneous perturbation algorithm for stochastic optimization[J].IEEE Transactions on Aerospace and Electronic Systems, 1998, 34 (3):817-823

一种基于梯度信息的多目标优化算法

A multi-objective optimization algorithm based on gradient information

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 20

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张生安, 刘桂莲. 高效太阳能电解水制氢系统及其性能的多目标优化[J]. 化工学报, 2023, 74(3): 1260-1274.
[2]	张淑君, 王诗慧, 张欣, 吉旭, 戴一阳, 党亚固, 周利. 集成轻烃回收单元代理模型的氢气网络多目标优化[J]. 化工学报, 2022, 73(4): 1658-1672.
[3]	石晓青, 朱炜玄, 叶昊天, 韩志忠, 董宏光. 碳五隔壁反应精馏预处理工艺模拟及多目标优化[J]. 化工学报, 2022, 73(3): 1246-1255.
[4]	刘立邦, 杨颂, 王志坚, 贺欣欣, 赵文磊, 刘守军, 杜文广, 米杰. 基于改进WOA-LSTM的焦炭质量预测[J]. 化工学报, 2022, 73(3): 1291-1299.
[5]	林渠成, 廖祖维. 基于分解算法的功热交换网络多目标优化[J]. 化工学报, 2022, 73(11): 5047-5055.
[6]	柳旭, 许松林, 王燕飞. 原甲酸三甲酯-醋酸萃取精馏全局多目标优化[J]. 化工学报, 2022, 73(10): 4518-4526.
[7]	魏彬, 周鑫, 王耀伟, 郭振莲, 陈小博, 刘熠斌, 杨朝合. 基于改进NSGA-Ⅱ算法的FCC分离系统多目标优化[J]. 化工学报, 2021, 72(5): 2735-2744.
[8]	赵杨, 熊伟丽. 基于多策略自适应差分进化算法的污水处理过程多目标优化控制[J]. 化工学报, 2021, 72(4): 2167-2177.
[9]	李勇, 钱锋, 宋育梅. 基于特征选择的常减压装置模型及在计划优化中的应用[J]. 化工学报, 2021, 72(3): 1419-1429.
[10]	朱鹏飞, 郭磊磊, 尧兢, 杨福胜, 张早校, 吴震. 以生物质为燃料的SOFC和发动机热电联供系统：参数分析和性能优化[J]. 化工学报, 2021, 72(2): 1089-1099.
[11]	杨辉, 代文豪, 陆荣秀, 朱建勇. 基于分离系数校正的稀土萃取流程模拟[J]. 化工学报, 2020, 71(7): 3180-3190.
[12]	吴乐, 王竞, 王玉琪, 郑岚. 生物质油与蜡油在FCC装置共炼的多目标优化[J]. 化工学报, 2020, 71(5): 2182-2189.
[13]	王磊, 陈玉婷, 徐燕燕, 叶爽, 黄伟光. 综合考虑经济性与效率的换热网络多目标约束优化方法[J]. 化工学报, 2020, 71(3): 1189-1201.
[14]	关宏伟, 叶凌箭, 沈非凡, 顾德, 宋执环. 基于经济模型预测控制的金氰化浸出过程动态实时优化[J]. 化工学报, 2020, 71(3): 1122-1130.
[15]	何德峰, 张永达, 李廉明, 仇翔. 循环流化床燃烧系统无终端约束字典序经济预测控制[J]. 化工学报, 2020, 71(3): 1210-1216.