Adjustable Multimode Monitoring With Hybrid Variables and Its Application in a Thermal Power Plant

Adjustable Multimode Monitoring With Hybrid Variables and Its Application in a Thermal Power Plant
复制标题

混合变量可调多模式监测及其在火电厂中的应用

DOI:
10.1109/tii.2022.3157927
复制
发表时间:
2023-02
影响因子:
12.3
通讯作者:
Maoyin Chen
Maoyin Chen
中科院分区:
计算机科学1区
文献类型:
--
作者:
Min Wang;Donghua Zhou;Maoyin Chen

文献摘要

参考文献

被引文献

相似文献

多工况已成为影响实际工业过程监控性能的关键因素。具有混合变量(包含连续变量和二进制变量)的多模式的监测更加棘手。此外,由于生产策略、物料、负荷等因素的影响,训练数据的标签信息可能不可用,在系统的连续运行过程中,可能出现新的模式或收集到的模式可能消失。因此,本文提出了一种混合变量可调多模式监控(AMMHV)模型。在AMMHV中,当标签信息未知时,期望最大化算法用于参数估计。AMMHV不仅可以在不需要训练样本标签信息的情况下有效地进行混合变量的多模态过程监控,而且可以在运行模式发生变化时无需再训练即可进行更新。采用增量学习策略对模型进行扩展,使其对新到达模式具有良好的监测性能。如果原始收集的模式在运行过程中不再出现,AMMHV可以通过压缩冗余的无关信息来提高剩余模式的监测精度。最后,通过算例和火电厂过程仿真,充分证明了AMMHV的优越性。
Multiple operating modes have become a key factor affecting the monitoring performance of practical industrial processes. The monitoring of multiple modes with hybrid variables (containing continuous and binary variables) is more intractable. In addition, the label information of the training data may be unavailable, and new modes may arrive or collected modes may disappear in continuous running of the system owing to the influence of production strategies, materials, loads, etc. Therefore, this article proposes an adjustable multimode monitoring with hybrid variables (AMMHV) model. In AMMHV, the expectation maximization algorithm is utilized for parameter estimation when the label information is unknown. AMMHV can not only effectively conduct the multimode process monitoring of hybrid variables without the label information of training samples, but also be updated without retraining when operation modes change. The incremental learning strategy is adopted to extend the model to give it outstanding monitoring performance for new arriving modes. If the originally collected modes no longer appear during operation, AMMHV can improve the monitoring accuracy of the remaining modes by condensing redundant irrelevant information. Finally, the superiority of AMMHV is fully demonstrated first on a numerical example and then on a process of a thermal power plant.
基于切换自回归动态潜变量模型的多模式过程监控
DOI: 10.1109/tie.2018.2803727
发表时间: 2018-02
影响因子: 7.7
作者:
Zhou Le;Zheng Jiaqi;Ge Zhiqiang;Song Zhihuan;Shan Shengdao
通讯作者: Shan Shengdao
DOI: 10.1007/1-4020-2295-6_2
发表时间: 2001
期刊: --
影响因子: --
作者:
M. Collins
通讯作者: M. Collins
DOI: 10.1007/s10994-018-5699-z
发表时间: 2018
期刊: Machine Learning
影响因子: 7.5
作者:
Enric Junqué de Fortuny;David Martens;F. Provost
通讯作者: Enric Junqué de Fortuny;David Martens;F. Provost
DOI: --
发表时间: 2008
期刊: --
影响因子: --
作者:
H. Langseth;Thomas D. Nielsen;R. Rumí;A. Salmerón
通讯作者: H. Langseth;Thomas D. Nielsen;R. Rumí;A. Salmerón
基于共性和个体特征提取的多模式过程监控方法及其在精轧过程中的应用
DOI: 10.1109/tii.2018.2799600
发表时间: 2018-11-01
影响因子: 12.3
作者:
Zhang, Kai;Peng, Kaixiang;Dong, Jie
通讯作者: Dong, Jie