| 引用本文: | 代伟,王献伟,路兴龙,柴天佑.基于案例推理增强学习的磨矿过程设定值优化[J].控制理论与应用,2019,36(1):53~64.[点击复制] |
| DAI Wei,WANG Xian-wei,LU Xing-long,CHAI Tian-you.Case-based reasoning and reinforcement learning integrated set-point optimization method for grinding process[J].Control Theory and Technology,2019,36(1):53~64.[点击复制] |
|
| 基于案例推理增强学习的磨矿过程设定值优化 |
| Case-based reasoning and reinforcement learning integrated set-point optimization method for grinding process |
| 摘要点击 2538 全文点击 1240 投稿时间：2017-10-05 修订日期：2018-03-18 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/CTA.2018.70719 |
| 2019,36(1):53-64 |
| 中文关键词 案例推理 增强学习 神经网络 设定值优化 磨矿过程 |
| 英文关键词 case-based reasoning reinforcement learning neural network set-point optimization grinding process |
| 基金项目 国家自然科学基金项目(61603393, 61741318), 江苏省自然科学基金项目(BK20160275), 中国博士后科学基金项目(2015M581885, 2018T110571), 东北大学流程工业综合自动化国家重点实验室开放课题(PAL–N201706)资助 |
|
| 中文摘要 |
| 磨矿粒度和循环负荷是磨矿过程产品质量与生产效率的关键运行指标, 相对于底层控制偏差, 回路设定值
对其影响要严重的多. 然而, 磨矿过程受矿石成分与性质、设备状态等变化因素影响, 运行工况动态时变, 难以建立
模型, 因此难以通过传统的模型方法优化回路设定值. 本文将增强学习与案例推理相结合, 提出一种数据驱动的磨
矿过程设定值优化方法. 首先根据当前运行工况, 采用基于Prey-Predator 优化的案例推理方法, 决策出可行的基于
Elman神经网络的Q函数网络模型; 然后利用实际运行数据, 在增强学习的框架下, 根据Q函数网络模型优化回路设
定值. 在基于METSIM的磨矿流程模拟系统上进行实验研究, 结果表明所提方法可根据工况变化在线优化回路设定
值, 实现磨矿运行指标的优化控制. |
| 英文摘要 |
| In grinding processes, particle size and circulating load are two key operation indexes for product quality and
production efficiency. With respect to the economic performance, the basic loop controller performance is most probably
not as important as the right selection of the loop set-points. The industrial grinding processes, however, are affected by
the factors such as composition and properties of ore, the equipment status and so on. When the large fluctuation of the
factors occurs, the operation will be time-varying, thereby making the process modeling very difficult. Therefore, it is
hard to employ the traditional model-based methods to optimize the loop set-points. In this paper, a data-driven optimalsetting
control method is proposed by using case-based reasoning (CBR) and reinforcement learning (RL) technologies.
The method first employs a Prey-Predator optimization-based CBR method to determine a feasible Elman neural networkbased
Q function model in accordance with current operation condition. Then, under the RL framework, the Q function
model is adopted to optimize the loop set-points according to the operation data. Experiments studies are carried out in a
METSIM-based grinding simulation system. Results show that the proposed method can realize the optimization control
of the grinding operation indexes by optimizing the loop set-points online according to the varied operation conditions. |
|
|
|
|
|