引用本文:董洁,陈柔汝,彭开香.基于WD-MNPE-CVA的带钢热轧全流程动态过程监测方法[J].控制理论与应用,2024,41(12):2356~2364.[点击复制]
DONG Jie,CHEN Rou-ru,PENG.Dynamic process monitoring based on WD-MNPE-CVA for hot strip mill plant-wide process[J].Control Theory and Technology,2024,41(12):2356~2364.[点击复制]
基于WD-MNPE-CVA的带钢热轧全流程动态过程监测方法
Dynamic process monitoring based on WD-MNPE-CVA for hot strip mill plant-wide process
摘要点击 1734  全文点击 27  投稿时间:2022-06-02  修订日期:2024-08-28
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  10.7641/CTA.2023.20485
  2024,41(12):2356-2364
中文关键词  过程监测  邻域保持嵌入  规范变量分析  贝叶斯融合  带钢热轧全流程
英文关键词  process monitoring  neighborhood preserving embedding  canonical variable analysis  Bayesian fusion  hot strip mill plant-wide process
基金项目  国家重点研发计划项目(2021YFB3301200), 国家自然科学基金项目(U21A20483, 62273031)资助.
作者单位E-mail
董洁 北京科技大学自动化学院 dongjie@ies.ustb.edu.cn 
陈柔汝 北京科技大学自动化学院  
彭开香* 北京科技大学自动化学院 kaixiang@ustb.edu.cn 
中文摘要
      过程监测技术是保障复杂工业全流程安全、高质、高效运行的有效手段. 考虑带钢热轧过程的“非线性、多模态、动态性”等特征, 本文提出一种基于改进的加权差分邻域保持嵌入–规范变量分析(WD-MNPE-CVA)的带钢热轧全流程动态过程监测方法. 首先, 针对过程数据的非线性、多模态特性, 采用加权差分方法进行数据预处理; 其次,基于过程的机理知识进行流程划分, 并开发了一种改进的邻域保持嵌入算法, 基于样本点之间的欧氏距离和余弦距离, 获得每个样本点更准确的邻域关系, 进而基于规范变量分析建立每个子流程的局部动态监测模型; 最后, 采用贝叶斯推理建立全局的动态过程监测模型, 通过带钢热轧实际过程故障数据验证了该方法的有效性.
英文摘要
      Process monitoring technology is an effective measure to ensure the safety and efficiency of the hot strip mill plant-wide process. Considering the “nonlinear, multimode, dynamic”characteristics of the hot strip mill process, a weighted difference-modified neighborhood preserving embedding-canonical variable analysis (WD-MNPE-CVA) method for dynamic process monitoring of plant-wide process is proposed in this paper. Firstly, in view of the nonlinear and multimode characteristics existing in the process data, the weighted difference method is used to preprocess the process data. Then the plant-wide process is divided based on the mechanism knowledge. An improved neighborhood preserving embedding algorithm is developed to obtain more accurate neighborhood relationship of each sample point based on Euclidean distance and cosine distance between sample points, and then establish local dynamic monitoring model of each subprocess based on canonical variable analysis. Finally, a global dynamic process monitoring model is established by Bayesian inference, and the effectiveness of the proposed method is verified by the actual fault data of hot strip mill process.