摘要
针对基于迭代学习控制的间歇过程产品质量优化控制算法难以进行收敛性分析的难题,以数据驱动的神经模糊模型为基础,提出一种新颖间歇过程的产品质量迭代学习控制方法。通过在优化算法中加入了新的约束条件,改变了最优解的搜索空间范围,从而使产品质量在批次轴上收敛,并创新性地对优化问题的收敛性给出了严格的数学证明。在理论研究的基础上,将提出的算法用于间歇连续反应釜的终点质量控制研究,仿真结果验证了本文算法的有效性和实用价值,为间歇过程的优化控制提供了一条新途径。
Considering that it is difficult to analyze the convergence of iterative learning optimal control for quality control of batch processes, a novel iterative learning control based on data-driven neural fuzzy model for product quality control in batch process was proposed. In the presented algorithm, the region of the searching space for optimal solution is changed by adding a new constraint condition, which resulted in the convergence of the product quality in batch axes. Moreover, the rigorous proof was given. Lastly, to verify the efficiency of the proposed algorithm, it was applied to a benchmark batch process. The simulation results showed that the proposed method was better and could be applied to practical processes, thus it provides a new way for the control of batch processes.
出处
《化工学报》
EI
CAS
CSCD
北大核心
2009年第8期2017-2023,共7页
CIESC Journal
基金
上海市国际科技合作基金项目(08160705900)
上海市科委地方高校专项基金项目(08160512100)
上海市教育委员会科研创新项目(09YZ08)
上海大学"十一五"211建设项目~~
关键词
间歇过程
产品质量控制
神经模糊网络
迭代学习
batch process
product quality control
fuzzy neural network
iterative learning control
