引用本文: | 乔俊飞,孙子健,汤健.面向工业过程软测量建模的概念漂移检测综述[J].控制理论与应用,2021,38(8):1159~1174.[点击复制] |
QIAO Jun-fei,SUN Zi-jian,TANG Jian.Overview of concept drift detection for industrial process soft sensor modeling[J].Control Theory and Technology,2021,38(8):1159~1174.[点击复制] |
|
面向工业过程软测量建模的概念漂移检测综述 |
Overview of concept drift detection for industrial process soft sensor modeling |
摘要点击 2720 全文点击 943 投稿时间:2020-06-10 修订日期:2021-06-10 |
查看全文 查看/发表评论 下载PDF阅读器 |
DOI编号 10.7641/CTA.2021.00334 |
2021,38(8):1159-1174 |
中文关键词 工业过程 软测量 概念漂移 过程变量 样本分布 |
英文关键词 industrial process soft sensor concept drift process variable sample distribution |
基金项目 国家自然科学基金项目(61703089, 61890930–5), 国家科技重大专项项目(2018YFC1900801)资助. |
|
中文摘要 |
基于数据驱动的软测量模型广泛用于工业过程中产品质量与环保指标等难测参数的在线测量, 该过程中
存在的概念漂移问题易导致模型精度下降. 如何有效识别过程概念变化并精准检测漂移样本是提高模型测量性能
的关键. 本文总结并分析目前漂移检测的研究思路与进展, 为面向工业过程软测量的漂移检测算法提供设计指导.
首先, 介绍了概念漂移的通常定义与其在工业过程中的表现形式; 然后, 从检测依据与检测对象两个视角分析了目
前具有代表性的检测方法; 接着, 讨论了这些算法的技术特点和当前工业领域的研究难点; 最后, 展望了未来的研
究方向. |
英文摘要 |
Data-driven soft sensor models are widely used for online measurement of difficult-to-measure parameters
such as product quality and environmental protection indicators in industrial processes, and the concept drift in this process
will lead to a decrease in model accuracy. Effective recognition of process concept changes and accurate detection of drift
samples are the keys to improving model measure performance. This paper summarizes and analyzes the current research
ideas and progress of drift detection, and provides design guidance for drift detection algorithms for industrial soft sensor
modeling. First, the general definition of concept drift and its manifestation in the industrial process are introduced. Then,
the current representative research methods are analyzed from the perspective of detection object and detection basis.
Next, the technical characteristics of different algorithm strategies and the current research difficulties in the industrial field
according to the literature are discussed. Finally, suggestions for future research directions are given. |
|
|
|
|
|