首页|面向复杂工业过程的虚拟样本生成综述

面向复杂工业过程的虚拟样本生成综述

扫码查看
用于复杂工业过程难测运行指标和异常故障建模的样本具有量少稀缺、分布不平衡以及内涵机理知识匮乏等特性.虚拟样本生成(Virtual sample generation,VSG)作为扩充建模样本数量及其涵盖空间的技术,已成为解决上述问题的主要手段之一,但已有研究还存在缺乏理论支撑、分类准则与应用边界模糊等问题.本文在描述复杂工业过程难测运行指标和异常故障建模所存在问题的基础上,梳理虚拟样本定义及其内涵,给出面向工业过程回归与分类问题的VSG实现流程;接着,从样本覆盖区域、实现流程与推广应用等方向进行综述;然后,分析讨论VSG的下一步研究方向;最后,对全文进行总结并给出未来挑战.
A Survey of Virtual Sample Generation for Complex Industrial Processes
The modeling samples for difficulty to measure operation indexes and abnormal faults of complex indus-trial processes usually have the characteristics of sparse quantity,unbalanced distribution,and lack of connotation mechanism knowledge.Virtual sample generation(VSG)is a technology to expand the space and quantity of model-ing samples and has become one of the main ways to solve the formerly mentioned difficulties.However,there are still some problems in the existing research results,such as the lack of theoretical support,the unclear of category criterion and the application boundary.First,the existing problems for difficulty to measure operational indexes and abnormal fault modeling of complex industrial processes are described.The definition of virtual samples and the connotation of virtual samples are combed,and the VSG implementation process for the regression and classifica-tion problems is provided.Second,the research status is summarized from the sample coverage area,implementa-tion process,and application.Third,further research direction is analyzed and discussed.Finally,the summary and future challenges are given out.

Complex industrial processvirtual sample generation(VSG)data-driven modelingsample coverage area

汤健、崔璨麟、夏恒、乔俊飞

展开 >

北京工业大学信息学部 北京 100124

北京工业大学智慧环保北京实验室 北京 100124

北京工业大学智能感知与自主控制教育部工程研究中心 北京 100124

复杂工业过程 虚拟样本生成 数据驱动建模 样本覆盖区域

国家自然科学基金国家自然科学基金北京市自然科学基金科技创新2030新一代人工智能重大项目科技创新2030新一代人工智能重大项目

620730066217312042120322021ZD01123012021ZD0112302

2024

自动化学报
中国自动化学会 中国科学院自动化研究所

自动化学报

CSTPCD北大核心
影响因子:1.762
ISSN:0254-4156
年,卷(期):2024.50(4)
  • 164