引用本文:刘美枝,孔祥玉,安秋生,罗家宇.双空间特征自适应融合的故障检测方法[J].控制理论与应用,2025,42(9):1721~1732.[点击复制]
LIU Mei-zhi,KONG Xiang-yu,AN Qiu-sheng,LUO Jia-yu.Fault detection method with adaptive fusion of dual-space features[J].Control Theory & Applications,2025,42(9):1721~1732.[点击复制]
双空间特征自适应融合的故障检测方法
Fault detection method with adaptive fusion of dual-space features
摘要点击 3246  全文点击 164  投稿时间：2023-07-18  修订日期：2024-12-07
查看全文  查看/发表评论  下载PDF阅读器   HTML
DOI编号  10.7641/CTA.2024.30492
  2025,42(9):1721-1732
中文关键词  故障检测  特征提取  混合相关性  贝叶斯推理  统计指标
英文关键词  fault detection  feature extraction  hybrid correlations  Bayesian inference  statistical index
基金项目  国家自然科学基金项目(62273354,61673387),山西省高等学校科技创新项目(2022L434)资助.
作者单位E-mail
刘美枝 火箭军工程大学 导弹工程学院 lmzdtdx@163.com 
孔祥玉* 火箭军工程大学 导弹工程学院 xiangyukong01@163.com 
安秋生 山西师范大学 数学与计算机科学学院  
罗家宇 火箭军工程大学 导弹工程学院  
中文摘要
      对于大型复杂工业过程,因其结构复杂,过程变量往往呈现混合相关性,单一模型无法精确表征变量之间 的混合相关性,导致故障检测中存在大量漏报或误报.针对该问题,本文提出一种双空间特征自适应融合的故障检 测方法.首先,采用分层级联特征提取策略,分别在原始数据空间和残差核空间提取高斯线性特征和非高斯非线性 特征. 其次,采用贝叶斯推理将不同空间的监测统计指标转换为故障概率,并设计自适应概率加权策略,进而构造 总体概率统计指标以监测过程运行状态.最后,通过数值仿真和田纳西–伊仕曼过程,验证所提算法的可行性和有 效性.
英文摘要
      Due to the complex structure of the large complex industrial processes, the process variables often exhibit hybrid correlations. A single model cannot accurately represent the hybrid correlations between variables, resulting in a large number of missed alarms or false alarms in the fault detection. To address this problem, a fault detection method with adaptive fusion of dual-space features is proposed. Firstly, the Gaussian linear features and non-Gaussian nonlinear features are extracted in the original data space and the residual kernel space, respectively, using a hierarchical feature extraction strategy. Then, the Bayesian inference is utilized to convert the monitoring statistics from different spaces into failure probabilities, and an adaptive probabilistic weighting strategy is designed to construct the total probabilistic statistical indices for monitoring the process operation status. Finally, several experiments on a numerical simulation and the Tennessee Eastman benchmark process are presented to demonstrate the feasibility and effectiveness of the proposed method.