A protein inspired RNA genetic algorithm for parameter estimation in hydrocracking of heavy oil
A protein inspired RNA genetic algorithm for parameter estimation in hydrocracking of heavy oil
复制标题
用于重油加氢裂化参数估计的蛋白质启发 RNA 遗传算法
DOI：
10.1016/j.cej.2010.12.036
复制
发表时间：
2011-02
影响因子：
15.1
通讯作者：
中科院分区：
文献类型：
--
作者：
加氢裂化是炼油厂的关键工艺，合适的模型有助于理解和设计加氢裂化过程。模拟从RNA到蛋白质的过程，提出了一种基于蛋白质启发的RNA遗传算法（PIRGA）来估计重油加氢裂化反应参数。在PIRGA中，每个个体由一条RNA链表示，并采用一种新的适应度函数，结合传统的适应度值和个体排序，以保持种群的多样性。此外，传统的交叉算子被RNA编码算子和蛋白质折叠算子所取代，以提高搜索能力。在PIRGA中引入自适应变异概率，使算法有更多的机会跳出局部最优。对7个标准函数的数值实验表明，PIRGA在收敛速度和精度上都明显优于其他遗传算法。用PIRGA得到10个参数，建立了重油加氢裂化动力学模型。实验结果表明，预测值与实验数据吻合较好，相对误差小于5%。通过实验验证了模型的有效性和鲁棒性。
Hydrocracking is a crucial process in refineries and suitable model is useful to understand and design hydrocracking processes. Simulating the procedure from RNA to protein, a protein inspired RNA genetic algorithm (PIRGA) is proposed to estimate the parameters of hydrocracking of heavy oil. In the PIRGA, each individual is represented by a RNA strand and a new fitness function combining traditional fitness value and individual ranking is employed to maintain population diversity. Furthermore conventional crossover operators are replaced by RNA-recoding operator and protein-folding operators to improve the searching ability. An adaptive mutation probability in the PIRGA makes the algorithm have more chance to jump out of local optima. Numerical experiments on seven benchmark functions indicate that the PIRGA outperforms other genetic algorithms on both convergence speed and accuracy greatly. 10 parameters are obtained by the PIRGA and the kinetic model for hydrocracking of heavy oil is established. Experimental results reveal that the predictive values are in good agreement with the experimental data with relative error less than 5%. The effectiveness and the robustness of the model are also validated by experiments.
登录
查看更多内容
影响因子：
15.1
作者：
I. R. S. Victorino;J. P. Maia;E. R. Morais;M. Maciel;R. M. Filho
通讯作者：
I. R. S. Victorino;J. P. Maia;E. R. Morais;M. Maciel;R. M. Filho
影响因子：
4.7
作者：
YoungSu Yun;M. Gen
通讯作者：
YoungSu Yun;M. Gen
DOI：
10.1016/j.ijheatmasstransfer.2005.11.031
发表时间：
2006-07
影响因子：
5.2
作者：
T. Dias;L. Milanez
通讯作者：
T. Dias;L. Milanez
基于 DNA 的氢化反应参数估计遗传算法
影响因子：
15.1
作者：
Chen, Xiao;Wang, Ning
通讯作者：
Wang, Ning
影响因子：
4.3
作者：
Mansoornejad, Behrang;Mostoufi, Navid;Jalali-Farahani, Farhang
通讯作者：
Jalali-Farahani, Farhang