| 基于改进多目标差分进化算法的诺西肽发酵过程优化 |
| |
| 引用本文： | 牛大鹏,王福利,何大阔,贾明兴.基于改进多目标差分进化算法的诺西肽发酵过程优化[J].控制理论与应用,2010,27(4):505-508. |
| |
| 作者姓名： | 牛大鹏 王福利 何大阔 贾明兴 |
| |
| 作者单位： | 1. 东北大学流程工业综合自动化教育部重点实验室,辽宁沈阳110004;东北大学信息科学与工程学院,辽宁沈阳110004
2. 东北大学信息科学与工程学院,辽宁沈阳,110004 |
| |
| 基金项目： | 国家自然科学基金资助项目(60774068); 教育部及辽宁省流程工业综合自动化重点实验室开放课题基金资助项目(PAL200509). |
| |
| 摘 要： | 诺西肽发酵存在着产量较低和生产效率不高的问题, 多目标优化是解决此类问题的有效途径. 将差分进化算法引入多目标优化, 构建了改进的多目标差分进化算法((IDEMO). 根据Pareto优劣等级和拥挤距离对种群进行选择操作, 并引入自适应变异算子和棍沌迁移算子以改善算法性能. 在诺西肽分批发酵动力学模型的基础上建立了多目标优化的模型, 并利用IDEMO对此优化问题进行了求解, 优化结果表明了算法的有效性.
|
| 关 键 词： | 诺西肽发酵 多目标优化 差分进化算法 自适应变异算子 混沌迁移算子 |
| 收稿时间： | 2008/5/14 0:00:00 |
| 修稿时间： | 2008/11/7 0:00:00 |
Optimization of nosiheptide fermentation process based on the improved differential evolution algorithm for multi-objective optimization |
| |
| NIU Da-peng,WANF Fu-li,HE Da-kuo and JIA Ming-xing.Optimization of nosiheptide fermentation process based on the improved differential evolution algorithm for multi-objective optimization[J].Control Theory & Applications,2010,27(4):505-508. |
| |
| Authors: | NIU Da-peng WANF Fu-li HE Da-kuo and JIA Ming-xing |
| |
| Affiliation: | Key Laboratory of Integrated Automation of Process Industry, Ministry of Education, Northeastern University; School of Information Science and Engineering, Northeastern University,Key Laboratory of Integrated Automation of Process Industry, Ministry of Education, Northeastern University; School of Information Science and Engineering, Northeastern University,School of Information Science and Engineering, Northeastern University,School of Information Science and Engineering, Northeastern University |
| |
| Abstract: | Multi-objective optimization is an effective way to solve the problem of low yield and low efficiency in the nosiheptide fermentation process. Based on the differential evolution algorithm, we propose an improved differential evolution algorithm for multi-objective optimization(IDEMO), in which the selection operation is based on the Pareto rank and the crowding distance of each individual in the population. The adaptive mutation operator and the chaotic migration operator are developed to improve the performance of the algorithm. Based on the kinetic models of the nosiheptide batch fer-mentation process, we develop a multi-objective optimization model(IDEMO) for its optimization. Application results show its effectiveness. |
| |
| Keywords: | nosiheptide fermentation multi-objective optimization differential evolution algorithm adaptive mutation operator chaotic migration operator |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《控制理论与应用》浏览原始摘要信息 |
|
点击此处可从《控制理论与应用》下载全文 |
|
