摘要
针对传统方法在解决化工参数辨识问题中易陷入局部最优、导致求解精度不足的问题,提出了一种组合三角变异差分进化(CTMDE)算法,融入了组合三角高斯变异策略和DE/current-to-pbest/1变异策略.其中,组合三角高斯变异策略引入了组合权重来适应性利用较优个体、一般个体、当前个体的信息,维持种群多样性;而DE/current-to-pbest/1变异策略能够利用种群中的较优个体来指导搜索,对解空间的开采能力较强.两者结合使得算法在加快收敛速度的同时降低陷入局部最优的可能性.在12个基准测试函数上,将CTMDE算法与其他新近DE算法进行比较,并将CTMDE算法应用于甲醇转化为烃类物质的参数辨识问题.实验结果表明:CTMDE算法具有较好的寻优性能,且在化工参数辨识问题上具有较好的求解效果.
The traditional methods are prone to falling into local optimum when identifying the parameters of chemical reaction kinetics,which may obtain unsatisfactory results.To solve this problem,a differential evolution with combined triangular mutation(CTMDE)strategy was proposed.The combined triangular mutation strategy and the DE/current-to-pbest/1 mutation strategy were integrated in CTMDE to improve the performance.In the proposed CTMDE,the combined triangular mutation strategy introduced a combination weight to adaptively employ the information of the better individual,the general individual,and the current individual to maintain the population diversity.Meanwhile,the DE/current-to-pbest/1 mutation strategy can use the better individual to guide the search,and has a strong ability to exploit the solution space.The combination of the two mutation strategies can accelerate the convergence rate,which can also decrease the probability of falling into local optimum.In the experiments,CTMDE was compared with several excellent DE algorithms on 12 benchmark test functions,and it was applied to identify the parameters of the methanol-to-hydrocarbons.The experimental results show that CTMDE can achieve better performance and it is an effective approach for parameters identification of chemical reaction kinetics.
作者
熊小峰
刘啸婵
郭肇禄
张文生
XIONG Xiaofeng;LIU Xiaochan;GUO Zhaolu;ZHANG Wensheng(School of Science,Jiangxi University of Science and Technology,Ganzhou 341000,Jiangxi China;Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China)
出处
《华中科技大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2020年第9期12-18,共7页
Journal of Huazhong University of Science and Technology(Natural Science Edition)
基金
国家自然科学基金资助项目(61662029,U1636220)
江西省教育厅科技项目(GJJ160623,GJJ170495)
江西理工大学青年英才支持计划资助项目(2018)。
关键词
差分进化
高斯变异
局部最优
反应动力学
参数辨识
differential evolution
Gaussian mutation
local optimum
reaction kinetics
parameter identification
